Skills skill-20260619-103648

Skills Catalog (39 skills)

Download individual files or grab all-skills.zip for the full bundle.

Skill	Description
add-skill	Create new Claude Code skills with proper structure. Use when adding a skill or slash command.
agent-demo-recorder	Record demo GIFs/MP4s of agent TUI sessions (Claude Code, Codex CLI, other agent CLIs), synchronized via a Stop-hook sentinel so the recording knows exactly when each response finishes. Two modes - scripted (VHS tape, repeatable) and live/adaptive (tmux + asciinema, where the outer Claude reads each inner response and decides the next prompt). Use when the user wants to record, capture, or make a demo/GIF/video of a Claude Code or Codex session, create a .tape file, drive a nested agent session interactively, or asks about VHS/asciinema recording of an agent CLI.
ai-engineer	Build LLM apps, RAG systems, and prompt pipelines. Use for AI-powered features.
architect	Design system architecture and component interfaces. Use for architectural decisions.
argdown	Author and iterate on .argdown argument-map files. Use when the user asks to "create an argdown", structure a debate / argument / pro-con map, lint a .argdown file, or export an argument map to SVG/DOT/HTML/JSON via the argdown CLI. Workflow — draft, then run argdown on the file to lint with line/col errors, fix, then argdown map -f svg to render.
cf-gate	>-
checkpoint	Git checkpoint management. Use when starting risky changes or needing recovery points.
code-review	Run a comprehensive code review
codex-imagegen	Generate an image via Codex CLI (OpenAI gpt-image-1) and save to a local path. Use when user asks to create/draw/generate an image AND save it (e.g. "draw X, save to images/y.png", "用 codex 生圖"). Requires codex login + $OPENAI_API_KEY.
context-report	Analyze Claude Code context efficiency. Use when evaluating session token usage.
debug	Debug errors and unexpected behavior with log analysis. Use for issues and error messages.
deepseek-webgui	DeepSeek client via the private chat.deepseek.com API (browser-exported userToken), not the official platform.deepseek.com API. Use for personal webgui automation, x-ds-pow-response / DeepSeekHashV1 POW solving, or SSE THINK/TOOL_SEARCH stream parsing.
defer	Defer execution of a slash-command or prompt until a timer elapses. Starts a background polling timer that prints "TIMER DONE" on stdout, then executes the deferred prompt.
dev-docs	Create strategic plan and dev docs. Use when starting large multi-session tasks.
dx-optimizer	Improve developer experience and tooling. Use when setting up projects or reducing friction.
end-to-end-study	End-to-end data-first research pipeline — find an underutilised public dataset, pick the publishable claim, target a journal, ship LaTeX manuscript + tagged GitHub release. Use for computational-bio / bioinformatics / clinical-genomics on TCGA, GEO, GDC, cBioPortal, or when user says "end-to-end paper" / "what's publishable here".
env-dx	Scan environment for dev readiness — tools, runtimes, permissions. Use in new containers.
funnel-config	Manage Tailscale Funnel routes. Use when configuring tunnels or external HTTPS access.
hook	Enable, disable, and manage Claude Code hooks. Use for hook debugging or configuration.
human-write	Scan and replace AI-flavored vocabulary in English text. Use when polishing writing.
kimi-webbridge
mail	Read Mail.app inboxes and create Reminders for actionable items. Use for email triage.
map	Generate semantic codebase symbol map. Use when navigating unfamiliar code or before refactoring.
perf	Profile and optimize bottlenecks. Use for performance issues or caching strategies.
prime	Load codebase context by analyzing structure and README. Use when starting a new session.
prompt-engineer	Optimize prompts for LLMs. Use when crafting system prompts or improving agent performance.
publish-the-skill	Publish a skill folder as a .skill package to GitHub. Use when distributing skills.
refactor	Refactor code for quality and maintainability. Use for cleanup and tech debt reduction.
repo-init	Initialize GitHub repo with CITATION.cff, LICENSE, README badges. Use for new repos.
research-plan-implement	Three-phase RPI workflow (Research, Plan, Implement). Use for non-trivial code changes.
retro	Session retrospective report. Use when reviewing or summarizing a work session.
sc	Unified SuperClaude workflow with subcommands. Use for structured development workflows.
search	Expert web research with advanced techniques. Use for deep research or fact verification.
security	Security audits and secure coding. Use for vulnerability detection or auth implementation.
test-auto	Create unit, integration, and e2e test suites. Use when setting up or improving tests.
todoist	Todoist CRUD via API v1 — tasks (due + deadline), projects, sections, labels, comments, reminders. Use when user mentions Todoist, their todo list, scheduling/completing a task, "加到待辦", "今天的 Todoist".
update-dev-docs	Update dev docs before compaction. Use before ending sessions or switching tasks.
vale	Run Vale prose linter and auto-fix issues. Use when linting or proofreading markdown/text.
vm-docker	Deploy Docker services on VM with Traefik and Homepage. Use for VM container deploys.

Skills skill-20260613-193424

Skills Catalog (39 skills)

Download individual files or grab all-skills.zip for the full bundle.

Skill	Description
add-skill	Create new Claude Code skills with proper structure. Use when adding a skill or slash command.
agent-demo-recorder	Record demo GIFs/MP4s of agent TUI sessions (Claude Code, Codex CLI, other agent CLIs), synchronized via a Stop-hook sentinel so the recording knows exactly when each response finishes. Two modes - scripted (VHS tape, repeatable) and live/adaptive (tmux + asciinema, where the outer Claude reads each inner response and decides the next prompt). Use when the user wants to record, capture, or make a demo/GIF/video of a Claude Code or Codex session, create a .tape file, drive a nested agent session interactively, or asks about VHS/asciinema recording of an agent CLI.
ai-engineer	Build LLM apps, RAG systems, and prompt pipelines. Use for AI-powered features.
architect	Design system architecture and component interfaces. Use for architectural decisions.
argdown	Author and iterate on .argdown argument-map files. Use when the user asks to "create an argdown", structure a debate / argument / pro-con map, lint a .argdown file, or export an argument map to SVG/DOT/HTML/JSON via the argdown CLI. Workflow — draft, then run argdown on the file to lint with line/col errors, fix, then argdown map -f svg to render.
cf-gate	>-
checkpoint	Git checkpoint management. Use when starting risky changes or needing recovery points.
code-review	Run a comprehensive code review
codex-imagegen	Generate an image via Codex CLI (OpenAI gpt-image-1) and save to a local path. Use when user asks to create/draw/generate an image AND save it (e.g. "draw X, save to images/y.png", "用 codex 生圖"). Requires codex login + $OPENAI_API_KEY.
context-report	Analyze Claude Code context efficiency. Use when evaluating session token usage.
debug	Debug errors and unexpected behavior with log analysis. Use for issues and error messages.
deepseek-webgui	DeepSeek client via the private chat.deepseek.com API (browser-exported userToken), not the official platform.deepseek.com API. Use for personal webgui automation, x-ds-pow-response / DeepSeekHashV1 POW solving, or SSE THINK/TOOL_SEARCH stream parsing.
defer	Defer execution of a slash-command or prompt until a timer elapses. Starts a background polling timer that prints "TIMER DONE" on stdout, then executes the deferred prompt.
dev-docs	Create strategic plan and dev docs. Use when starting large multi-session tasks.
dx-optimizer	Improve developer experience and tooling. Use when setting up projects or reducing friction.
end-to-end-study	End-to-end data-first research pipeline — find an underutilised public dataset, pick the publishable claim, target a journal, ship LaTeX manuscript + tagged GitHub release. Use for computational-bio / bioinformatics / clinical-genomics on TCGA, GEO, GDC, cBioPortal, or when user says "end-to-end paper" / "what's publishable here".
env-dx	Scan environment for dev readiness — tools, runtimes, permissions. Use in new containers.
funnel-config	Manage Tailscale Funnel routes. Use when configuring tunnels or external HTTPS access.
hook	Enable, disable, and manage Claude Code hooks. Use for hook debugging or configuration.
human-write	Scan and replace AI-flavored vocabulary in English text. Use when polishing writing.
kimi-webbridge
mail	Read Mail.app inboxes and create Reminders for actionable items. Use for email triage.
map	Generate semantic codebase symbol map. Use when navigating unfamiliar code or before refactoring.
perf	Profile and optimize bottlenecks. Use for performance issues or caching strategies.
prime	Load codebase context by analyzing structure and README. Use when starting a new session.
prompt-engineer	Optimize prompts for LLMs. Use when crafting system prompts or improving agent performance.
publish-the-skill	Publish a skill folder as a .skill package to GitHub. Use when distributing skills.
refactor	Refactor code for quality and maintainability. Use for cleanup and tech debt reduction.
repo-init	Initialize GitHub repo with CITATION.cff, LICENSE, README badges. Use for new repos.
research-plan-implement	Three-phase RPI workflow (Research, Plan, Implement). Use for non-trivial code changes.
retro	Session retrospective report. Use when reviewing or summarizing a work session.
sc	Unified SuperClaude workflow with subcommands. Use for structured development workflows.
search	Expert web research with advanced techniques. Use for deep research or fact verification.
security	Security audits and secure coding. Use for vulnerability detection or auth implementation.
test-auto	Create unit, integration, and e2e test suites. Use when setting up or improving tests.
todoist	Todoist CRUD via API v1 — tasks (due + deadline), projects, sections, labels, comments, reminders. Use when user mentions Todoist, their todo list, scheduling/completing a task, "加到待辦", "今天的 Todoist".
update-dev-docs	Update dev docs before compaction. Use before ending sessions or switching tasks.
vale	Run Vale prose linter and auto-fix issues. Use when linting or proofreading markdown/text.
vm-docker	Deploy Docker services on VM with Traefik and Homepage. Use for VM container deploys.

Skills skill-20260613-152423

Skills Catalog (39 skills)

Download individual files or grab all-skills.zip for the full bundle.

Skill	Description
add-skill	Create new Claude Code skills with proper structure. Use when adding a skill or slash command.
agent-demo-recorder	Record demo GIFs/MP4s of agent TUI sessions (Claude Code, Codex CLI, other agent CLIs), synchronized via a Stop-hook sentinel so the recording knows exactly when each response finishes. Two modes - scripted (VHS tape, repeatable) and live/adaptive (tmux + asciinema, where the outer Claude reads each inner response and decides the next prompt). Use when the user wants to record, capture, or make a demo/GIF/video of a Claude Code or Codex session, create a .tape file, drive a nested agent session interactively, or asks about VHS/asciinema recording of an agent CLI.
ai-engineer	Build LLM apps, RAG systems, and prompt pipelines. Use for AI-powered features.
architect	Design system architecture and component interfaces. Use for architectural decisions.
argdown	Author and iterate on .argdown argument-map files. Use when the user asks to "create an argdown", structure a debate / argument / pro-con map, lint a .argdown file, or export an argument map to SVG/DOT/HTML/JSON via the argdown CLI. Workflow — draft, then run argdown on the file to lint with line/col errors, fix, then argdown map -f svg to render.
cf-gate	>-
checkpoint	Git checkpoint management. Use when starting risky changes or needing recovery points.
code-review	Run a comprehensive code review
codex-imagegen	Generate an image via Codex CLI (OpenAI gpt-image-1) and save to a local path. Use when user asks to create/draw/generate an image AND save it (e.g. "draw X, save to images/y.png", "用 codex 生圖"). Requires codex login + $OPENAI_API_KEY.
context-report	Analyze Claude Code context efficiency. Use when evaluating session token usage.
debug	Debug errors and unexpected behavior with log analysis. Use for issues and error messages.
deepseek-webgui	DeepSeek client via the private chat.deepseek.com API (browser-exported userToken), not the official platform.deepseek.com API. Use for personal webgui automation, x-ds-pow-response / DeepSeekHashV1 POW solving, or SSE THINK/TOOL_SEARCH stream parsing.
defer	Defer execution of a slash-command or prompt until a timer elapses. Starts a background polling timer that prints "TIMER DONE" on stdout, then executes the deferred prompt.
dev-docs	Create strategic plan and dev docs. Use when starting large multi-session tasks.
dx-optimizer	Improve developer experience and tooling. Use when setting up projects or reducing friction.
end-to-end-study	End-to-end data-first research pipeline — find an underutilised public dataset, pick the publishable claim, target a journal, ship LaTeX manuscript + tagged GitHub release. Use for computational-bio / bioinformatics / clinical-genomics on TCGA, GEO, GDC, cBioPortal, or when user says "end-to-end paper" / "what's publishable here".
env-dx	Scan environment for dev readiness — tools, runtimes, permissions. Use in new containers.
funnel-config	Manage Tailscale Funnel routes. Use when configuring tunnels or external HTTPS access.
hook	Enable, disable, and manage Claude Code hooks. Use for hook debugging or configuration.
human-write	Scan and replace AI-flavored vocabulary in English text. Use when polishing writing.
kimi-webbridge
mail	Read Mail.app inboxes and create Reminders for actionable items. Use for email triage.
map	Generate semantic codebase symbol map. Use when navigating unfamiliar code or before refactoring.
perf	Profile and optimize bottlenecks. Use for performance issues or caching strategies.
prime	Load codebase context by analyzing structure and README. Use when starting a new session.
prompt-engineer	Optimize prompts for LLMs. Use when crafting system prompts or improving agent performance.
publish-the-skill	Publish a skill folder as a .skill package to GitHub. Use when distributing skills.
refactor	Refactor code for quality and maintainability. Use for cleanup and tech debt reduction.
repo-init	Initialize GitHub repo with CITATION.cff, LICENSE, README badges. Use for new repos.
research-plan-implement	Three-phase RPI workflow (Research, Plan, Implement). Use for non-trivial code changes.
retro	Session retrospective report. Use when reviewing or summarizing a work session.
sc	Unified SuperClaude workflow with subcommands. Use for structured development workflows.
search	Expert web research with advanced techniques. Use for deep research or fact verification.
security	Security audits and secure coding. Use for vulnerability detection or auth implementation.
test-auto	Create unit, integration, and e2e test suites. Use when setting up or improving tests.
todoist	Todoist CRUD via API v1 — tasks (due + deadline), projects, sections, labels, comments, reminders. Use when user mentions Todoist, their todo list, scheduling/completing a task, "加到待辦", "今天的 Todoist".
update-dev-docs	Update dev docs before compaction. Use before ending sessions or switching tasks.
vale	Run Vale prose linter and auto-fix issues. Use when linting or proofreading markdown/text.
vm-docker	Deploy Docker services on VM with Traefik and Homepage. Use for VM container deploys.

Skills skill-20260611-024127

Skills Catalog (38 skills)

Download individual files or grab all-skills.zip for the full bundle.

Skill	Description
add-skill	Create new Claude Code skills with proper structure. Use when adding a skill or slash command.
ai-engineer	Build LLM apps, RAG systems, and prompt pipelines. Use for AI-powered features.
architect	Design system architecture and component interfaces. Use for architectural decisions.
argdown	Author and iterate on .argdown argument-map files. Use when the user asks to "create an argdown", structure a debate / argument / pro-con map, lint a .argdown file, or export an argument map to SVG/DOT/HTML/JSON via the argdown CLI. Workflow — draft, then run argdown on the file to lint with line/col errors, fix, then argdown map -f svg to render.
cf-gate	>-
checkpoint	Git checkpoint management. Use when starting risky changes or needing recovery points.
code-review	Run a comprehensive code review
codex-imagegen	Generate an image via Codex CLI (OpenAI gpt-image-1) and save to a local path. Use when user asks to create/draw/generate an image AND save it (e.g. "draw X, save to images/y.png", "用 codex 生圖"). Requires codex login + $OPENAI_API_KEY.
context-report	Analyze Claude Code context efficiency. Use when evaluating session token usage.
debug	Debug errors and unexpected behavior with log analysis. Use for issues and error messages.
deepseek-webgui	DeepSeek client via the private chat.deepseek.com API (browser-exported userToken), not the official platform.deepseek.com API. Use for personal webgui automation, x-ds-pow-response / DeepSeekHashV1 POW solving, or SSE THINK/TOOL_SEARCH stream parsing.
defer	Defer execution of a slash-command or prompt until a timer elapses. Starts a background polling timer that prints "TIMER DONE" on stdout, then executes the deferred prompt.
dev-docs	Create strategic plan and dev docs. Use when starting large multi-session tasks.
dx-optimizer	Improve developer experience and tooling. Use when setting up projects or reducing friction.
end-to-end-study	End-to-end data-first research pipeline — find an underutilised public dataset, pick the publishable claim, target a journal, ship LaTeX manuscript + tagged GitHub release. Use for computational-bio / bioinformatics / clinical-genomics on TCGA, GEO, GDC, cBioPortal, or when user says "end-to-end paper" / "what's publishable here".
env-dx	Scan environment for dev readiness — tools, runtimes, permissions. Use in new containers.
funnel-config	Manage Tailscale Funnel routes. Use when configuring tunnels or external HTTPS access.
hook	Enable, disable, and manage Claude Code hooks. Use for hook debugging or configuration.
human-write	Scan and replace AI-flavored vocabulary in English text. Use when polishing writing.
kimi-webbridge
mail	Read Mail.app inboxes and create Reminders for actionable items. Use for email triage.
map	Generate semantic codebase symbol map. Use when navigating unfamiliar code or before refactoring.
perf	Profile and optimize bottlenecks. Use for performance issues or caching strategies.
prime	Load codebase context by analyzing structure and README. Use when starting a new session.
prompt-engineer	Optimize prompts for LLMs. Use when crafting system prompts or improving agent performance.
publish-the-skill	Publish a skill folder as a .skill package to GitHub. Use when distributing skills.
refactor	Refactor code for quality and maintainability. Use for cleanup and tech debt reduction.
repo-init	Initialize GitHub repo with CITATION.cff, LICENSE, README badges. Use for new repos.
research-plan-implement	Three-phase RPI workflow (Research, Plan, Implement). Use for non-trivial code changes.
retro	Session retrospective report. Use when reviewing or summarizing a work session.
sc	Unified SuperClaude workflow with subcommands. Use for structured development workflows.
search	Expert web research with advanced techniques. Use for deep research or fact verification.
security	Security audits and secure coding. Use for vulnerability detection or auth implementation.
test-auto	Create unit, integration, and e2e test suites. Use when setting up or improving tests.
todoist	Todoist CRUD via API v1 — tasks (due + deadline), projects, sections, labels, comments, reminders. Use when user mentions Todoist, their todo list, scheduling/completing a task, "加到待辦", "今天的 Todoist".
update-dev-docs	Update dev docs before compaction. Use before ending sessions or switching tasks.
vale	Run Vale prose linter and auto-fix issues. Use when linting or proofreading markdown/text.
vm-docker	Deploy Docker services on VM with Traefik and Homepage. Use for VM container deploys.

Skills skill-20260605-161247

Skills Catalog (37 skills)

Download individual files or grab all-skills.zip for the full bundle.

Skill	Description
add-skill	Create new Claude Code skills with proper structure. Use when adding a skill or slash command.
ai-engineer	Build LLM apps, RAG systems, and prompt pipelines. Use for AI-powered features.
architect	Design system architecture and component interfaces. Use for architectural decisions.
argdown	Author and iterate on .argdown argument-map files. Use when the user asks to "create an argdown", structure a debate / argument / pro-con map, lint a .argdown file, or export an argument map to SVG/DOT/HTML/JSON via the argdown CLI. Workflow — draft, then run argdown on the file to lint with line/col errors, fix, then argdown map -f svg to render.
checkpoint	Git checkpoint management. Use when starting risky changes or needing recovery points.
code-review	Run a comprehensive code review
codex-imagegen	Generate an image via Codex CLI (OpenAI gpt-image-1) and save to a local path. Use when user asks to create/draw/generate an image AND save it (e.g. "draw X, save to images/y.png", "用 codex 生圖"). Requires codex login + $OPENAI_API_KEY.
context-report	Analyze Claude Code context efficiency. Use when evaluating session token usage.
debug	Debug errors and unexpected behavior with log analysis. Use for issues and error messages.
deepseek-webgui	DeepSeek client via the private chat.deepseek.com API (browser-exported userToken), not the official platform.deepseek.com API. Use for personal webgui automation, x-ds-pow-response / DeepSeekHashV1 POW solving, or SSE THINK/TOOL_SEARCH stream parsing.
defer	Defer execution of a slash-command or prompt until a timer elapses. Starts a background polling timer that prints "TIMER DONE" on stdout, then executes the deferred prompt. Use when the user types /defer <duration>: <prompt> (e.g. /defer 30 mins: run @plan xxx), /defer list, /defer cancel <id>, or asks to delay/queue a one-shot prompt for later in the current session.
dev-docs	Create strategic plan and dev docs. Use when starting large multi-session tasks.
dx-optimizer	Improve developer experience and tooling. Use when setting up projects or reducing friction.
end-to-end-study	End-to-end data-first research pipeline — find an underutilised public dataset, pick the publishable claim, target a journal, ship LaTeX manuscript + tagged GitHub release. Use for computational-bio / bioinformatics / clinical-genomics on TCGA, GEO, GDC, cBioPortal, or when user says "end-to-end paper" / "what's publishable here".
env-dx	Scan environment for dev readiness — tools, runtimes, permissions. Use in new containers.
funnel-config	Manage Tailscale Funnel routes. Use when configuring tunnels or external HTTPS access.
hook	Enable, disable, and manage Claude Code hooks. Use for hook debugging or configuration.
human-write	Scan and replace AI-flavored vocabulary in English text. Use when polishing writing.
kimi-webbridge
mail	Read Mail.app inboxes and create Reminders for actionable items. Use for email triage.
map	Generate semantic codebase symbol map. Use when navigating unfamiliar code or before refactoring.
perf	Profile and optimize bottlenecks. Use for performance issues or caching strategies.
prime	Load codebase context by analyzing structure and README. Use when starting a new session.
prompt-engineer	Optimize prompts for LLMs. Use when crafting system prompts or improving agent performance.
publish-the-skill	Publish a skill folder as a .skill package to GitHub. Use when distributing skills.
refactor	Refactor code for quality and maintainability. Use for cleanup and tech debt reduction.
repo-init	Initialize GitHub repo with CITATION.cff, LICENSE, README badges. Use for new repos.
research-plan-implement	Three-phase RPI workflow (Research, Plan, Implement). Use for non-trivial code changes.
retro	Session retrospective report. Use when reviewing or summarizing a work session.
sc	Unified SuperClaude workflow with subcommands. Use for structured development workflows.
search	Expert web research with advanced techniques. Use for deep research or fact verification.
security	Security audits and secure coding. Use for vulnerability detection or auth implementation.
test-auto	Create unit, integration, and e2e test suites. Use when setting up or improving tests.
todoist	Todoist CRUD via API v1 — tasks (due + deadline), projects, sections, labels, comments, reminders. Use when user mentions Todoist, their todo list, scheduling/completing a task, "加到待辦", "今天的 Todoist".
update-dev-docs	Update dev docs before compaction. Use before ending sessions or switching tasks.
vale	Run Vale prose linter and auto-fix issues. Use when linting or proofreading markdown/text.
vm-docker	Deploy Docker services on VM with Traefik and Homepage. Use for VM container deploys.

Skills skill-20260514-201540

Skills Catalog (36 skills)

Download individual files or grab all-skills.zip for the full bundle.

Skill	Description
add-skill	Create new Claude Code skills with proper structure. Use when adding a skill or slash command.
ai-engineer	Build LLM apps, RAG systems, and prompt pipelines. Use for AI-powered features.
architect	Design system architecture and component interfaces. Use for architectural decisions.
argdown	Author and iterate on .argdown argument-map files. Use when the user asks to "create an argdown", structure a debate / argument / pro-con map, lint a .argdown file, or export an argument map to SVG/DOT/HTML/JSON via the argdown CLI. Workflow — draft, then run argdown on the file to lint with line/col errors, fix, then argdown map -f svg to render.
checkpoint	Git checkpoint management. Use when starting risky changes or needing recovery points.
code-review	Run a comprehensive code review
codex-imagegen	Generate an image via Codex CLI (OpenAI gpt-image-1) and save to a local path. Use when user asks to create/draw/generate an image AND save it (e.g. "draw X, save to images/y.png", "用 codex 生圖"). Requires codex login + $OPENAI_API_KEY.
context-report	Analyze Claude Code context efficiency. Use when evaluating session token usage.
debug	Debug errors and unexpected behavior with log analysis. Use for issues and error messages.
deepseek-webgui	DeepSeek client via the private chat.deepseek.com API (browser-exported userToken), not the official platform.deepseek.com API. Use for personal webgui automation, x-ds-pow-response / DeepSeekHashV1 POW solving, or SSE THINK/TOOL_SEARCH stream parsing.
defer	Defer execution of a slash-command or prompt until a timer elapses. Starts a background polling timer that prints "TIMER DONE" on stdout, then executes the deferred prompt. Use when the user types /defer <duration>: <prompt> (e.g. /defer 30 mins: run @plan xxx), /defer list, /defer cancel <id>, or asks to delay/queue a one-shot prompt for later in the current session.
dev-docs	Create strategic plan and dev docs. Use when starting large multi-session tasks.
dx-optimizer	Improve developer experience and tooling. Use when setting up projects or reducing friction.
end-to-end-study	End-to-end data-first research pipeline — find an underutilised public dataset, pick the publishable claim, target a journal, ship LaTeX manuscript + tagged GitHub release. Use for computational-bio / bioinformatics / clinical-genomics on TCGA, GEO, GDC, cBioPortal, or when user says "end-to-end paper" / "what's publishable here".
env-dx	Scan environment for dev readiness — tools, runtimes, permissions. Use in new containers.
funnel-config	Manage Tailscale Funnel routes. Use when configuring tunnels or external HTTPS access.
hook	Enable, disable, and manage Claude Code hooks. Use for hook debugging or configuration.
human-write	Scan and replace AI-flavored vocabulary in English text. Use when polishing writing.
mail	Read Mail.app inboxes and create Reminders for actionable items. Use for email triage.
map	Generate semantic codebase symbol map. Use when navigating unfamiliar code or before refactoring.
perf	Profile and optimize bottlenecks. Use for performance issues or caching strategies.
prime	Load codebase context by analyzing structure and README. Use when starting a new session.
prompt-engineer	Optimize prompts for LLMs. Use when crafting system prompts or improving agent performance.
publish-the-skill	Publish a skill folder as a .skill package to GitHub. Use when distributing skills.
refactor	Refactor code for quality and maintainability. Use for cleanup and tech debt reduction.
repo-init	Initialize GitHub repo with CITATION.cff, LICENSE, README badges. Use for new repos.
research-plan-implement	Three-phase RPI workflow (Research, Plan, Implement). Use for non-trivial code changes.
retro	Session retrospective report. Use when reviewing or summarizing a work session.
sc	Unified SuperClaude workflow with subcommands. Use for structured development workflows.
search	Expert web research with advanced techniques. Use for deep research or fact verification.
security	Security audits and secure coding. Use for vulnerability detection or auth implementation.
test-auto	Create unit, integration, and e2e test suites. Use when setting up or improving tests.
todoist	Todoist CRUD via API v1 — tasks (due + deadline), projects, sections, labels, comments, reminders. Use when user mentions Todoist, their todo list, scheduling/completing a task, "加到待辦", "今天的 Todoist".
update-dev-docs	Update dev docs before compaction. Use before ending sessions or switching tasks.
vale	Run Vale prose linter and auto-fix issues. Use when linting or proofreading markdown/text.
vm-docker	Deploy Docker services on VM with Traefik and Homepage. Use for VM container deploys.

Skills skill-20260513-012925

Skills Catalog (35 skills)

Download individual files or grab all-skills.zip for the full bundle.

Skill	Description
add-skill	Create new Claude Code skills with proper structure. Use when adding a skill or slash command.
ai-engineer	Build LLM apps, RAG systems, and prompt pipelines. Use for AI-powered features.
architect	Design system architecture and component interfaces. Use for architectural decisions.
argdown	Author and iterate on .argdown argument-map files. Use when the user asks to "create an argdown", structure a debate / argument / pro-con map, lint a .argdown file, or export an argument map to SVG/DOT/HTML/JSON via the argdown CLI. Workflow — draft, then run argdown on the file to lint with line/col errors, fix, then argdown map -f svg to render.
checkpoint	Git checkpoint management. Use when starting risky changes or needing recovery points.
code-review	Run a comprehensive code review
codex-imagegen	Generate an image via Codex CLI (OpenAI gpt-image-1) and save to a local path. Use when user asks to create/draw/generate an image AND save it (e.g. "draw X, save to images/y.png", "用 codex 生圖"). Requires codex login + $OPENAI_API_KEY.
context-report	Analyze Claude Code context efficiency. Use when evaluating session token usage.
debug	Debug errors and unexpected behavior with log analysis. Use for issues and error messages.
deepseek-webgui	DeepSeek client via the private chat.deepseek.com API (browser-exported userToken), not the official platform.deepseek.com API. Use for personal webgui automation, x-ds-pow-response / DeepSeekHashV1 POW solving, or SSE THINK/TOOL_SEARCH stream parsing.
dev-docs	Create strategic plan and dev docs. Use when starting large multi-session tasks.
dx-optimizer	Improve developer experience and tooling. Use when setting up projects or reducing friction.
end-to-end-study	End-to-end data-first research pipeline — find an underutilised public dataset, pick the publishable claim, target a journal, ship LaTeX manuscript + tagged GitHub release. Use for computational-bio / bioinformatics / clinical-genomics on TCGA, GEO, GDC, cBioPortal, or when user says "end-to-end paper" / "what's publishable here".
env-dx	Scan environment for dev readiness — tools, runtimes, permissions. Use in new containers.
funnel-config	Manage Tailscale Funnel routes. Use when configuring tunnels or external HTTPS access.
hook	Enable, disable, and manage Claude Code hooks. Use for hook debugging or configuration.
human-write	Scan and replace AI-flavored vocabulary in English text. Use when polishing writing.
mail	Read Mail.app inboxes and create Reminders for actionable items. Use for email triage.
map	Generate semantic codebase symbol map. Use when navigating unfamiliar code or before refactoring.
perf	Profile and optimize bottlenecks. Use for performance issues or caching strategies.
prime	Load codebase context by analyzing structure and README. Use when starting a new session.
prompt-engineer	Optimize prompts for LLMs. Use when crafting system prompts or improving agent performance.
publish-the-skill	Publish a skill folder as a .skill package to GitHub. Use when distributing skills.
refactor	Refactor code for quality and maintainability. Use for cleanup and tech debt reduction.
repo-init	Initialize GitHub repo with CITATION.cff, LICENSE, README badges. Use for new repos.
research-plan-implement	Three-phase RPI workflow (Research, Plan, Implement). Use for non-trivial code changes.
retro	Session retrospective report. Use when reviewing or summarizing a work session.
sc	Unified SuperClaude workflow with subcommands. Use for structured development workflows.
search	Expert web research with advanced techniques. Use for deep research or fact verification.
security	Security audits and secure coding. Use for vulnerability detection or auth implementation.
test-auto	Create unit, integration, and e2e test suites. Use when setting up or improving tests.
todoist	Todoist CRUD via API v1 — tasks (due + deadline), projects, sections, labels, comments, reminders. Use when user mentions Todoist, their todo list, scheduling/completing a task, "加到待辦", "今天的 Todoist".
update-dev-docs	Update dev docs before compaction. Use before ending sessions or switching tasks.
vale	Run Vale prose linter and auto-fix issues. Use when linting or proofreading markdown/text.
vm-docker	Deploy Docker services on VM with Traefik and Homepage. Use for VM container deploys.

Skills skill-20260512-190251

Skills Catalog (34 skills)

Download individual files or grab all-skills.zip for the full bundle.

Skill	Description
add-skill	Create new Claude Code skills with proper structure. Use when adding a skill or slash command.
ai-engineer	Build LLM apps, RAG systems, and prompt pipelines. Use for AI-powered features.
architect	Design system architecture and component interfaces. Use for architectural decisions.
checkpoint	Git checkpoint management. Use when starting risky changes or needing recovery points.
code-review	Run a comprehensive code review
codex-imagegen	Generate an image and write it to a local file by delegating to the Codex CLI agent, which calls OpenAI's images API (gpt-image-1) and saves the result. Use when the user asks for an image to be created/drawn/generated AND saved to a path (e.g. "幫我生一張戴墨鏡的柴犬，存成 tmp/shiba.png", "draw me X and save to images/y.png", "用 codex 生圖"). Requires codex login AND $OPENAI_API_KEY set in the environment.
context-report	Analyze Claude Code context efficiency. Use when evaluating session token usage.
debug	Debug errors and unexpected behavior with log analysis. Use for issues and error messages.
deepseek-webgui	Talk to DeepSeek through its private chat.deepseek.com API (the same one the web UI uses) with a browser-exported userToken, instead of the official platform.deepseek.com OpenAI-compatible API. Use when the user wants to drive their personal/free DeepSeek webgui account from a script or TUI, mentions reusing browser cookies, asks about the x-ds-pow-response POW header, the DeepSeekHashV1 algorithm, the SSE streaming format with THINK / TOOL_SEARCH fragments, or wants to integrate the webgui backend into another tool (e.g. DeepSeek-TUI). Bundles a SHA3 WASM POW solver run via wasmtime, an httpx-based client, and an SSE patch-stream parser.
dev-docs	Create strategic plan and dev docs. Use when starting large multi-session tasks.
dx-optimizer	Improve developer experience and tooling. Use when setting up projects or reducing friction.
end-to-end-study	Data-first reproducible research workflow. Given a topic (or none), find the best underutilised public dataset, identify the low-hanging-fruit claim inside it, target the highest-acceptance-probability journal, fetch that journal's author instructions, design method under standard-of-rigor checklist, analyse, write reviewer-and-reader-oriented LaTeX + BibTeX manuscript matching the target-journal style, and ship to a private GitHub repo with CI-built tagged releases bundling PDF + .tex. Use when the user says "end-to-end paper", "take topic to publication", "find a paper in this dataset", "what's publishable here", or asks for a full research pipeline from idea to a tagged release. Good fit for computational-biology, bioinformatics, and clinical-genomics studies on public datasets (TCGA, BeatAML, GEO, GDC, UCSC Xena, cBioPortal).
env-dx	Scan environment for dev readiness — tools, runtimes, permissions. Use in new containers.
funnel-config	Manage Tailscale Funnel routes. Use when configuring tunnels or external HTTPS access.
hook	Enable, disable, and manage Claude Code hooks. Use for hook debugging or configuration.
human-write	Scan and replace AI-flavored vocabulary in English text. Use when polishing writing.
mail	Read Mail.app inboxes and create Reminders for actionable items. Use for email triage.
map	Generate semantic codebase symbol map. Use when navigating unfamiliar code or before refactoring.
perf	Profile and optimize bottlenecks. Use for performance issues or caching strategies.
prime	Load codebase context by analyzing structure and README. Use when starting a new session.
prompt-engineer	Optimize prompts for LLMs. Use when crafting system prompts or improving agent performance.
publish-the-skill	Publish a skill folder as a .skill package to GitHub. Use when distributing skills.
refactor	Refactor code for quality and maintainability. Use for cleanup and tech debt reduction.
repo-init	Initialize GitHub repo with CITATION.cff, LICENSE, README badges. Use for new repos.
research-plan-implement	Three-phase RPI workflow (Research, Plan, Implement). Use for non-trivial code changes.
retro	Session retrospective report. Use when reviewing or summarizing a work session.
sc	Unified SuperClaude workflow with subcommands. Use for structured development workflows.
search	Expert web research with advanced techniques. Use for deep research or fact verification.
security	Security audits and secure coding. Use for vulnerability detection or auth implementation.
test-auto	Create unit, integration, and e2e test suites. Use when setting up or improving tests.
todoist	CRUD operations on the user's Todoist — list/create/update/close/delete tasks (incl. due + deadline), projects, sections, labels, comments, and reminders via the Todoist API v1. Use when the user asks about Todoist, their todo list, adding/completing/rescheduling a task, setting a deadline or reminder, managing projects or labels, or says things like "加到待辦", "今天的 Todoist", "把這個工作排到 Todoist".
update-dev-docs	Update dev docs before compaction. Use before ending sessions or switching tasks.
vale	Run Vale prose linter and auto-fix issues. Use when linting or proofreading markdown/text.
vm-docker	Deploy Docker services on VM with Traefik and Homepage. Use for VM container deploys.

Skills skill-20260512-171403

Skills Catalog (34 skills)

Download individual files or grab all-skills.zip for the full bundle.

Skill	Description
add-skill	Create new Claude Code skills with proper structure. Use when adding a skill or slash command.
ai-engineer	Build LLM apps, RAG systems, and prompt pipelines. Use for AI-powered features.
architect	Design system architecture and component interfaces. Use for architectural decisions.
checkpoint	Git checkpoint management. Use when starting risky changes or needing recovery points.
code-review	Run a comprehensive code review
codex-imagegen	Generate an image and write it to a local file by delegating to the Codex CLI agent, which calls OpenAI's images API (gpt-image-1) and saves the result. Use when the user asks for an image to be created/drawn/generated AND saved to a path (e.g. "幫我生一張戴墨鏡的柴犬，存成 tmp/shiba.png", "draw me X and save to images/y.png", "用 codex 生圖"). Requires codex login AND $OPENAI_API_KEY set in the environment.
context-report	Analyze Claude Code context efficiency. Use when evaluating session token usage.
debug	Debug errors and unexpected behavior with log analysis. Use for issues and error messages.
deepseek-webgui	Talk to DeepSeek through its private chat.deepseek.com API (the same one the web UI uses) with a browser-exported userToken, instead of the official platform.deepseek.com OpenAI-compatible API. Use when the user wants to drive their personal/free DeepSeek webgui account from a script or TUI, mentions reusing browser cookies, asks about the x-ds-pow-response POW header, the DeepSeekHashV1 algorithm, the SSE streaming format with THINK / TOOL_SEARCH fragments, or wants to integrate the webgui backend into another tool (e.g. DeepSeek-TUI). Bundles a SHA3 WASM POW solver run via wasmtime, an httpx-based client, and an SSE patch-stream parser.
dev-docs	Create strategic plan and dev docs. Use when starting large multi-session tasks.
dx-optimizer	Improve developer experience and tooling. Use when setting up projects or reducing friction.
end-to-end-study	Data-first reproducible research workflow. Given a topic (or none), find the best underutilised public dataset, identify the low-hanging-fruit claim inside it, target the highest-acceptance-probability journal, fetch that journal's author instructions, design method under standard-of-rigor checklist, analyse, write reviewer-and-reader-oriented LaTeX + BibTeX manuscript matching the target-journal style, and ship to a private GitHub repo with CI-built tagged releases bundling PDF + .tex. Use when the user says "end-to-end paper", "take topic to publication", "find a paper in this dataset", "what's publishable here", or asks for a full research pipeline from idea to a tagged release. Good fit for computational-biology, bioinformatics, and clinical-genomics studies on public datasets (TCGA, BeatAML, GEO, GDC, UCSC Xena, cBioPortal).
env-dx	Scan environment for dev readiness — tools, runtimes, permissions. Use in new containers.
funnel-config	Manage Tailscale Funnel routes. Use when configuring tunnels or external HTTPS access.
hook	Enable, disable, and manage Claude Code hooks. Use for hook debugging or configuration.
human-write	Scan and replace AI-flavored vocabulary in English text. Use when polishing writing.
mail	Read Mail.app inboxes and create Reminders for actionable items. Use for email triage.
map	Generate semantic codebase symbol map. Use when navigating unfamiliar code or before refactoring.
perf	Profile and optimize bottlenecks. Use for performance issues or caching strategies.
prime	Load codebase context by analyzing structure and README. Use when starting a new session.
prompt-engineer	Optimize prompts for LLMs. Use when crafting system prompts or improving agent performance.
publish-the-skill	Publish a skill folder as a .skill package to GitHub. Use when distributing skills.
refactor	Refactor code for quality and maintainability. Use for cleanup and tech debt reduction.
repo-init	Initialize GitHub repo with CITATION.cff, LICENSE, README badges. Use for new repos.
research-plan-implement	Three-phase RPI workflow (Research, Plan, Implement). Use for non-trivial code changes.
retro	Session retrospective report. Use when reviewing or summarizing a work session.
sc	Unified SuperClaude workflow with subcommands. Use for structured development workflows.
search	Expert web research with advanced techniques. Use for deep research or fact verification.
security	Security audits and secure coding. Use for vulnerability detection or auth implementation.
test-auto	Create unit, integration, and e2e test suites. Use when setting up or improving tests.
todoist	CRUD operations on the user's Todoist — list/create/update/close/delete tasks (incl. due + deadline), projects, sections, labels, comments, and reminders via the Todoist API v1. Use when the user asks about Todoist, their todo list, adding/completing/rescheduling a task, setting a deadline or reminder, managing projects or labels, or says things like "加到待辦", "今天的 Todoist", "把這個工作排到 Todoist".
update-dev-docs	Update dev docs before compaction. Use before ending sessions or switching tasks.
vale	Run Vale prose linter and auto-fix issues. Use when linting or proofreading markdown/text.
vm-docker	Deploy Docker services on VM with Traefik and Homepage. Use for VM container deploys.

Skills skill-20260512-171223

Skills Catalog (34 skills)

Download individual files or grab all-skills.zip for the full bundle.

Skill	Description
add-skill	Create new Claude Code skills with proper structure. Use when adding a skill or slash command.
ai-engineer	Build LLM apps, RAG systems, and prompt pipelines. Use for AI-powered features.
architect	Design system architecture and component interfaces. Use for architectural decisions.
checkpoint	Git checkpoint management. Use when starting risky changes or needing recovery points.
code-review	Run a comprehensive code review
codex-imagegen	Generate an image and write it to a local file by delegating to the Codex CLI agent, which calls OpenAI's images API (gpt-image-1) and saves the result. Use when the user asks for an image to be created/drawn/generated AND saved to a path (e.g. "幫我生一張戴墨鏡的柴犬，存成 tmp/shiba.png", "draw me X and save to images/y.png", "用 codex 生圖"). Requires codex login AND $OPENAI_API_KEY set in the environment.
context-report	Analyze Claude Code context efficiency. Use when evaluating session token usage.
debug	Debug errors and unexpected behavior with log analysis. Use for issues and error messages.
deepseek-webgui	Talk to DeepSeek through its private chat.deepseek.com API (the same one the web UI uses) with a browser-exported userToken, instead of the official platform.deepseek.com OpenAI-compatible API. Use when the user wants to drive their personal/free DeepSeek webgui account from a script or TUI, mentions reusing browser cookies, asks about the x-ds-pow-response POW header, the DeepSeekHashV1 algorithm, the SSE streaming format with THINK / TOOL_SEARCH fragments, or wants to integrate the webgui backend into another tool (e.g. DeepSeek-TUI). Bundles a SHA3 WASM POW solver run via wasmtime, an httpx-based client, and an SSE patch-stream parser.
dev-docs	Create strategic plan and dev docs. Use when starting large multi-session tasks.
dx-optimizer	Improve developer experience and tooling. Use when setting up projects or reducing friction.
end-to-end-study	Data-first reproducible research workflow. Given a topic (or none), find the best underutilised public dataset, identify the low-hanging-fruit claim inside it, target the highest-acceptance-probability journal, fetch that journal's author instructions, design method under standard-of-rigor checklist, analyse, write reviewer-and-reader-oriented LaTeX + BibTeX manuscript matching the target-journal style, and ship to a private GitHub repo with CI-built tagged releases bundling PDF + .tex. Use when the user says "end-to-end paper", "take topic to publication", "find a paper in this dataset", "what's publishable here", or asks for a full research pipeline from idea to a tagged release. Good fit for computational-biology, bioinformatics, and clinical-genomics studies on public datasets (TCGA, BeatAML, GEO, GDC, UCSC Xena, cBioPortal).
env-dx	Scan environment for dev readiness — tools, runtimes, permissions. Use in new containers.
funnel-config	Manage Tailscale Funnel routes. Use when configuring tunnels or external HTTPS access.
hook	Enable, disable, and manage Claude Code hooks. Use for hook debugging or configuration.
human-write	Scan and replace AI-flavored vocabulary in English text. Use when polishing writing.
mail	Read Mail.app inboxes and create Reminders for actionable items. Use for email triage.
map	Generate semantic codebase symbol map. Use when navigating unfamiliar code or before refactoring.
perf	Profile and optimize bottlenecks. Use for performance issues or caching strategies.
prime	Load codebase context by analyzing structure and README. Use when starting a new session.
prompt-engineer	Optimize prompts for LLMs. Use when crafting system prompts or improving agent performance.
publish-the-skill	Publish a skill folder as a .skill package to GitHub. Use when distributing skills.
refactor	Refactor code for quality and maintainability. Use for cleanup and tech debt reduction.
repo-init	Initialize GitHub repo with CITATION.cff, LICENSE, README badges. Use for new repos.
research-plan-implement	Three-phase RPI workflow (Research, Plan, Implement). Use for non-trivial code changes.
retro	Session retrospective report. Use when reviewing or summarizing a work session.
sc	Unified SuperClaude workflow with subcommands. Use for structured development workflows.
search	Expert web research with advanced techniques. Use for deep research or fact verification.
security	Security audits and secure coding. Use for vulnerability detection or auth implementation.
test-auto	Create unit, integration, and e2e test suites. Use when setting up or improving tests.
todoist	CRUD operations on the user's Todoist — list/create/update/close/delete tasks (incl. due + deadline), projects, sections, labels, comments, and reminders via the Todoist API v1. Use when the user asks about Todoist, their todo list, adding/completing/rescheduling a task, setting a deadline or reminder, managing projects or labels, or says things like "加到待辦", "今天的 Todoist", "把這個工作排到 Todoist".
update-dev-docs	Update dev docs before compaction. Use before ending sessions or switching tasks.
vale	Run Vale prose linter and auto-fix issues. Use when linting or proofreading markdown/text.
vm-docker	Deploy Docker services on VM with Traefik and Homepage. Use for VM container deploys.