Improve/skill review optimization#3
Open
yogesh-tessl wants to merge 2 commits into
Open
Conversation
Hey @fatihguner 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements. Here's the full before/after:  | Skill | Before | After | Change | |-------|--------|-------|--------| | clarity-and-concision | 70% | 90% | +20% | | enemies-of-clear-thinking | 67% | 87% | +20% | | stoic-emotional-mastery | 73% | 93% | +20% | | blue-ocean-strategy | 70% | 87% | +17% | | strategic-thinking-and-alignment | 70% | 79% | +9% | ## Summary - Optimised 5 skills across leadership, writing, frameworks, thinking, and stoic categories for better actionability and workflow clarity - Added explicit numbered workflows with validation checkpoints to each skill - Preserved all domain expertise, prompts, output templates, and related skills references ## Type of Change - [ ] New skill - [ ] New output template - [ ] New diagnostic - [ ] New playbook - [x] Bug fix - [ ] Documentation - [x] Infrastructure (scripts, CI, templates, config) - [x] Other: Skill content optimisation for improved actionability and conciseness ## Layer Affected - skills/leadership, skills/writing, skills/frameworks, skills/thinking, skills/stoic ## Checklist - [x] Frontmatter complete with all required fields - [x] No prohibited phrases used - [x] No book author names referenced - [x] All cross-references point to existing files - [ ] `scripts/validate-all.sh` passes - [ ] `scripts/broken-refs.sh` reports zero broken references - [x] Writing style matches the style guide - [x] Related Skills section includes 4-7 cross-references ## Testing - Ran `tessl skill review` before and after each optimisation - Verified frontmatter YAML validity across all 5 modified skills - Confirmed all cross-references in Related Skills sections point to existing files <details> <summary>What changed in each skill</summary> **clarity-and-concision (70% → 90%)** - Added a 5-step editing workflow (Structure review → Clarity stress test → Word economy audit → Subtraction edit → Metrics check) - Removed persuasive prose sections ("Clarity as Courage", "The Research Case for Less") — Claude doesn't need convincing that concision matters - Preserved all actionable content: the 20-Word Rule, Show Don't Tell tables, Three Surgical Techniques, Before/After examples, Padding elimination list - Wrapped Use Cases and Anti-Patterns in collapsible `<details>` blocks **enemies-of-clear-thinking (67% → 87%)** - Expanded description trigger terms with natural language users would actually say ("making emotional decisions", "stuck on a failing idea", "following the crowd", "cognitive bias") - Added a 6-step diagnostic workflow with explicit validation checkpoint - Condensed each default from multi-paragraph essays to terse recognition-pattern bullets - Removed repetitive prose paragraphs after the By Stage table that restated table content - Wrapped Use Cases and Anti-Patterns in collapsible `<details>` blocks **stoic-emotional-mastery (73% → 93%)** - Converted the four-step protocol from prose to a structured table with validation column - Added emotion-specific sub-protocols (Anger, Fear, Desire) as numbered step-by-step procedures instead of philosophical essays - Added explicit workflow with feedback loop ("If validation fails, return to Step 3") - Trimmed philosophical exposition while preserving Stoic terminology and practical frameworks - Wrapped Use Cases and Anti-Patterns in collapsible `<details>` blocks **blue-ocean-strategy (70% → 87%)** - Added a 5-step workflow (Map canvas → Validate factors → Build ERRC Grid → Analyze noncustomers → Feasibility test) with validation at each step - Trimmed literary opening and condensed framework explanations Claude already knows - Preserved ERRC Grid, Strategy Canvas description, Three Tiers definitions, and all prompts - Wrapped Use Cases and Anti-Patterns in collapsible `<details>` blocks **strategic-thinking-and-alignment (70% → 79%)** - Added a 5-step workflow (Audit → Identify gaps → Design habits → Communication plan → Alignment diagnostic) - Condensed the five habits from full paragraphs to 1-2 sentence actionable summaries - Trimmed communication failures and alignment components to tight bullet points - Wrapped Use Cases and Anti-Patterns in collapsible `<details>` blocks </details> --- Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute. Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at [this Tessl guide](https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices) and ask it to optimize your skill. Ping me - [@yogesh-tessl](https://github.com/yogesh-tessl) - if you hit any snags. Thanks in advance 🙏
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hey @fatihguner 👋
158 skills across 12 categories — this is one of the most comprehensive strategic advisor skill sets I've come across. Love how you've structured the McKinsey-grade frameworks alongside Stoic philosophy — the /stoic on mode is a really creative touch. Kudos on building this for the 99% of entrepreneurs who can't hire McKinsey.
I ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the full before/after:What changed in each skill
clarity-and-concision (70% → 90%)
<details>blocksenemies-of-clear-thinking (67% → 87%)
<details>blocksstoic-emotional-mastery (73% → 93%)
<details>blocksblue-ocean-strategy (70% → 87%)
<details>blocksstrategic-thinking-and-alignment (70% → 79%)
<details>blocksHonest disclosure — I work at https://github.com/tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute.
I also added a lightweight GitHub Action that auto-reviews any skill.md changed in a PR (includes min permissions, uses a pinned action version, only posts a review comment).
This means that it gives you and your contributors an instant quality signal before you have to review yourself (no signup, no tokens needed).
Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at this Tessl guide (https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices) and ask it to optimize your skill. Ping me - @yogesh-tessl (https://github.com/yogesh-tessl) - if you hit any snags.
Thanks in advance 🙏