feat: terraform-ls code intelligence#24
Merged
Merged
Conversation
Add layer-2 terraform-ls capability facts to the public skill: - New SKILL.md "Code Intelligence" section: decision table (LSP vs manual rename vs moved block vs rg), supported/unsupported op facts, position-anchor and init prereqs. - New diagnose-table row "Navigation / safe-rename blind spots" anchored to the capability matrix; existing 9 rows untouched. - New references/code-intelligence-lsp.md with stable "###" anchors: Capability Matrix, Position-Anchored Calls, Manual Rename Workflow, Degradation Gate, When to Use rg Instead. - README: optional terraform-ls install plus generic navigation tips, upstream link, no host-specific names. - tests: Scenario 17 (Code Navigation and Safe Rename) plus matching rationalization-table row 17, counts updated for parity. Generic only: no CTF fixtures, oracles, sync mechanism, or global tool-precedence duplication. Generic LSP discipline skill and a PreToolUse enforcement gate remain documented follow-ups.
Add references/code-intelligence-lsp.md to the repo structure tree and bump SKILL.md line-count notes (277 -> 299) in the structure tree and Content Standards token-budget line.
Light pointer (layer-2 -> layer-1) now that the generic code-intelligence skill is published. SKILL.md Code Intelligence section and references/code-intelligence-lsp.md each note that the language-agnostic discipline is formalized in the standalone code-intelligence skill and that this terraform-ls layer stays self-contained if that skill is absent. No content removed; public skill remains standalone. SKILL.md 301 lines (CI <500 ok; the separate compression branch restores the <300 authoring margin).
The earlier bare "standalone code-intelligence skill" mention was weak and ambiguous. Now: - Marketplace-qualified: code-intelligence@antonbabenko, source URL, and the /plugin install command. - States plainly that it does NOT auto-load from this mention - Claude Code skills trigger on their own description, not from references elsewhere. - Name-collision guard: verify an active code-intelligence skill is this one before deferring (name is not globally unique). - Reasserts terraform-ls layer is self-contained: apply it directly; correctness never depends on another skill loading. No content removed. SKILL.md still 301 lines (CI <500 ok).
/ask-both review applied (both APPROVE). - SKILL.md + references/code-intelligence-lsp.md: cross-reference reduced to one self-contained line each. Install commands, "skills do not auto-load", and name-collision caveats are human/setup concerns and no longer burn the agent's context. references intro 1430 -> 755 chars. - README.md: setup + caveats merged into the EXISTING "## Code intelligence (optional)" section as a "### Generic discipline (any language)" subsection (GPT review: avoid a duplicate top-level section split across Contributing). - Dismissed Gemini's "available available" critical: false positive, the text is correct. No agent-load-bearing guidance lost; skill stays self-contained.
…ketplace terraform-skill and code-intelligence both install from the one antonbabenko marketplace (sourced from agent-plugins, which lists terraform-skill as an external plugin). Stop advertising '/plugin marketplace add antonbabenko/terraform-skill' - that repo's marketplace.json declares the same marketplace name and collides if added alongside agent-plugins.
antonbabenko
changed the title
antonbabenko
changed the title
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
1 participant
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.
Summary
Adds terraform-ls code-intelligence guidance to the skill (the Terraform-specific
layer of a layered design; the generic language-agnostic discipline ships
separately as the
code-intelligenceplugin inantonbabenko/agent-plugins).Also consolidates distribution onto a single marketplace and simplifies the
README.
Fact-checked against the branch on 2026-05-16 (independent verification).
Numbers below are the corrected, verified values.
Commits (10)
3a84dc0feat: terraform-ls code intelligence guidance (SKILL.md section + one diagnose-table row, new reference file, baseline scenario, rationalization row, marketplace keywords)6daa7f4docs: refresh CLAUDE.md (repo tree + line-count notes)0aef2b8docs: cross-reference the standalone code-intelligence skill9d718c4docs: harden that cross-reference (qualified name, non-auto)ca4a36adocs: trim cross-ref tokens from skill body, move setup to README3c157f4docs: promote the companion section in README512276cdocs: route install through the singleantonbabenko/agent-pluginsmarketplace160af5cdocs: simplify README wording (humanizer pass)0aa4f9adocs: de-em-dash skill + marketplace descriptions (ASCII)aa0c458docs: fix rationalization-table (second summary block was stale)Changes (8 files vs master)
skills/terraform-skill/SKILL.md: new## Code Intelligence (terraform-ls)section (decision table, capability facts, prereqs), one new diagnose-table row (Navigation / safe-rename blind spots), one-line cross-reference to the generic skill, ASCII frontmatter description.skills/terraform-skill/references/code-intelligence-lsp.md(new): terraform-ls capability matrix, position-anchored calls, manual rename, degradation gate, when-to-use-rg; stable###anchors.tests/baseline-scenarios.md: Scenario 17 (Code Navigation and Safe Rename) + count updates.tests/rationalization-table.md: row 17; both progress summaries reconciled to 17 surfaces / 16 covered / 1 open.README.md: single-marketplace install,## Recommended companion: code-intelligence,## Code intelligence (optional), plainer wording.CLAUDE.md: repo-tree + version-note refresh..claude-plugin/marketplace.json:lsp/terraform-lskeywords, ASCII description.CHANGELOG.md: release-line touch.Verified
wc -l; CI guideline<500= pass; CLAUDE.md authoring target<300is +1 over on this pre-compression base - a separaterefactor/skill-compress-scaffoldingbranch restores the margin).code-intelligence-lsp.mdanchors (#terraform-ls-capability-matrix,#degradation-gate) resolve to existing###headings.descriptionfields are ASCII (no em/en dash, curly quotes, ellipsis). The new reference file and README are fully ASCII. Note: SKILL.md still contains pre-existing em-dashes in untouched body lines (not introduced here).terraform-skill@antonbabenkoandcode-intelligence@antonbabenkothroughantonbabenko/agent-plugins, with an explicit "do not also addantonbabenko/terraform-skill" note.Before merge (blocker)
This branch predates master's v1.8.0 release. Versus master the diff shows a
version downgrade:
.claude-plugin/marketplace.jsonroot + pluginversionandSKILL.mdmetadata.versiongo1.8.0 -> 1.7.0. Squash-mergingas-is would revert master's version. Rebase the branch onto current master
(resolving the version/CHANGELOG lines in favour of master's
1.8.0, keepingthe content changes) before merge.