Improve an existing skill by checking its structure and category requirements, proposing focused fixes, and testing again. Compare failure and warning counts to decide whether to keep changes or restore the previous content.
Improve a skill via a test-fix-retest loop — static checks, targeted fixes, keep or revert on score change.
Review the instructions the agent will receive before you install.
!bash "${CLAUDE_SKILL_DIR}/../../hooks/yaml-helper.sh" resolve_config --keys automation
Automation mode: Resolve modes.automation (project.local.yaml →
project.yaml → default collaborative). Every AskUserQuestion call and
every file write follows .claude/docs/automation-modes.md
(collaborative asks always · guided major-only · autonomous logs and proceeds;
automation_always_ask categories always prompt).
Runs an improvement loop on a single skill: test → fix → retest → keep or revert.
Read the skill name from the first argument. If missing, output usage and stop:
Usage: /skill-improve [skill-name]
Example: /skill-improve tech-debt
Verify .claude/skills/[name]/SKILL.md exists. If not, stop with:
"Skill '[name]' not found."
Run /skill-test static [name] and record the baseline score:
Display to the user:
Static baseline: [N] failures, [M] warnings
Failing: Check 4 (no ask-before-write), Check 5 (no handoff)
If the static result is NOT ASSESSED (the skill file could not be read or parsed), stop and report it with its reason: there is no score to improve, and 0 FAILs from a file nobody could read is not a clean result.
If baseline is 0 FAILs and 0 WARNs, note it and proceed to Phase 2b.
Look up the skill's category: field in CCGS Skill Testing Framework/catalog.yaml.
If no category: field is found, display:
"Category: not yet assigned — skipping category checks."
and skip to Phase 3.
If category is found, run /skill-test category [name] and record the category baseline:
Display to the user:
Category baseline: [N] failures, [M] warnings ([category] rubric)
A category result of NOT ASSESSED (a rubric section the skill-test could not find or apply) is reported with its reason and is not a zero: the category dimension is then excluded from "already passes" below.
If BOTH static and category baselines are 0 FAILs and 0 WARNs — and neither is NOT ASSESSED — stop: "This skill already passes all static and category checks. No improvements needed."
Read the full skill: .claude/skills/[name]/SKILL.md and every file in its references/ folder,
if it has one — the longest skills keep each phase there. Name the file each
gap is in.
For each failing or warning static check, identify the exact gap:
context: fork set but fewer than 5 phases foundFor each failing or warning category check (if category was assigned in Phase 2b), identify the exact gap in the skill's text. For example:
modes.workflow (PR at minimal, TD + PR at standard,
all 4 at full)Show the full combined diagnosis to the user before proposing any changes.
Write a targeted fix for each failure and warning. Show the proposed changes
as clearly marked before/after blocks. Only change what is failing — do not
rewrite sections that are passing. In a skill with a references/ folder, a
fix to a phase's steps goes in that phase's references/ file, not back into
SKILL.md; the question below then names each file the fix changes.
Ask: "May I write this improved version to .claude/skills/[name]/SKILL.md?"
If the user says no, stop here.
Record the current content of each file the fix changes — the exact text, kept in this conversation — so Phase 6 can restore it.
Write the improved skill to .claude/skills/[name]/SKILL.md, and to each
references/ file the fix changes.
Re-run /skill-test static [name] and record the new static score — measured by that run, never stated from the edit.
If a category was assigned, also re-run /skill-test category [name] and record the new category score.
Display the comparison:
Static: Before [N] failures, [M] warnings → After [N'] failures, [M'] warnings
Category: Before [N] failures, [M] warnings → After [N'] failures, [M'] warnings (if applicable)
Combined: [before] → [after] (improved / no change / worse)
[before] and [after] are the Phase 6 combined counts — failures plus
warnings, both dimensions — e.g. Combined: 3 → 0 (improved).
Count the combined failure total: static FAILs + category FAILs + static WARNs + category WARNs. A re-test that comes back NOT ASSESSED (for example, the edit broke the frontmatter so the file no longer parses) is never an improvement, whatever its counts: take the "did not improve" branch below.
If combined score improved (combined failure count is lower than baseline): Report: "Score improved. Changes kept." Show a summary of what was fixed in each dimension.
If combined score is the same or worse:
Report: "Combined score did not improve."
Show what changed and why it may not have helped.
Ask: "May I restore .claude/skills/[name]/SKILL.md to the content it had before this run?"
— naming every file Phase 5 wrote.
If yes: write the content recorded in Phase 5 back to each file with Write; if no, leave the files as written. Never
git checkout it — that returns the last committed version and discards any edits
made before this run that were not yet committed.
/skill-test static all to find the next skill with failures./skill-improve [next-name] to continue the loop on another skill./skill-test audit to see overall coverage progress.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Audit an existing project's design documents and supporting files to check whether their formats work with the template's skills. Get a numbered migration plan that prioritizes gaps and required changes, rather than simply listing what exists.
Document a technical decision in an architecture decision record, or ADR. Capture its context, alternatives, and consequences, assign a record number, and distinguish a proposed decision from an accepted one so dependent work reflects its actual status.
Review whether game design requirements are covered by documented architecture decisions. Identify missing coverage, conflicting decisions, and engine compatibility concerns, with an optional matrix linking requirements to development stories and tests.
Create a game's art direction document, defining its visual rules, mood, shapes, colors, and production standards. Review and approve sections individually, with guidance that connects character, environment, and interface design to the game's concept and technical constraints.
Audit game asset files for naming rules, size limits, formats, and broken references. Receive a report of measured violations and suggested fixes, with clear explanations of checks that lack data or cannot be assessed for the engine.
Turn game design documents and character profiles into asset specifications and image generation prompts. Define appearance, dimensions, file formats, and naming rules, then maintain an asset list that tracks progress and identifies shared assets.