heal-skill — Claude Code command: fix skill documentation
heal-skill — a command to update skill documentation based on errors discovered during execution. Shows proposed changes, waits for approval, then applies edits with optional commit.
MIT ★ 1,988 updated 2026-04-01
/plugin marketplace add glittercowboy/taches-cc-resources
/plugin install taches-cc-resources@taches-cc-resourcesWhat heal-skill does
heal-skill reads the conversation context to identify which skill is running and detects what went wrong in its documentation. You can target a specific issue by passing it as an argument, or let the command analyze the broader context.
The workflow runs in steps: detect the skill from history, reflect on what failed and how it was discovered, present a diff with proposed corrections, wait for your approval, then apply changes to SKILL.md and related files. After edits, it can create a git commit describing what was fixed.
The command can read and edit files, run git and listing commands. It updates not just the main documentation but also files in references/ and scripts/ directories if they exist.
What it helps with
- review skill documentation after an execution error
- propose and approve changes to SKILL.md before applying
- update command examples or parameters in documentation
- sync skill documentation with its actual behavior
- commit corrected documentation with a clear explanation
Example prompts for the agent
- Fix the skill documentation based on what just happened
- Heal the error in SKILL.md: the API parameter changed
- Update skill documentation, check all files in references and scripts
How to install heal-skill
1Plugin marketplace
/plugin marketplace add glittercowboy/taches-cc-resources/plugin install taches-cc-resources@taches-cc-resources2Manually: put the files in place
.claude/commands/heal-skill.mdCall it with /heal-skill. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/heal-skill.mdCall it with /prompts:heal-skill. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/heal-skill.prompt.mdManually: put the files in place
.gemini/commands/heal-skill.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about heal-skill
How do I install heal-skill in Claude Code?
Run /plugin marketplace add glittercowboy/taches-cc-resources, then /plugin install taches-cc-resources@taches-cc-resources. The command becomes available at .claude/commands/heal-skill.md.
What does heal-skill do?
It detects errors in skill documentation, proposes corrections with reasoning, waits for your approval, then applies the changes. Can also create a commit that describes what was fixed.
Which files can heal-skill modify?
The main SKILL.md file and documentation in subdirectories like references/ and scripts/, if they exist. All changes are shown and require your approval before being applied.
Source text
heal-skill.md · MIT
--- description: Heal skill documentation by applying corrections discovered during execution with approval workflow argument-hint: [optional: specific issue to fix] allowed-tools: [Read, Edit, Bash(ls:*), Bash(git:*)] --- <objective> Update a skill's SKILL.md and related files based on corrections discovered during execution. Analyze the conversation to detect which skill is running, reflect on what went wrong, propose specific fixes, get user approval, then apply changes with optional commit. </objective> <context> Skill detection: !`ls -1 ./skills/*/SKILL.md | head -5` </context> <quick_start> <workflow> 1. **Detect skill** from conversation context (invocation messages, recent SKILL.md references) 2. **Reflect** on what went wrong and how you discovered the fix 3. **Present** proposed changes with before/after diffs 4. **Get approval** before making any edits 5. **Apply** changes and optionally commit </workflow> </quick_start> <process> <step_1 name="detect_skill"> Identify the skill from conversation context: - Look for skill invocation messages - Check which SKILL.md was recently referenced - Examine current task context Set: `SKILL_NAME=[skill-name]` and `SKILL_DIR=./skills/$SKILL_NAME` If unclear, ask the user. </step_1> <step_2 name="reflection_and_analysis"> Focus on $ARGUMENTS if provided, otherwise analyze broader context. Determine: - **What was wrong**: Quote specific sections from SKILL.md that are incorrect - **Discovery method**: Context7, error messages, trial and error, documentation lookup - **Root cause**: Outdated API, incorrect parameters, wrong endpoint, missing context - **Scope of impact**: Single section or multiple? Related files affected? - **Proposed fix**: Which files, which sections, before/after for each </step_2> <step_3 name="scan_affected_files"> ```bash ls -la $SKILL_DIR/ ls -la $SKILL_DIR/references/ 2>/dev/null ls -la $SKILL_DIR/scripts/ 2>/dev/null ``` </step_3> <step_4 name="present_proposed_changes"> Present changes in this format: ``` **Skill being healed:** [skill-name] **Issue discovered:** [1-2 sentence summary] **Root cause:** [brief explanation] **Files to be modified:** - [ ] SKILL.md - [ ] references/[file].md - [ ] scripts/[file].py **Proposed changes:** ### Change 1: SKILL.md - [Section name] **Location:** Line [X] in SKILL.md **Current (incorrect):** ``` [exact text from current file] ``` **Corrected:** ``` [new text] ``` **Reason:** [why this fixes the issue] [repeat for each change across all files] **Impact assessment:** - Affects: [authentication/API endpoints/parameters/examples/etc.] **Verification:** These changes will prevent: [specific error that prompted this] ``` </step_4> <step_5 name="request_approval"> ``` Should I apply these changes? 1. Yes, apply and commit all changes 2. Apply but don't commit (let me review first) 3. Revise the changes (I'll provide feedback) 4. Cancel (don't make changes) Choose (1-4): ``` **Wait for user response. Do not proceed without approval.** </step_5> <step_6 name="apply_changes"> Only after approval (option 1 or 2): 1. Use Edit tool for each correction across all files 2. Read back modified sections to verify 3. If option 1, commit with structured message showing what was healed 4. Confirm completion with file list </step_6> </process> <success_criteria> - Skill correctly detected from conversation context - All incorrect sections identified with before/after - User approved changes before application - All edits applied across SKILL.md and related files - Changes verified by reading back - Commit created if user chose option 1 - Completion confirmed with file list </success_criteria> <verification> Before completing: - Read back each modified section to confirm changes applied - Ensure cross-file consistency (SKILL.md examples match references/) - Verify git commit created if option 1 was selected - Check no unintended files were modified </verification>
© Lex Christopherson · MIT · glittercowboy/taches-cc-resources