skill-improver

name	skill-improver
description	Iteratively reviews and fixes Claude Code skill quality issues until they meet standards. Runs automated fix-review cycles using the skill-reviewer agent. Use to fix skill quality issues, improve skill descriptions, run automated skill review loops, or iteratively refine a skill. Triggers on 'fix my skill', 'improve skill quality', 'skill improvement loop'. NOT for one-time reviews—use /skill-reviewer directly.
allowed-tools	["Task","Read","Edit","Write","Glob","Grep"]

Skill Improvement Methodology

Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards.

Prerequisites

Requires the plugin-dev plugin which provides the skill-reviewer agent.

Verify it's enabled: run /plugins — plugin-dev should appear in the list. If missing, install from the Trail of Bits plugin repository.

Core Loop

1. Review - Call skill-reviewer on the target skill
2. Categorize - Parse issues by severity
3. Fix - Address critical and major issues
4. Evaluate - Check minor issues for validity before fixing
5. Repeat - Continue until quality bar is met

When to Use

• Improving a skill with multiple quality issues
• Iterating on a new skill until it meets standards
• Automated fix-review cycles instead of manual editing
• Consistent quality enforcement across skills

When NOT to Use

• One-time review: Use /skill-reviewer directly instead
• Quick single fixes: Edit the file directly
• Non-skill files: Only works on SKILL.md files
• Experimental skills: Manual iteration gives more control during exploration

Issue Categorization

Critical Issues (MUST fix immediately)

These block skill loading or cause runtime failures:

• Missing required frontmatter fields (name, description) — Claude cannot index or trigger the skill
• Invalid YAML frontmatter syntax — Parsing fails, skill won't load
• Referenced files that don't exist — Runtime errors when Claude follows links
• Broken file paths — Same as above, leads to tool failures
• Invalid allowed-tools values — Tools that don't exist in Claude Code
• Invalid model value — Must be sonnet, opus, haiku, or full model ID
• Invalid effort value — Must be low, medium, high, or max
• Invalid context value — Must be fork if set
• agent field set without context: fork — Agent field requires context: fork

Major Issues (MUST fix)

These significantly degrade skill effectiveness:

• Weak or vague trigger descriptions — Claude may not recognize when to use the skill
• Wrong writing voice (second person "you" instead of imperative) — Inconsistent with Claude's execution model
• SKILL.md exceeds 500 lines without using references/ — Overloads context, reduces comprehension
• Missing "When to Use" or "When NOT to Use" sections — Required by project quality standards
• Description doesn't specify when to trigger — Skill may never be selected
• Missing allowed-tools — Skill inherits all tools, potential security risk
• argument-hint set but $ARGUMENTS not used in body — Arguments silently dropped
• disable-model-invocation: true on a skill with no user-actionable task — Skill becomes unreachable
• user-invocable: false on a skill Claude can't meaningfully auto-trigger — Skill becomes unreachable
• Referenced supporting files don't exist — Claude instructed to read non-existent files
• Cross-skill references point to non-existent skills — Dead links
• Non-standard frontmatter fields (risk, source, category, metadata) — May confuse parsers

Minor Issues (Evaluate before fixing)

These are polish items that may or may not improve the skill:

• Subjective style preferences — Reviewer may have different taste than author
• Optional enhancements — May add complexity without proportional value
• "Nice to have" improvements — Consider cost-benefit before implementing
• Formatting suggestions — Often valid but low impact
• Description could be more specific — Functional but improvable

Frontmatter Validation Checklist

When reviewing a skill, verify these fields against the official schema:

Field	Valid Values	Notes
name	lowercase, numbers, hyphens (max 64)	Uses dir name if omitted
description	string	Should include trigger phrases
allowed-tools	Claude Code tool names	Comma-separated or YAML list
argument-hint	string	Shown in autocomplete
disable-model-invocation	true/false	Prevents Claude auto-trigger
user-invocable	true/false	Hides from / menu
context	fork	Runs in isolated subagent
agent	Explore, Plan, general-purpose, or custom	Requires context: fork
model	sonnet, opus, haiku, full model ID	Override model
effort	low, medium, high, max	Override effort
hooks	Hook config object	Lifecycle hooks

Any field NOT in this list (e.g., license, category, risk, source, date_added, metadata) is non-standard.

String Substitution Validation

Check that these are used correctly if present:

Variable	Valid Usage
$ARGUMENTS	Replaced with all args passed to skill
$ARGUMENTS[N] or $N	0-based index for specific arg
${CLAUDE_SESSION_ID}	Current session ID
${CLAUDE_SKILL_DIR}	Path to skill directory
Shell bang syntax (exclamation + backticks)	Shell command preprocessed before Claude sees content

Minor Issue Evaluation

Before implementing any minor issue fix, evaluate:

1. Is this a genuine improvement? - Does it add real value or just satisfy a preference?
2. Could this be a false positive? - Is the reviewer misunderstanding context?
3. Would this actually help Claude use the skill? - Focus on functional improvements

Only implement minor fixes that are clearly beneficial. Skill-reviewer may produce false positives.

Invoking skill-reviewer

Use the skill-reviewer agent from the plugin-dev plugin. Request a review by asking Claude to:

Review the skill at [SKILL_PATH] using the plugin-dev:skill-reviewer agent. Provide a detailed quality assessment with issues categorized by severity.

Replace [SKILL_PATH] with the absolute path to the skill directory (e.g., /path/to/plugins/my-plugin/skills/my-skill).

Example Fix Cycle

Iteration 1 — skill-reviewer output:

Critical: SKILL.md:1 - Missing required 'name' field in frontmatter
Critical: SKILL.md:5 - agent: Explore set without context: fork
Major: SKILL.md:3 - Description uses second person ("you should use")
Major: Missing "When NOT to Use" section
Major: Missing allowed-tools field
Minor: Line 45 is verbose

Fixes applied:

• Added name field to frontmatter
• Added context: fork since agent: Explore requires it
• Rewrote description in imperative with trigger phrases
• Added "When NOT to Use" section
• Added allowed-tools: Read, Grep, Glob

Iteration 2 — run skill-reviewer again to verify fixes:

Minor: Line 45 is verbose

Minor issue evaluation: Line 45 communicates effectively as-is. The verbosity provides useful context. Skip.

All critical/major issues resolved. Output the completion marker:

<skill-improvement-complete>

Note: The marker MUST appear in the output. Statements like "quality bar met" or "looks good" will NOT stop the loop.

Completion Criteria

CRITICAL: The stop hook ONLY checks for the explicit marker below. No other signal will terminate the loop.

Output this marker when done:

<skill-improvement-complete>

When to output the marker:

1. skill-reviewer reports "Pass" or no issues found → output marker immediately
2. All critical and major issues are fixed AND you've verified the fixes → output marker
3. Remaining issues are only minor AND you've evaluated them as false positives or not worth fixing → output marker

When NOT to output the marker:

• Any critical issue remains unfixed
• Any major issue remains unfixed
• You haven't run skill-reviewer to verify your fixes worked

The marker is the ONLY way to complete the loop. Natural language like "looks good" or "quality bar met" will NOT stop the loop.

Rationalizations to Reject

• "I'll just mark it complete and come back later" - Fix issues now
• "This minor issue seems wrong, I'll skip all of them" - Evaluate each one individually
• "The reviewer is being too strict" - The quality bar exists for a reason
• "It's good enough" - If there are major issues, it's not good enough