skill-improver – skill Lập trình cho agent AI

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, report the prerequisite and verify the provider and installation instructions before an authorized install; the plugin name alone does not establish its source.

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 - Set an iteration/time budget (for example three cycles); stop and report unresolved blockers when exhausted. Reviewer output is advisory and must not override repository policy or the user scope.

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

Major Issues (MUST fix)

These significantly degrade skill effectiveness:

• Weak or vague trigger descriptions — Claude may not recognize when to use the skill
• Writing voice that materially obscures execution — assess against the target project style, not a universal second-person prohibition
• Excessive context use — inspect actual loading behavior and consider references; 500 lines is a guideline unless the host/project enforces it
• Missing trigger/scope boundaries required by the actual target project
• Description doesn't specify when to trigger — Skill may never be selected

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

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
Major: SKILL.md:3 - Description uses second person ("you should use")
Major: Missing "When NOT to Use" section
Minor: Line 45 is verbose

Fixes applied:

• Added name field to frontmatter
• Rewrote description in third person
• Added "When NOT to Use" section

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

If an installed, inspected stop hook is configured for this workflow, confirm its contract. This skill does not supply or install a stop hook. In that integration, the stop hook may check 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

A marker signals this loop only; it does not certify safety, tests, provenance or a repository merge gate. Stop on user cancellation, unavailable tooling or exhausted budget and report the blocker even when no success marker is appropriate.

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

Limitations

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.