From generic-skills
Analyzes and refines skills by identifying issues like time estimates, oversized files, poor structure, redundant content; prioritizes fixes (MUST/SHOULD/NICE); implements improvements with user feedback.
npx claudepluginhub przemocny/generic-skillsThis skill uses the workspace's default tool permissions.
**Purpose:** Critical analysis and improvement of agent skills
Reviews and improves AI agent SKILL.md files against Agent Skills spec and Anthropic guidelines. Scores 10 quality dimensions, identifies issues, and suggests rewrites for creating, editing, or auditing skills.
Analyzes skill executions from conversation friction, file diffs, user feedback, diagnostics, and lessons to propose concrete improvements to SKILL.md files for efficiency.
Audits Claude Code skills for violations, gaps, and improvements in frontmatter, structure, and quality across 7 dimensions. Outputs structured repair plans with severities.
Share bugs, ideas, or general feedback.
Purpose: Critical analysis and improvement of agent skills
Approach:
Output: Improved skill + change report in .tasks/skill-refactoring-[date]/
Based on Agent Skills Complete Guide:
🔴 PRIORITY 1: MUST FIX (breaking issues)
🟡 PRIORITY 2: SHOULD FIX (quality issues)
🟢 PRIORITY 3: NICE TO HAVE (enhancements)
Skill analyzed: code-review
Problem found:
Line 45: "This analysis should take about 5-10 minutes"
Line 89: "Quick scan (2-3 minutes)"
Priority: 🔴 MUST FIX - Core guideline violation
Fix: Remove all time references:
Line 45: "This analysis covers security, performance, and style"
Line 89: "Quick scan of critical issues"
For skill: pdf-processor (1200 lines in SKILL.md)
Analysis presented to user:
## 🔴 MUST FIX
### 1. SKILL.md Too Long (1200 lines)
**Problem:** Exceeds recommended 500 line limit
**Impact:** Loads unnecessary content into context
**Fix:** Move detailed API docs to references/api-reference.md
### 2. Time Estimates Found
**Problem:** Lines 234, 456, 789 contain time estimates
**Fix:** Remove phrases "takes 2 minutes", "quick 30 second scan"
## 🟡 SHOULD FIX
### 3. Missing Examples Section
**Problem:** No concrete input → output examples
**Fix:** Add examples showing PDF processing workflow
## 🟢 What's Good
- Clear step-by-step workflow
- Good error handling coverage
- Scripts are well-documented
Before:
## How to Use
So basically when you want to process a PDF you should first
check if the file exists and then you know, read it and extract
the text content which might take a few minutes depending on the
size, and then process it according to what the user needs...
After:
## How to Use
**Process PDF files:**
1. Validate PDF exists
2. Extract text using `scripts/extract.py`
3. Parse output for required format
4. Return processed content
**For detailed extraction options, see [references/extraction-guide.md](references/extraction-guide.md)**
Cel: Dogłębnie zrozumieć skill i jego strukturę.
Kroki:
Read main SKILL.md:
Read wszystkie references:
Compare z innymi skillami:
Output: Pełne zrozumienie skilla i jego kontekstu.
Goal: Ruthlessly identify all problems and group by priority
Analysis Checklist:
Use references/quality-criteria.md for complete criteria. Key checks:
Structure & Length:
Content Quality:
Description & Triggering:
Workflow & Features:
For Each Issue Found:
Output: Complete prioritized list of issues with solutions
Cel: Zaprezentować analizę użytkownikowi i zebrać feedback co poprawiać.
Presentation format:
## 🔴 Główne problemy (MUST FIX)
### 1. **[Problem name]**
**Problem:** [clear description]
**Konkretnie:** [specific examples with line numbers]
**Fix:** [concrete solution]
### 2. **[Problem name]**
...
## 🟡 Średnie problemy (SHOULD FIX)
[...]
## 🟢 Co jest dobre
[List positive aspects - important for balance]
## 💡 Sugestie poprawek
**Priority 1 (MUST fix):**
1. [Fix 1]
2. [Fix 2]
**Priority 2 (SHOULD fix):**
[...]
**Priority 3 (NICE to have):**
[...]
Zapytaj użytkownika:
Listen for:
Output: Jasna lista co poprawiać z user approval.
Cel: Systematycznie wprowadzić poprawki zgodnie z priorytetami i feedbackiem.
Refactoring workflow:
1. Start with Priority 1 issues:
2. Then Priority 2:
3. Priority 3 if time:
Refactoring patterns:
Use references/refactoring-patterns.md:
Best practices:
Track changes:
Create log in .tasks/skill-refactoring-[skill-name]-[date]/changes.md:
Cel: Sprawdzić że wszystko działa i podsumować zmiany.
Verification checklist:
✅ Files are valid:
✅ Metrics improved:
✅ Quality checklist passed:
Report to user:
"Gotowe! Poprawiłem skill [name].
Główne zmiany:
Metryki:
Co zostało poprawione: ✅ [Issue 1] ✅ [Issue 2] ✅ [Issue 3]
Co jest lepsze:
Szczegółowy raport w .tasks/skill-refactoring-[name]-[date]/"
Zapytaj:
Przed zakończeniem, upewnij się że:
✅ Analysis was thorough: Checked all aspects z quality-criteria.md ✅ Problems prioritized: Clear MUST/SHOULD/NICE to have ✅ User feedback gathered: User approved changes ✅ Changes implemented: All agreed fixes done ✅ No time estimates: Removed all time references ✅ Structure improved: SKILL.md is clear and not too long ✅ References optimized: Supporting files helpful, not overwhelming ✅ Changes documented: Log created with before/after ✅ Verification done: Quality checklist passed ✅ User satisfied: Final approval received
DO:
DON'T:
Twoje podejście: Jesteś bezwzględnym code reviewer który chce żeby skill był najlepszy jaki może być. Identifikujesz problemy, proponujesz rozwiązania, ale ostatecznie user decyduje co poprawiać.
Pamiętaj: