KS
Killer-Skills

manage-skills — how to use manage-skills how to use manage-skills, manage-skills alternative, manage-skills setup guide, what is manage-skills, manage-skills vs VRP Toolkit, manage-skills install, VRP Toolkit skill management, audit skills directory, skill compliance validation

v1.0.0
GitHub

About this Skill

Perfect for AI Agents needing advanced skill management and auditing capabilities, particularly those utilizing VRP Toolkit skills. manage-skills is a meta-skill for managing and auditing VRP Toolkit skills, ensuring directory comparison and compliance validation.

Features

Audits skills directory using `.claude/skills/` and SKILLS.md documentation
Validates skills against VRP Toolkit standards
Generates reports on skills in directory vs SKILLS.md
Identifies missing skills from documentation and directory
Executes sync status checks using `audit_skills.py` script

# Core Topics

dudusoar dudusoar
[0]
[0]
Updated: 3/7/2026

Quality Score

Top 5%
36
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add dudusoar/VRP-Toolkit/references/compliance_checklist.md

Agent Capability Analysis

The manage-skills MCP Server by dudusoar is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use manage-skills, manage-skills alternative, manage-skills setup guide.

Ideal Agent Persona

Perfect for AI Agents needing advanced skill management and auditing capabilities, particularly those utilizing VRP Toolkit skills.

Core Value

Empowers agents to efficiently manage and audit skills by comparing actual skills in `.claude/skills/` with SKILLS.md documentation, and validating skills against VRP Toolkit standards using Python scripts like `audit_skills.py`.

Capabilities Granted for manage-skills MCP Server

Auditing skills directories for compliance
Validating skill compliance against VRP Toolkit standards
Comparing actual skills with documented skills in SKILLS.md

! Prerequisites & Limits

  • Requires access to `.claude/skills/` directory
  • SKILLS.md documentation must be up-to-date
  • Python environment required for script execution
Project
SKILL.md
5.6 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Manage Skills

Meta-skill for managing, auditing, and maintaining all VRP Toolkit skills.

Core Functions

1. Audit Skills Directory

Compare actual skills in .claude/skills/ with SKILLS.md documentation.

Usage:

bash
1python .claude/skills/manage-skills/scripts/audit_skills.py

Reports:

  • Skills in directory vs SKILLS.md
  • Missing from documentation
  • Missing from directory
  • Sync status

2. Check Skill Compliance

Validate skills against VRP Toolkit standards.

Usage:

bash
1# Check specific skill 2python .claude/skills/manage-skills/scripts/check_compliance.py skill-name 3 4# Check all skills 5python .claude/skills/manage-skills/scripts/check_compliance.py --all

Checks:

  • Independence: Skill doesn't embed other skills' content
  • Size: SKILL.md ≤ 500 lines (body, excluding frontmatter)
  • Structure: Required files present, no prohibited files
  • Frontmatter: Valid YAML with name and description
  • References: All reference files mentioned in SKILL.md

See compliance_checklist.md for detailed standards.

3. Update SKILLS.md Index

Sync skills documentation in SKILLS.md with actual skills.

When:

  • After adding new skill
  • After removing skill
  • After significantly modifying skill description

See: update_procedures.md → Section 1

4. Record Changes in SKILLS_LOG.md

Log all skill modifications for tracking and history.

When:

  • After any skill change (add/update/remove/rename/split/merge)

Template:

markdown
1## YYYY-MM-DD - [Action]: [skill-name] 2**Action:** [Added/Updated/Removed/Renamed/Split/Merged] 3**Reason:** [Why this change was made] 4**Changes:** 5- [Specific change 1] 6- [Specific change 2] 7**Compliance Notes:** [Any compliance issues addressed] 8**Impact:** [How this affects other skills or workflows]

See: update_procedures.md → Section 2

Workflow Patterns

Pattern A: Add New Skill

1. Create skill using skill-creator
2. Run: audit_skills.py
   → Check if new skill appears in directory
3. Update SKILLS.md skills index (Section 1)
4. Record in SKILLS_LOG.md
5. Run: check_compliance.py skill-name
   → Verify new skill is compliant

Pattern B: Modify Existing Skill

1. Make changes to skill
2. Run: check_compliance.py skill-name
   → Check for violations (size, independence, etc.)
3. If issues found, fix them
4. Update SKILLS.md description if needed
5. Record changes in SKILLS_LOG.md

Pattern C: Periodic Audit

1. Run: audit_skills.py
   → Check directory vs SKILLS.md sync
2. Run: check_compliance.py --all
   → Check all skills for compliance
3. Review warnings and errors
4. Plan fixes or improvements
5. Update SKILLS_LOG.md with findings

Pattern D: Fix Compliance Issues

Size Violation (>500 lines):

1. Identify extractable sections
2. Move to references/ or create new skill
3. Update SKILL.md references
4. Re-run check_compliance.py
5. Record in SKILLS_LOG.md

Independence Violation:

1. Find embedded content from other skills
2. Replace with reference: "See [skill-name] for..."
3. Re-run check_compliance.py
4. Record in SKILLS_LOG.md

See update_procedures.md for detailed procedures on:

  • Renaming skills
  • Splitting large skills
  • Merging similar skills
  • Archiving deprecated skills

Integration with Other Skills

Works with:

  • skill-creator - Use to create new skills before managing them
  • update-migration-log - Similar logging pattern for migrations
  • update-task-board - Similar documentation sync pattern

DO NOT embed workflows from these skills - Reference them instead.

Compliance Standards Quick Reference

yaml
1Independence: 2 ✓ Can reference other skills: "See [skill-name] for..." 3 ✗ Cannot embed workflows from other skills 4 5Size: 6 ✓ SKILL.md ≤ 500 lines (excluding frontmatter) 7 ⚠ Warning at 400 lines 8 ✗ Error at 500 lines 9 10Structure: 11 ✓ Required: SKILL.md with valid frontmatter 12 ✓ Optional: scripts/, references/, assets/ 13 ✗ Prohibited: README.md, CHANGELOG.md, etc. 14 15Frontmatter: 16 ✓ Required fields: name, description 17 ✓ Description: 50-200 words with use cases 18 ✗ Extra fields discouraged 19 20References: 21 ✓ All refs linked from SKILL.md 22 ✓ Max 1 level deep (no nested dirs) 23 ⚠ Warning if ref >500 lines

Full details: compliance_checklist.md

Files in This Skill

manage-skills/
├── SKILL.md                          # This file
├── scripts/
│   ├── audit_skills.py              # Directory vs CLAUDE.md audit
│   └── check_compliance.py          # Compliance validation
├── references/
│   ├── compliance_checklist.md      # Detailed compliance standards
│   └── update_procedures.md         # Step-by-step update procedures
└── assets/
    └── SKILLS_LOG_template.md       # Template for SKILLS_LOG.md

Tips

  1. Run audit after adding skills - Catches missing documentation immediately
  2. Check compliance before packaging - Prevents distribution of non-compliant skills
  3. Keep SKILLS_LOG.md updated - Provides history for troubleshooting
  4. Review warnings seriously - They often indicate real issues
  5. Split before 500 lines - Easier to split at 400 than fix at 600

Limitations

  • Does not automatically fix compliance issues (manual fixes required)
  • Cannot detect semantic overlap between skills (manual review needed)
  • Windows encoding issues with emoji in scripts (uses ASCII fallback)

Related Skills

Looking for an alternative to manage-skills or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication