avibebuilder/claude-prime / .claude/skills/skill-creator
skill-creator
VerifiedUse when the user wants to work on a Claude Code skill file (SKILL.md): writing one from scratch, testing whether an existing one works well, running evals or benchmarks, improving its instructions, or fixing why it isn't triggering. Triggers on: 'make a skill for X', 'test this skill', 'run evals on my SKILL.md', 'touch-skill', sharing a SKILL.md and asking if it's ready to ship. The key signal is intent to create, validate, or improve a skill — not just mention one. Do NOT trigger for general Claude Code questions, hook debugging, or CLAUDE.md configuration.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 32.3 KB |
| agents/analyzer.md | markdown | 10.1 KB |
| agents/comparator.md | markdown | 7.1 KB |
| agents/grader.md | markdown | 10.5 KB |
| agents/judge.md | markdown | 6.0 KB |
| assets/eval_review.html | other | 6.9 KB |
| eval-viewer/generate_report.py | script | 17.4 KB |
| eval-viewer/generate_review.py | script | 16.0 KB |
| eval-viewer/report.html | other | 91.8 KB |
| eval-viewer/viewer.html | other | 43.9 KB |
| references/available-skill-resources.md | markdown | 2.0 KB |
| references/schemas.md | markdown | 15.6 KB |
| scripts/__init__.py | script | 0 B |
| scripts/aggregate_benchmark.pyexecutable | script | 21.4 KB |
| scripts/generate_report.pyexecutable | script | 12.5 KB |
| scripts/improve_description.pyexecutable | script | 10.9 KB |
| scripts/package_skill.pyexecutable | script | 4.1 KB |
| scripts/quick_validate.pyexecutable | script | 4.4 KB |
| scripts/run_eval.pyexecutable | script | 13.1 KB |
| scripts/run_loop.pyexecutable | script | 13.7 KB |
| scripts/utils.py | script | 1.6 KB |
references/available-skill-resources.md
View on GitHub# Available Skill Resources
Curated registry of external skill collections for discovering existing skills before creating new ones.
MUST download the entry point to know what's available — do not rely on secondhand summaries or lists, it's just some highlights and may be outdated.
**IMPORTANT**: Entry point content is large, prefer downloading it to /tmp, if you use WebFetch, MUST provide the prompt to search for your target domain in the raw content and return with real according URLs to follow up — do not summarize as it will lead to loss of information.
## Skill Repositories
### VoltAgent/awesome-agent-skills (Recommended)
- **Repo**: https://github.com/VoltAgent/awesome-agent-skills
- **Entry point**: https://raw.githubusercontent.com/VoltAgent/awesome-agent-skills/main/README.md
- **What**: 380+ curated agent skills from official dev teams (Anthropic, Vercel, Cloudflare, Stripe, Google, Microsoft, Hugging Face, Expo, Sentry, and more) plus community contributions. Compatible with Claude Code, Codex, Gemini CLI, Cursor, Copilot, and others. Focuses on real-world skills, not mass-generated content.
### hesreallyhim/awesome-claude-code
- **Repo**: https://github.com/hesreallyhim/awesome-claude-code
- **Entry point**: https://raw.githubusercontent.com/hesreallyhim/awesome-claude-code/main/README.md
- **What**: Curated index of hundreds of Claude Code resources organized by type — agent skills, workflows & knowledge guides, tooling (IDE integrations, orchestrators, config managers), status lines, hooks, slash-commands, CLAUDE.md files, and alternative clients.
### ComposioHQ/awesome-claude-skills
- **Repo**: https://github.com/ComposioHQ/awesome-claude-skills
- **Entry point**: https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/main/README.md
- **What**: 33+ practical Claude Skills across document processing, development tools, data analysis, business/marketing, creative/media, security, and productivity. Includes Composio automation skills for 78+ SaaS apps (CRM, project management, communication, storage, social media).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |