Skill collection
penwyp/ClaudePreference agent skills
- skills
- 7
- GitHub stars
- 136
GitHub description: “A comprehensive collection of development workflow commands for Claude Code”
- Stars
- 136 (20 forks)
- Licence
- MIT
- Last push
- May 2026
- Created
- Jul 2025
Install all skills
npx skills add penwyp/ClaudePreferenceAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in penwyp/ClaudePreference, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Diagnose and stabilize local project setup after clone or checkout. | penwyp/ | 136 | — | ~1.1k | Automated safety check: Notes | MIT | 4 mo ago |
| 2 | Convert images between common formats on macOS, especially SVG/PNG/ICO/ICNS/JPEG/WebP/PDF, using installed local tools such as ImageMagick, rsvg-convert, sips, qlmanage, and iconutil. | penwyp/ | 136 | — | ~955 | Automated safety check: Pass | MIT | 4 mo ago |
| 3 | 3.Explain Analyze a code snippet, file path, symbol name, or the current conversation context against the local repository and explain what it does in the project. | penwyp/ | 136 | — | ~1.2k | Automated safety check: Pass | MIT | 4 mo ago |
| 4 | Produce a professional, code-grounded refactor or implementation design report from identified technical problems, product gaps, review findings, architecture concerns, or frontend-backend contract… | penwyp/ | 136 | — | ~1.4k | Automated safety check: Pass | MIT | 4 mo ago |
| 5 | Review text input or documents against the local codebase and produce a structured review report with findings and refactor suggestions. | penwyp/ | 136 | — | ~1.5k | Automated safety check: Pass | MIT | 4 mo ago |
| 6 | Diagnose flaky browser automation flows (login, OAuth, signup, multi-step forms). | penwyp/ | 136 | — | ~1.1k | Automated safety check: Pass | MIT | 4 mo ago |
| 7 | 适用于这类请求：直接在当前 checkout 完成开发、固定做两轮自我 review/refactor、先把最终 review 结果给人类确认、确认后再继续改动、提交或进入下一步。用户可能会说："先开发再自审两轮"、"先 review 两次再给我确认"、"不要开 worktree，直接改"、"先输出 review 结论不要继续"、"做完先停在 gate"。 | penwyp/ | 136 | — | ~846 | Automated safety check: Pass | MIT | 4 mo ago |
Questions, answered from the data.
What is the best skill in penwyp/ClaudePreference?
Local Project Runtime from penwyp/ClaudePreference ranks first of the 7 skills in penwyp/ClaudePreference listed here, with the highest score: its repository has 136 GitHub stars, its SKILL.md loads about 1.1k tokens and it has informational notes only in the automated safety check. Next come Image Converter and Explain.
Are the skills in penwyp/ClaudePreference official?
None yet. All 7 skills in penwyp/ClaudePreference listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from penwyp/ClaudePreference?
Run npx skills add penwyp/ClaudePreference in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.