GitHub user
Agent skills by feiskyer
- skills
- 23
- repositories
- 2
Repositories by feiskyer
- claude-code-settingsCurated skills, sub-agents, and config templates that supercharge Claude Code — research, image gen, GitHub automation & more.1.7k stars · 12 skills
- codex-settingsCurated skills, profiles, and config templates that supercharge Codex CLI — multi-model, deep research, image gen & browser automation.244 stars · 11 skills
Skills by feiskyer, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Create, refine, and benchmark agent skills. An agent skill from feiskyer/claude-code-settings. | feiskyer/ | 1.7k | — | ~7.6k | Automated safety check: Pass | Apache-2.0 | 10 days ago |
| 2 | Explore user intent, requirements, and design options through collaborative dialogue before implementation. | feiskyer/ | 1.7k | — | ~985 | Automated safety check: Pass | MIT | 10 days ago |
| 3 | Extract subtitles or a transcript from a YouTube URL and save normalized timestamped text locally. | feiskyer/ | 244 | — | ~745 | Automated safety check: Pass | MIT | 10 days ago |
| 4 | Generate images when the user names MiniMax or image-01/image-01-live. | feiskyer/ | 244 | 1 repo | ~495 | Automated safety check: Pass | MIT | 10 days ago |
| 5 | Delegate a task to the Claude Code CLI, typically a headless claude -p run. | feiskyer/ | 244 | — | ~742 | Automated safety check: Pass | MIT | 10 days ago |
| 6 | Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless claude -p subprocesses, aggregate results into a polished report file. | feiskyer/ | 1.7k | — | ~2.6k | Automated safety check: Notes | MIT | 10 days ago |
| 7 | Leverage OpenAI Codex/GPT models for autonomous code implementation, code review, and plan review. | feiskyer/ | 1.7k | — | ~2.7k | Automated safety check: Warn | MIT | 10 days ago |
| 8 | Fix GitHub issues end-to-end — analysis, branch creation, implementation, testing, and PR submission. | feiskyer/ | 1.7k | — | ~786 | Automated safety check: Pass | MIT | 10 days ago |
| 9 | Generate or edit images when the user names OpenAI, GPT Image, or a gpt-image model. | feiskyer/ | 244 | — | ~572 | Automated safety check: Pass | MIT | 10 days ago |
| 10 | Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. | feiskyer/ | 1.7k | — | ~9.2k | Automated safety check: Pass | MIT | 10 days ago |
| 11 | Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). | feiskyer/ | 1.7k | — | ~1.4k | Automated safety check: Pass | MIT | 10 days ago |
| 12 | Generate or edit images via Google Gemini (nanobanana). An agent skill from feiskyer/claude-code-settings. | feiskyer/ | 1.7k | — | ~1.1k | Automated safety check: Pass | MIT | 10 days ago |
| 13 | Simplify existing code for clarity and maintainability without changing behavior. | feiskyer/ | 244 | — | ~521 | Automated safety check: Pass | MIT | 10 days ago |
| 14 | Extract subtitles/transcripts from YouTube videos. An agent skill from feiskyer/claude-code-settings. | feiskyer/ | 1.7k | — | ~1.1k | Automated safety check: Pass | MIT | 10 days ago |
| 15 | 用 Codex CLI 子任务完成多来源深度调研并综合成带出处的报告。用于确实需要分头取证的研究，不用于单次查证或已给定材料的总结。 | feiskyer/ | 244 | — | ~302 | Automated safety check: Pass | MIT | 10 days ago |
| 16 | Generate, edit, or composite images with Gemini/Nanobanana. An agent skill from feiskyer/codex-settings. | feiskyer/ | 244 | — | ~1.2k | Automated safety check: Pass | MIT | 10 days ago |
| 17 | 17.Grill Me 针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。 | feiskyer/ | 1.7k | — | ~913 | Automated safety check: Pass | MIT | 10 days ago |
| 18 | Review a GitHub pull request by number or URL for evidence-backed defects. | feiskyer/ | 244 | — | ~1.3k | Automated safety check: Pass | MIT | 10 days ago |
| 19 | 19.Translate Translate English or Japanese tech articles into natural, fluent Chinese. | feiskyer/ | 1.7k | — | ~513 | Automated safety check: Pass | MIT | 10 days ago |
| 20 | 把尚有关键取舍的功能或系统想法收敛为设计。用于用户要求讨论方案或需求尚未明确时；不用于 bug 修复、配置修改或照已有方案实现。 | feiskyer/ | 244 | — | ~241 | Automated safety check: Pass | MIT | 10 days ago |
| 21 | Investigate or fix a GitHub issue by number or URL. An agent skill from feiskyer/codex-settings. | feiskyer/ | 244 | — | ~896 | Automated safety check: Pass | MIT | 10 days ago |
| 22 | 22.Grill Me 仅当用户显式调用 $grill-me，或明确要求"追问我""挑战这个方案""拷打这个设计"时使用。通过高强度逐问逐答检验方案，并同步沉淀术语表和 ADR。不要因普通设计讨论自动触发。 | feiskyer/ | 244 | — | ~284 | Automated safety check: Pass | MIT | 10 days ago |
| 23 | 23.Handoff 将当前对话压缩为交接文档（handoff document / session handoff brief），供下一个 agent 接续工作。手动调用 /handoff。 | feiskyer/ | 1.7k | — | ~173 | Automated safety check: Pass | MIT | 10 days ago |
Questions, answered from the data.
What is the best skill by feiskyer?
Skill Creator from feiskyer/claude-code-settings ranks first of the 23 skills by feiskyer listed here, with the highest score: its repository has 1.7k GitHub stars, its SKILL.md loads about 7.6k tokens and it passes the automated safety check with no findings. Next come Brainstorming and Youtube Transcribe Skill.
Are feiskyer's skills official?
None yet. All 23 skills by feiskyer listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
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.