All authors
Claude Skills by cnfjlhj
github.com/cnfjlhj23 skills0 installs25 views
- Session Recovery CodexUse when recovering a Codex session, especially if the user provides a Codex session id or wants recent Codex sessions listed before resuming work.Votes: 0GitHub stars: 444
- Skill CreatorGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.Votes: 0GitHub stars: 444
- Skill Governance LoopUse when the user asks to review a skill, analyze skill quality, update or align a skill version, compare local state against a newer variant, or run a repeatable keep/enable/hide/disable/archive decision loop from real failures instead of abstract best practices.Votes: 0GitHub stars: 444
- ReferencesUse this note before moving content between `AGENTS.md` and a skill.Votes: 0GitHub stars: 444
- Skills GovernanceUse when auditing a large local skill collection, identifying duplicate or imported skills, comparing skill roots, or deciding what to keep, disable, or archive across Codex and adjacent agent skill directories.Votes: 0GitHub stars: 444
- Timestamped Video SummaryGenerate a detailed, professional video content summary from timestamped subtitles/transcripts (e.g., lines starting with 00:00 / 1:23:45). Enforce strict per-segment structure (timestamp range + bold segment title + 2-paragraph body: first-person creator summary + expert 【导师评注】 critique with uncertainty handling). Use when the user provides time-coded subtitles and asks for a规范化纪要/内容纪要/逐段总结, and optionally wants a clean PDF export (do NOT include the full raw transcript in the PDF unless exp...Votes: 0GitHub stars: 444
- Writing Anti AiUse only when the user explicitly asks to remove formulaic AI-writing patterns, humanize prose, or make English or Chinese text sound more natural while preserving its meaning.Votes: 0GitHub stars: 444
- Xhs Longform Private PublisherThis skill should be used when the user wants to publish an existing Markdown article to Xiaohongshu as a private longform post, keep the original wording and structure, insert inline images in order, use one-click layout, and verify the result in note manager.Votes: 0GitHub stars: 444
- Xhs Note CreatorUse when the user wants Xiaohongshu note materials such as the note text, cover card, body cards, or publishing-ready assets. Do not use this for generic social copywriting or image generation when the deliverable is not a Xiaohongshu post package.Votes: 0GitHub stars: 444
- Academic Paper HelperUse only when the user explicitly asks for help drafting or revising an AI/ML research paper in LaTeX, including structure, BibTeX, formatting, or academic-writing checks.Votes: 0GitHub stars: 444
- All PlanUse when a task is ambiguous and needs deep multi-role planning with designer, inspiration, and reviewer perspectives before execution. Skip this for ordinary task plans.Votes: 0GitHub stars: 444
- Collaborating With ClaudeUse when you want Claude Code CLI as a second opinion for coding tasks such as design tradeoffs, debugging, or diff review, while keeping Codex as the primary implementer.Votes: 0GitHub stars: 444
- Collaborating With CodexUse when you explicitly want a second local or SSH remote Codex CLI session to prototype, debug, or review code, while your current session remains the primary owner of the final result.Votes: 0GitHub stars: 444
- Collaborating With GeminiUse when you want Gemini CLI as a second opinion for coding tasks such as prototyping, debugging, or diff review, while keeping Codex as the primary implementer.Votes: 0GitHub stars: 444
- Find SkillsUse when the user asks whether a skill exists, wants help finding or installing one, or asks how to extend agent capabilities with a reusable skill. Start with `npx skills find`; if that fails, use a GitHub-aware fallback before concluding no good match exists.Votes: 0GitHub stars: 444
- Paper Review PipelineUse when a mostly complete ML conference paper needs self-review, pre-submission QA, camera-ready checking, section-by-section critique, citation-risk inspection, or rebuttal/review-response drafting. Skip this for initial drafting and use `paperreview` only when the user explicitly wants external submission.Votes: 0GitHub stars: 444
- PaperreviewUse when the user explicitly wants to upload a final or near-final PDF to paperreview.ai for an external second opinion. Skip this for local paper critique, which should go through `paper-review-pipeline` first.Votes: 0GitHub stars: 444
- Proactive ExplorerUse when missing context may be recoverable from local code, files, logs, or environment evidence before asking the user or making assumptions.Votes: 0GitHub stars: 444
- Prompt PolisherUse when the user explicitly wants rough notes, voice transcription, or stream-of-consciousness instructions rewritten into a clean reusable prompt for another model or for later execution. Do not use this just because the input is messy; use input-triage when the job is to separate goals, claims, and options.Votes: 0GitHub stars: 444
- Question RefinerUse when a research question is still vague and must be clarified into a structured deep-research brief before actual literature research or execution. Skip this if the user already has a concrete paper draft or a ready-to-run research specification.Votes: 0GitHub stars: 444
- Research Lead SidecarUse when the user wants multi-agent division of labor for research-led work and the lead should stay on the critical path while 1-2 bounded sidecars handle low-coupling tasks. Do not use this for tiny tasks, fully sequential debugging, or overlapping refactors.Votes: 0GitHub stars: 444
- Paper2htmlUse when turning an academic paper PDF/arXiv/OpenReview page/local LaTeX source into a single-file Chinese HTML deep-reading page, especially when the user wants a Cheat-Sheet style explanation, KaTeX formulas, figure/table evidence, validation, or a publishable research page.Votes: 0GitHub stars: 444
- Spec First MvpUse when one idea feels exciting enough that the user may rush into implementation before the scope is stable. Turn the idea into a spec seed, define 1-3 throwaway MVP probes, and set a go/no-go gate before full design or execution.Votes: 0GitHub stars: 444