注释
代码注释与标注
concept-dissector-9step
jysd-ai
Deep concept learning and explanation via a strict 9-step "Concept Dissector" workflow (Overview, Definition, Deconstruct, Mechanism, Ecology, Comparison, Practice, Critique, Synthesis). Use when users ask to understand, teach, benchmark, or critically evaluate a concept and need clear boundaries ("what it is NOT"), trade-offs, practical MRE, pitfalls, and intuitive analogy.
protocolsio-integration
TimLai666
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
documentation
josavicentevw
Generate and maintain high-quality technical documentation including API docs, README files, architecture documentation, user guides, and code comments. Use when creating documentation, writing README files, documenting APIs, or when user mentions documentation, docs, or technical writing.
minimal-implementation-explainer
sethmblack
Transform complex technical concepts into minimal, working code implementations that build genuine understanding - the Karpathy pedagogical approach.
research-writing
Nonsteroidevangel872
科研论文写作助手，提供 30 个 Prompt 模板覆盖论文写作全流程。 当用户提到：论文写作、润色、翻译、文献综述、摘要、引言、方法章节、回复审稿人、基金申请、研究计划、学术演讲 PPT、LaTeX 编辑、学术图表、实验结果分析、模拟审稿、去 AI 味、文献对比、找研究空白、论文大纲时使用。
impeccable-onboard
SebastiaanWouters
"Skills-only equivalent of impeccable.style /onboard. Design or improve onboarding flows, empty states, and first-time user experiences. Helps users get started successfully and understand value quickly. Use for frontend and UI design tasks."
pare-docs
aahoughton
Cuts bloat from a project's prose documentation — README, guides, package docs — by first deciding what each file is for, then in three passes: necessity, cross-file redundancy, then concision and tone. Written for docs that were drafted with LLM help and carry the usual tells: long, conversational, over-complete, redundant across files. Use this skill when the user asks to tighten, pare, trim, or de-slop documentation, or says the docs are too long or repeat themselves. Triggers on phrases like "these docs are bloated", "tighten up the README", "cut the docs down", or "the docs repeat themselves". Changes documentation only — never executable code.
ai-diff-reviewer-generate-extension
DailybotHQ
Generates a repo-tailored review-configuration file (.review/extension.md by default, or a full replacement prompt-file in advanced mode) by inspecting THIS codebase — stack, architecture, security surface, existing conventions, historical pain points — and producing concrete, code-anchored severity overrides. Uses the harness's Read/Grep/Glob tools to gather evidence before writing (12+ tool calls minimum). Default output extends the bundled AI Diff Reviewer prompt with project-specific rules; advanced mode replaces it entirely. Use when the developer says "customize the review for this repo", "generate review rules", "help me write my .review/extension.md", or when the local ai-diff-reviewer skill activates on a repo that has no extension file yet.
ai-diff-reviewer-setup
DailybotHQ
Interactive installer for the AI Diff Reviewer GitHub Action — walks the developer through 6 key decisions (provider, strictness, trigger mode, external-contributor policy, PR description mode, complexity labels), detects the repo's stack for sensible defaults, and writes a working .github/workflows/pr-review.yml tailored to those choices. Also acts as the reference manual for every action.yml input any coding agent might be asked about ("what is strictness?", "how do I use label-gate?"). Use when the developer says "set up AI Diff Reviewer for this repo", "configure the reviewer action", "install the AI Diff Reviewer action", "help me create the pr-review workflow", or when the local ai-diff-reviewer skill is present on a repo that has no .github/workflows/pr-review.yml yet.
golang-documentation
jangrui
"Comprehensive documentation guide for Golang projects, covering godoc comments, README, CONTRIBUTING, CHANGELOG, Go Playground, Example tests, API docs, and llms.txt. Use when writing or reviewing doc comments, documentation, adding code examples, setting up doc sites, or discussing documentation best practices. Triggers for both libraries and applications/CLIs."
golang-code-style
jangrui
"Golang code style conventions — line length and breaking, variable declarations, control flow clarity, when comments help vs hurt. Use when writing or reviewing Go code, asking about style or clarity, or establishing project coding standards. Not for naming conventions (→ See samber/cc-skills-golang@golang-naming skill), linter configuration (→ See samber/cc-skills-golang@golang-lint skill), or doc comments (→ See samber/cc-skills-golang@golang-documentation skill)."
review
crodris
This skill should be used when the user asks to "review this PR", "review PR 107", "review these PRs the same way", "do a visual pass on this branch", "verify this against the issue", pastes a pull request URL to review, or asks for a UI change to be checked before merge. Also use when the user asks whether a reviewed PR is safe to merge, or asks to escalate or downgrade a finding's severity. Verifies a pull request against the tracker issue it claims to close, on a running build, with measured evidence, then posts one review with line-specific findings inline and general findings in the summary body.
ai-diff-reviewer-address-review
DailybotHQ
Close the review loop in one invocation — a bare invocation on a fresh context is fully specified — it targets the current branch's open PR. Surveys ALL the PR's CI health (every workflow and check — failing checks diagnosed from logs and fixed, a behind branch updated, at most one flake re-run), checks whether the AI Diff Reviewer run covered the current head — and when it never ran because the trigger label is missing, arms it — adding the label is the loop's first move, not an error. Walks the findings (apply / defer / skip; commits + pushes in small Conventional Commits batches), then re-arms the reviewer adaptively (label-gated → toggle off/on or add; push-triggered → confirm the new run; no workflow → offer the local review). Artifact-first; skips minimized/stale reviews; multi-leg aware. Use when the developer says "address the review and re-run", "resolve the reviewer comments and toggle ready", "fix the failing workflows", "loop the review", "the PR has no review yet — trigger it".
code-quality
vanillagreencom
"Load for any coding or development task in any repository: writing, changing, fixing, refactoring, or testing code or scripts in any language."
drawings
meech-ward
Create or change hand-drawn style drawings (Excalidraw scenes) in elaborat.ing and embed them in notes. Use when the user wants a sketch, a whiteboard or shapes placed by hand in an elaborat.ing project.
SKILL.md — OpenClaw Agent Skill
freaxnx01
Pick a repo under ~/projects/repos via fzf and launch Claude Code — with slot tracking, per-slot Telegram pages, and Remote Control integration.
summarizing-papers
motoki4869
Use when the user points to a paper PDF under ai_news/article/ (by filename, title, or "この論文") and asks to summarize it, explain it, or make it understandable — always produce a technical Japanese summary, an elementary-school-friendly explanation, and a beginner-friendly explanation as three files, even if only one was explicitly requested.
github-threads
nitedani
"Any GitHub thread you're in: the live loop (watcher, 👀, replies, which threads are yours) and the posting gate every post, edit and PR body passes."
coding-standards
dhkong01
Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.
pdf-anonymize
jamesconsultingllc
True-redacts PII from PDF, Word (.docx), and Excel (.xlsx) documents before sharing. PDFs have glyphs physically removed and replacement text re-laid; DOCX patches run slices to preserve formatting; XLSX replaces cells, comments, headers, defined names, and properties. Handles names, addresses, account numbers, credit scores, and merchants/stores/phones/cities on transaction lines. Works on ASCII PDFs and modern bank statements with CID-encoded subsetted fonts (BoA, Chase). Single file or directory (with --recursive). Output cannot be recovered via Ctrl+F, pdftotext, or another AI. Trigger on "anonymize/redact/sanitize/de-identify this PDF/Word/Excel", "scrub PII", "remove my name/address", "share this safely" — even when the user just attaches a file and asks to strip identifying info. DO NOT USE FOR visual watermarking, legacy .doc/.xls, or .pptx. Do NOT use nano-pdf — it re-renders pages via image AI and corrupts financial text.
atmofab-review-loop
seiya
Use when implementation in this repository reaches a pause and review begins, when running subagent or Codex review rounds, when fixing findings and moving to the next round, and when judging whether the loop has converged. Required reading for 「レビューして」「レビュー回して」「指摘を直して」「codex review」「この PR merge していい？」「まだ見るべきところある？」 and immediately after finishing the implementation of an audit finding or an issue. The subject is review of changes you made; do not use it for reading existing spec, docs, or implementation to judge whether they are sound (review without a change).
hyfa
syntropika
Use the Hyfa CLI to choose executable GitHub Issue work, inspect dependencies, manage Issues and assignments, reconcile queued changes, and generate Issue graph explorers. Use when a task involves Hyfa or dependency-aware GitHub Issue planning.
humanizer-en
kadirhanpolat
Remove signs of AI-generated writing from English text. A more robust English humanizer built on Wikipedia's "Signs of AI writing" guide and extended with structural, data, quote, conversational, and domain-specific patterns ported from the Turkish insanlastirici project. Detects 85 universal patterns plus 45 domain-specific guides (LinkedIn, academic, news, SEO blog, e-commerce, corporate, medical, tech, marketing, self-help, travel, video script, education, finance, startup, email, code documentation, dialogue/screenwriting, fashion/beauty, real estate, customer support, parenting, legal writing, scientific paper methods/results/discussion, English regional variation, HR/performance reviews/job descriptions, social media, government/public communications, sports/match analysis, food writing/recipes, podcast/long-form audio scripts, mental health/therapy content, obituaries/eulogies, grant writing/nonprofit communications, architecture/interior design writing, personal finance/budgeting content, event planning/wedding content, pet care/veterinary writing, political/opinion writing, automotive/car review writing, fitness/exercise content, gardening/horticulture writing, museum/cultural institution writing, cybersecurity writing). Adds modes (fast/standard/focused), intervention levels (minimum/medium/ maximum), cluster guide, density score, domain-context legitimacy table, register inconsistency detection, claim list mode, change summary mode, comparative analysis mode, and voice profile estimation.
clean-codejs-comments
DamianWrooby
Commenting patterns that improve readability and maintainability.