Docs & writing
16,632 rows, by stacks then stars
3,030 of these skill files have been read, by 1,951 distinct authors, and what they tell an agent counted. What Docs & writing authors agree on, and what they forbid
grandheman/claude-sdlc/skills/qa-engineer Skill
1★ repoUse this skill for any quality assurance task: writing test plans, creating test cases, filing bug reports, performing test execution, defining quality gates, or planning regression testing. Triggers on: "write test cases", "test plan", "QA", "file a bug", "bug report", "how do I test this", "regression testing", "acceptance testing", "test coverage", "quality gate", "sign off on this", "validate this feature". Also use when reviewing PRD acceptance criteria to ensure they are testable.
grandheman/claude-sdlc/skills/release-manager Skill
1★ repoUse this skill for anything related to managing or preparing a software release: release checklists, release notes, version bumping, release planning, go/no-go decisions, changelog maintenance, deployment coordination, or rollback planning. Triggers on: "prepare a release", "release notes", "write the changelog", "version bump", "deploy to production", "release checklist", "go/no-go", "rollback plan", "release planning", "ship this", "release process", "cut a release". Use for both major releases and patch/hotfix releases.
dss-time/repo-doctor-skills/plugins/productivity-toolkit/skills/report-writer Skill
1★ repoDraft or revise a structured report from user-provided goals, audience, evidence, and format, separating facts, quotations, inferences, recommendations, and unknowns. Use when the deliverable is a report; use research-brief when the main task is gathering and synthesizing evidence, and do not invent missing facts or claim DOCX/PDF generation without available tools and explicit authorization. 根据用户提供的目标、读者、证据和格式撰写或修订结构化报告,并区分事实、引用、推断、建议和未知项。交付物是报告时使用;主要任务是搜集和综合证据时使用 research-brief;不得补造事实,也不得在缺少工具或未获明确授权时声称生成 DOCX/PDF。
dss-time/repo-doctor-skills/plugins/productivity-toolkit/skills/research-brief Skill
1★ repoDefine and answer a bounded research question with a source plan, evidence ledger, cross-checking, conclusions, unknowns, and next steps. Use when gathering or synthesizing evidence is the primary task; use report-writer when supplied material only needs a polished report, and never claim current research without accessible sources or network capability. 围绕有边界的研究问题制定来源计划、建立证据台账、交叉验证并输出结论、未知项和下一步。主要任务是搜集或综合证据时使用;已有材料只需形成正式报告时使用 report-writer;无法访问资料或网络时不得声称完成实时研究。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/documentation-sync Skill
1★ repoSynchronize documentation with a confirmed code, configuration, API, or behavior change by updating only evidence-backed README, API, configuration, example, migration, and changelog content while preserving style and language. Use for documentation-only edits; do not modify production behavior, invent undocumented facts, or use as a general code fix. 根据已确认的代码、配置、API 或行为变更,只更新有证据支持的 README、API、配置、示例、迁移和 CHANGELOG 内容,并保留原有风格与语言。用于仅文档修改;不得改变生产行为、编造未证实内容,也不作为通用代码修复。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/requirements-clarification Skill
1★ repoResolve the material product, behavior, compatibility, data, permission, security, migration, and acceptance decisions that remain open before specification or implementation. Use when a request contains consequential ambiguity; inspect repository evidence before asking one focused question at a time, then produce a clarification summary for requirements-to-spec. Do not use for an already clear small change, write the final specification, edit long-term documentation, or implement code. 在规格化或实施前,关闭仍未确定且会实质影响产品、行为、兼容性、数据、权限、安全、迁移和验收的决策。用于存在关键歧义的需求;先检查仓库证据,再一次聚焦一个问题,最终生成交给 requirements-to-spec 的澄清摘要。已清楚的小改动不使用,也不生成最终规格、不修改长期文档或实施代码。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/spec-to-work-items Skill
1★ repoDecompose a confirmed specification, implementation plan, or settled conversation into independently executable and verifiable vertical work items with dependencies, safe parallelism, conflict areas, tests, risks, and rollback notes. Use for delivery planning of a multi-behavior scope; return copyable Markdown in the current response only and never write files, invoke Shell, or create external tasks even with user authorization. Do not use for unresolved requirements, a single small fix, or a file-by-file technical-layer checklist. 将已确认规格、实施计划或已闭合对话拆成可独立执行和验证的垂直工作项,明确依赖、安全并行、冲突区域、测试、风险和回滚。用于包含多个可交付行为的交付规划;只在当前响应返回可复制 Markdown;即使用户授权也不写文件、不调用 Shell、不创建外部任务。需求未闭合、单个小修复或按文件与技术层罗列清单时不使用。
clever-cc-plugins/cc-content/plugins/cc-content/skills/cc-content-ideation Skill
1★ repoUse this skill when the owner wants content ideas, angles, or directions for a piece of content — not a finished text. Invoke when the user says "give me content ideas", "brainstorm angles for this article", "what could we post about this", "develop some directions from this briefing", "I need angles for a LinkedIn post / blog / newsletter", or pastes an article or notes and asks how the company could pick up the topic. This is the idea-generation step that precedes writing — it produces distinct strategic angles the owner can then hand to a writing skill. Do NOT use it to write the finished text itself.
clever-cc-plugins/cc-content/plugins/cc-content/skills/cc-content-research-prompt Skill
1★ repoUse this skill when the owner wants a ready-to-paste research prompt for a "deep research" AI tool (Claude, ChatGPT, Gemini, Perplexity, DeepSeek, or similar) to investigate a topic before writing content. Invoke when the user says "give me a research prompt for X", "write me a deep research prompt", "I need to research this before drafting", or "generate a prompt I can run in ChatGPT/Perplexity for research". This produces only the prompt text — it does not run research itself, call any external tool, or save results anywhere.
clever-cc-plugins/cc-content/plugins/cc-content/skills/cc-content-text Skill
1★ repoUse this skill to draft a finished marketing or PR text for an output format that does NOT have its own dedicated skill — for example a newsletter, whitepaper, landing-page copy, product description, email, webinar abstract, or ad copy. Invoke when the user says "draft a newsletter", "write the copy for this landing page", "turn this idea into a <format>", or names any text deliverable without a dedicated skill. This is the general-purpose writer for the long tail of formats. It deliberately defers: if a dedicated skill exists for the requested format (such as a blog article or LinkedIn post, or a project-specific skill), it points the owner there first. Do NOT use it for formats that already have a dedicated skill.
AnotherSava/claude-code-common/claude/skills/document-data-flow Skill
1★ repoCreate or update the data flow architecture document (docs/pages/data-flow.md).
AnotherSava/claude-code-common/claude/skills/documentation Skill
1★ repoUpdate stale documentation and comments to match current code
AnotherSava/claude-code-common/claude/skills/github-pages Skill
1★ repoArrange a project's README and GitHub Pages documentation into a consistent user-first layout: short README that links out, just-the-docs Jekyll site with a user-facing index, one page per user-facing feature (split into child pages when long), and a developer guide with technical sub-pages. TRIGGER when: setting up docs/ for a new project, adding a GitHub Pages site, writing or restructuring a README that will link to GH Pages, adding a new user-facing feature page, or asked to align docs with this project or bga-assistant. DO NOT TRIGGER when: editing unrelated docs outside docs/, working on a project that already has an incompatible docs framework (Docusaurus, MkDocs, VitePress, etc.).
AnotherSava/claude-code-common/claude/skills/memo Skill
1★ repoCapture an off-task idea to the project's memo backlog, or list and act on existing memos
ronniepinnell/casper/skills/premortem Skill
1★ repoWrite the incident report before shipping. Assume the work shipped and failed 3 months from now; write the post-mortem first, then harden the top risks. Use before locking a design, launching a feature, running a migration, or dispatching autonomous work.
ajbarea/techne/plugins/techne/skills/docs-site Skill
1★ repoMaintain the Zensical-powered documentation site — nav ordering in zensical.toml, the docs GitHub Pages workflow, CSS and JS assets, and link/anchor integrity across docs/**/*.md. Sibling of /techne:docsync (which only verifies prose claims against code). Use when the user wants the site itself audited — config, deploy pipeline, theming, assets, cross-page links — rather than content accuracy.
ajbarea/techne/plugins/techne/skills/docsync Skill
1★ repoCheck a documentation file for drift against the actual codebase — CLI commands, file paths, config keys, function signatures, version numbers, environment variables — and propose corrections. Use when the user wants to audit README.md, docs/*.md, or similar for claims that no longer match reality. Drift usually comes from refactors that forgot to update the docs.
ajbarea/techne/plugins/techne/skills/reslop Skill
1★ repoRewrite docstrings and comments by reading the actual implementation, call sites, and tests — produce grounded, factual prose instead of deleting slop. Sibling of /techne:deslop. Use when the user wants to replace overhyped or hallucinated documentation with accurate one- or two-line descriptions derived from what the code actually does.
turntuptechnologies-ai/skills/skills/write-readme Skill
1★ repoREADME を新規に作る、または既存の README を実証済みの構成で整え直すとき。「README を書いて/整えて」「README が薄い・構成を揃えたい」等で使う。概要/Stack/Quick start/Configuration/Layout/Documentation/Development/License の構成で、実装から裏を取って書く。
broneq/bdk/skills/create-adr Skill
1★ repoBDK — Broneq Dev Kit. Reusable Claude Code workflows: skills, agents, and hooks for TDD, planning, code review, and architecture documentation.
broneq/bdk/skills/explain-complex-code Skill
1★ repoGenerate comprehensive architecture documentation for complex code modules with Graphviz diagrams and examples. Use when user asks to "explain this code", "document the architecture", or wants to understand how a module/system works.
broneq/bdk/skills/graphviz-docs-compiler Skill
1★ repoCompile Graphviz diagrams (.dot files) to SVG in-place. Use when working with .dot files or markdown with Graphviz code blocks, or when user says "compile diagrams", "generate SVG from dot files", "update documentation diagrams".
broneq/bdk/skills/update-docs Skill
1★ repoBDK — Broneq Dev Kit. Reusable Claude Code workflows: skills, agents, and hooks for TDD, planning, code review, and architecture documentation.
zxc7563598/skillbox/skills/create-readme-zh Skill
1★ repo为项目生成专业的中文 README.md 文档。当用户提到"写 README"、"生成 README"、"README 文档"、"项目说明"、"自述文件"、"帮我写个 README"时触发。也适用于用户说"给项目加个说明文档"、"完善一下项目介绍"等场景。
omas-odoo/odoo-superpowers/skills/odoo-xml-conventions Skill
no license1★ repoUse when writing, reviewing, or migrating any .xml file in an Odoo module — views, actions, menus, security records, data files, QWeb templates. Holds Odoo's naming, formatting, inheritance, and cross-version syntax conventions. Invoke before adding records to views/, security/, data/, or report/ directories.
The same file is in 1 other repository
scoobydont-666/shared-claude-skills/skills/ms-office-suite Skill
1★ repoGenerate professional Excel workbooks, Word documents, PowerPoint decks, and PDFs, including CPA-grade financial reports, cost analyses, ROI projections, executive summaries, budgets, and break-even reports. Uses python-docx, openpyxl, python-pptx, reportlab, weasyprint, and Markdown. Use when asked to generate a report, spreadsheet, PDF, pitch deck, presentation, financial projection, cloud-cost analysis, or other Microsoft Office-style deliverable.
scoobydont-666/shared-claude-skills/skills/write-a-prd Skill
1★ repoCreate a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.
The same file is in 3 other repositories
RealDougEubanks/ClaudeMarketplace/skills/agent-based-development/skills/abd-docs Skill
1★ repoABD Documentation agent: updates README, ToDo, assumptions, and changelogs from all handoff artifacts and the codebase.
RealDougEubanks/ClaudeMarketplace/skills/changelog-generator Skill
1★ repoGenerates a structured CHANGELOG.md following Keep a Changelog format from git history and ABD handoff artifacts. Prepends new version sections to existing changelogs.
RealDougEubanks/ClaudeMarketplace/skills/doc-refresh Skill
1★ repoComplete documentation refresh — audits for stale docs, creates missing docs, and rewrites everything for a 2am on-call engineer with zero assumed context. Security items are prominently callout-boxed.
RealDougEubanks/ClaudeMarketplace/skills/incident-report Skill
1★ repoGenerates professional incident reports using customizable templates. Supports outage, security, performance, and data-loss incident types. Extensible via templates/ and rules/.
RealDougEubanks/ClaudeMarketplace/skills/test-writer Skill
1★ repoGenerates comprehensive unit and integration tests for a given file or function, auto-detecting the project test framework and matching existing test style.
Huangleyang125207/ctrl-c-v-code-skills/skills/human-ai-schedule Skill
1★ repoCo-author doctrine for shared, half-hour-block daily schedules. Make sure to consult this skill whenever working in a dated daily log, journal, retro, or coordination file shared with a coworker — even if the user only says "log this at 11:00" or "what did we say last Tuesday." Default behavior of dumping procedural details, paraphrasing voice into corporate prose, or fragmenting one task across multiple cells must defer to this skill — entries distill to result + significance, and a cell is removed only when its time falls inside a verified-active task's span (never pre-merged on guess). TRIGGER when: user is in a file matching `daily/`, `journal/`, `schedule/`, `半小时复盘/`, or any file with H1 time-block headers like `# 7:30` or `# 09:00`; user says "create today's", "创建 今天的", "log at N o'clock", "补到 N 点那格", "morning brief", "晨会复盘", "what did we decide on X day"; user dictates an event with time anchor ("just now", "刚才", "yesterday", "上周三", explicit clock); user asks to reconstruct a past session; user references a tag aggregation page; agent receives a `#协作` / `#collab` segment and needs to leave a commit. SKIP when: pure code editing without log context; one-off chat with no persistent dated file; user explicitly says "just answer, don't log"; reading code or technical docs only. Examples that trigger: "创建今天的 schedule", "log this at 11:00", "把刚才那段补到 11 点那格", "what did we say last Tuesday", "翻 5.7 那次 session", "记一下今天去了彭镇喝茶". Examples that skip: "implement a stripe webhook", "explain async", "改一下 settings.json 的 permission", "rename this private function".
goldenprofile/llm-skills/docs-generator Skill
1★ repoГенерация и аудит документации для соло-разработчика: README, ADR, Python-docstrings (Google-стиль), синхронизация CLAUDE.md/AGENTS.md. Документирует «почему», а не пересказывает код; находит отсутствующую и устаревшую документацию. Используй когда пользователь просит написать или обновить README, оформить ADR, добавить или проверить docstrings, синхронизировать CLAUDE.md и AGENTS.md, или говорит «задокументируй проект», «doc audit». Для спек/планов/брифов — см. spec-writer; DoD/tooling-обвязку агентских правил настраивает harness-engineering.
goldenprofile/llm-skills/spec-writer Skill
1★ repoПишет проектные документы как Markdown-файлы в трёх режимах: spec (техспецификация — проблема, цели, архитектура, ADR-решения, риски), plan (план реализации — фазы, оценки, зависимости) и brief (записка для CEO без кода и терминов). Заточен под solo-разработчика. Используй когда пользователь просит «напиши спеку», «tech spec», «design doc», «RFC», «запроектируй фичу», «план разработки», «разбей на фазы», «аналитическая записка», «executive summary». Только документ — ничего не исполняет; для документации по коду (README/docstrings/ADR) — см. docs-generator.
goldenprofile/llm-skills/test-writer Skill
1★ repoНаписание тестов для Python-бэкенда (pytest-first): стратегия покрытия критического пути, дизайн кейсов (границы, ошибки, идемпотентность), фикстуры и параметризация, фабрики (factory_boy), паттерны Django (pytest-django, client, БД-маркеры), FastAPI (httpx AsyncClient, dependency_overrides) и aiogram 3.x (моки Bot, тесты хендлеров). Используй когда пользователь просит написать тесты, покрыть код/фичу/модуль тестами, добавить регрессионный тест на баг, настроить pytest/фикстуры/фабрики, или говорит «напиши тесты», «покрой тестами», «нужен тест на». Аудит качества уже существующих тестов — см. test-coverage-auditor.
horizon-foundry/foundry/skills/scaffold Skill
1★ repoUse when starting a new project, or when an existing project still has placeholder markers in its docs. Declares the project's profile (experiment, internal-tool, web-product, service, or library), then stands up the doc set, posture, and deploy or publish shape that profile actually needs, filled from the builder's answers, not a blank prototype. Not for maintaining docs on an already-scaffolded project (that is document) or deciding whether the idea is worth building (that is frame).
bhuvangupta/vapt-claude/skills/vapt-report-pdf Skill
1★ repoFull-spectrum web application VAPT skill for Claude Code, OpenCode, Codex CLI & Gemini CLI — from reconnaissance to exploitation to remediation reporting
bhuvangupta/vapt-claude/skills/vapt-report Skill
1★ repoFull-spectrum web application VAPT skill for Claude Code, OpenCode, Codex CLI & Gemini CLI — from reconnaissance to exploitation to remediation reporting
guntherb7/helm/business/.claude/skills/new-proposal Skill
1★ repoGuided proposal generation. Asks discovery questions, references past pricing, generates document in your voice using writer agent.
alainator/worldcodex/.claude/skills/designing-lore Skill
1★ repoCreates mythologies, legendary figures, historical eras, relics, and sacred artifacts for fictional worlds. Use when building creation myths, founding legends, historical timelines, mythic heroes, symbolic systems, or sacred objects, or when user says "origin story", "myth", "legend", "relic", "artifact", "ancient history", or "prophecy". Does NOT write final files — use /writing-worldbuilding for that.
alainator/worldcodex/.claude/skills/designing-worlds Skill
1★ repoGenerates physical world foundations: biomes, planetary systems, climate, and ecological zones with embedded narrative tension. Use when creating a new world, planet, biome, or ecosystem, or when user says "new world", "new planet", "new biome", "build a world", "create a setting", or "environmental design". Does NOT write final files — use /writing-worldbuilding for that.
alainator/worldcodex/.claude/skills/verifying-completion Skill
1★ repoRuns a mandatory completion checklist before declaring any worldbuilding task finished. Catches missing frontmatter, broken cross-references, unlinked glossary terms, and deferral language. Use after writing any content, before reporting task complete, or when user says "is this done", "verify", "check my work", or "completion check". Does NOT write content — only verifies.
alainator/worldcodex/.claude/skills/writing-science Skill
1★ repoWrites new science files following academic prose standards: third-person voice, present tense for laws, in-universe terminology, consistent equation formatting, citation format. Use when creating new physics, chemistry, biology, or science files, expanding existing science content, or when user says "write", "create", "draft", "formalize", or "derive" in a science context. Does NOT write civilization or narrative content — use /writing-worldbuilding for that.
alainator/worldcodex/.claude/skills/writing-style Skill
1★ repoGenerates a WRITING.md file with YAML tokens for prose consistency — voice, tense, forbidden words, citation format, equation format, locked spellings — paired with usage rationale. Use when establishing prose standards, updating style rules, or when user says "WRITING.md", "style guide", "prose standards", "writing tokens", "voice", "style system", or "writing rules". Does NOT write content — generates the style reference only.
alainator/worldcodex/.claude/skills/writing-worldbuilding Skill
1★ repoWrites new worldbuilding content: civilizations, characters, locations, factions, events, languages, or narrative elements. Use when creating new entries, expanding existing ones, or when user says "create", "write", "add", "flesh out", "build", or "expand" for any non-science content. Does NOT write science files — use /writing-science for that.
donatassimkus/claude-ai-skills/skills/blog-post Skill
1★ repoCreate an SEO blog post from a primary keyword on a CMS-backed site. Runs end-to-end autonomously by default (no in-process gates): keyword intake → SERP data pull → competitor page scrape → gap analysis → outline → draft → image generation → publish → comprehensive end-of-run self-audit. Auto-fixes known failure modes (zero counts, em-dashes in structured fields, source URL rot, keyword density drift) without prompting the user. Escalates only what genuinely needs human judgement (cannibalization >30% with adjacent post, factual claim that can't be sourced). Opt-in gates via --review-outline / --review-images / --review flags. Loads a per-site pipeline config for shortcodes, author, paths, taxonomy, geography, currency, editorial rules. Enforces forbidden-words ban + zero em-dashes across EVERY authored field (body, title, excerpt, structured-field rows, meta) + keyword-density rules (primary 1-2% for entity articles, never 2x per paragraph; each secondary 1-3x distributed across H2s, never >5x). Supports batch mode with daily schedule.
donatassimkus/claude-ai-skills/skills/cold-outreach Skill
1★ repoCold outreach execution — writing cold emails, link building outreach, partnership pitches, influencer outreach, and follow-up sequences. Use when asked to write outreach messages, build link building campaigns, or pitch partnerships. Scope is the message and the sequence; the strategic role of cold outreach inside a wider lead generation system, and cold email deliverability setup (SPF, DKIM, domain warmup), are adjacent disciplines handled separately.
donatassimkus/claude-ai-skills/skills/content-plan Skill
1★ repoPlan a blog content program for a registered site. Turn a broad keyword, or one or more skills, into a validated pillar-and-cluster map and a seeded keyword queue that the blog batch writes from. Each row carries volume, difficulty, search intent, a content format, secondary keywords, People Also Ask questions, SERP features, competitor entities, internal-link targets, and a priority score. Researches demand and SERP intelligence with your keyword and SERP tools, gates against cannibalization and competitor coverage gaps, and ranks by demand x winnability so a low-authority site builds the winnable posts first. Use when the user says /content-plan, "plan blog content for <site>", "build a content map", "turn this skill into blog posts", "what should we write for <site>", "seed the keyword queue", or wants a content or keyword plan before batching. Plans only: it never writes, publishes, or builds engine adapters. Writing a single post, running the batch that writes many, general SEO frameworks, and market research are each a separate step or skill, not this one.
donatassimkus/claude-ai-skills/skills/hooks Skill
1★ repoUse when writing or improving the opening of any piece of content — ads, emails, videos, social posts, landing pages, outreach messages. Covers hook types, hook structures, the 70-20-10 testing framework, how to build a hook library, the Colleidoscope Process (squeezing a winner 10-100x), 50-hook session structure (40/10 proven/experimental split), and call-out specificity. Invoke when asked to write a hook, improve a headline, make an ad more compelling, or stop the scroll.
donatassimkus/claude-ai-skills/skills/optimize-vs-skill Skill
1★ repoMulti-skill autonomous quality optimizer. Analyzes a target (website, codebase, copy, campaign, document), locks an objective function, proposes relevant skills, fans out to parallel per-skill auditors, arbitrates cross-skill conflicts via a dedicated arbiter subagent, stops at diminishing returns or max rounds, produces a detailed scorecard and recommendation report with reject list and tradeoffs named. Invoke when the user says "make this as good as possible", "iterate on quality", "optimize this to world class", "run a multi-skill audit", "push this to its ceiling", "auto-optimize", or "run the optimizer".
donatassimkus/claude-ai-skills/skills/tone-of-voice Skill
1★ repoVoice and tone reference. Two layers: universal rules that stop writing sounding like AI, and a personal voice profile captured from how one person actually talks. Covers register (how formal, and who decides), the politeness and energy dials, and person (I, you, or neither) with a deterministic first-person density check. Load as a reference layer whenever content is being written, and use directly to audit existing content. The universal layer works immediately with nothing filled in; the personal profile is optional and can be added later.
LukeJMadden/Veltrix-skills/skills/content/newsletter Skill
1★ repoNewsletter pipeline skill — drafting, quality assurance, approval flow, scheduling. Use when creating, reviewing, or managing email newsletters.
vanthienha199/openclaw-skills/translate Skill
1★ repoTranslate text, files, and conversations between any languages. Auto-detects source language. Preserves formatting (markdown, code blocks, tables). Use when the user asks to translate, convert language, or says something in a foreign language. Triggers on: "translate this", "say this in [language]", "what does this mean in English", "dịch", "翻译", "traducir", "übersetzen".
ArielSmoliar/safe-agent/tests/fixtures/vulnerable-mcp-config Skill
1★ repoFormats and aligns Markdown tables in the current file. Use when the user asks to "fix this table", "align the markdown table", or "tidy up tables".
ArielSmoliar/safe-agent/tests/fixtures/vulnerable-untrusted-input Skill
1★ repoSummarizes release notes from a project's upstream changelog URL and applies the relevant updates to the local CHANGELOG.md. Use when the user asks to "pull the latest changelog" or "sync release notes".
lennney/gate-all-skills/skills/website/seo-copywriting Skill
no license1★ repo抓眼球 SEO 标题+描述写手。18 套标题公式、强力词库、CTR 提升技巧、好奇心缺口模板。写 title/description 前加载。
YuAICode/ai-skills/skills/readme-init Skill
1★ repo扫描项目自动生成或刷新 README(检测技术栈/结构/可运行脚本)。用户说「/readme-init」「帮我生成 README」「项目没有 README,帮我写一个」「刷新/更新 README」「README 太旧了帮我刷新」时触发。
KirKruglov/OFFICINA/skills/release-finalize Skill
1★ repoFinalize a product release and prepare the repo for a public push or deploy — updates the changelog and root README, scans for secrets and version consistency, creates an annotated git tag. Does NOT merge, push, or deploy. Universal — auto-detects release artifacts, optional .release-finalize.yml overrides. Manual-invocation only via /release-finalize — the skill does not self-activate.
assoumaaa/odoo-superpowers/skills/odoo-xml-conventions Skill
no license1★ repoUse when writing, reviewing, or migrating any .xml file in an Odoo module — views, actions, menus, security records, data files, QWeb templates. Holds Odoo's naming, formatting, inheritance, and cross-version syntax conventions. Invoke before adding records to views/, security/, data/, or report/ directories.
The same file is in 1 other repository