Docs & Writing

benedictking Bundle

Use this skill when users need current documentation, setup steps, API references, or code examples for a named library, framework, SDK, or API. It fetches up-to-date Context7 docs.

benmarte Skill

Run the full measurement suite defined in .claude/autoimprove/config.md and report the current codebase quality score (0-100). Use this to check your baseline before running the improve loop, or to spot-check at any time.

bestiaya Skill

Report status — use on "what's the status", "where do things stand", "show the board", or /ctx-status; reads the board and case files, reports goal chain, case states, pending decisions and one-offs in plain language. Also triggers on Chinese — 用户说"现在什么情况""进展如何""有哪些案""资产都在哪""看一下板"，或显式 /ctx-status 时用。

breakthrough-edu Skill

Write down how the owner does a kind of work: one Method note when a piece of work closes, a Playbook when the owner asks for one (composed from the folder's methods, or ⭐ dictated straight from how they already work when there are none, day one included), and the door of any folder born along the way. Runs when the owner calls this skill by name, asks for a method or a playbook to be written, or when the session was told at the outset to write a Method when the work closed. ⛔ Work-closing phrasing alone ("we are done", "that went well", "wrap up") is not a request for this skill; session closeout belongs to breakthrough-session-report. NOT for a pit that hurt (that is a Lesson, written at session closeout), NOT for a call that still stands (that is a decision), NOT for dead repeatable steps (that is breakthrough-sop-builder), and ⛔ NOT the runner of a playbook's four beats: those live in the door itself and run without any skill (doctrine section 9.3).

breakthrough-edu Skill

Close out a working session in the owner's second-brain vault while whoever was in it still remembers: the Lesson it earned, the decision made but never written, anything reusable, and one baton note in `00_Inbox/` for the next session to read and archive. Use when the user says "wrap up", "close out", or otherwise ends a working session that produced something worth keeping. ⛔ NOT the end of the day, which is the owner's own command-base skill ("compile", "done for today"): a day ending is not a piece of work ending, and the two have separate words. NOT the weekly maintenance ritual (that is my-second-brain's distill mode), and NOT the place to write a Method (that is breakthrough-method-builder, which runs when a piece of WORK closes, not when a session does).

aigne-io Bundle

Generate and update structured documentation from project data sources. Supports initial generation and modifying existing documents. Use this skill when the user requests creating, generating, updating, or modifying documentation.

aigne-io Bundle

Translate Doc-Smith generated documentation into multiple languages. Use this skill when the user requests document translation, localization, or multi-language support. Supports batch translation of documents and images.

akegaviar Bundle

Research imageboards and forums (4chan, 5ch, leftypol, kohlchan, endchan, zzzchan, 2ch.hk, DCInside, Arca.live, Machi BBS, Shitaraba + FoolFuuka archives). Use when the user wants to (1) browse boards and catalogs across sites, (2) search threads by keyword with FTS5, (3) export threads to markdown with optional local image download, (4) search historical archives, or (5) research community sentiment and discussion on any topic mentioned on imageboards. Trigger on mentions of 4chan, /biz/, /g/, /pol/, imageboard, anonymous forum, or "what are people saying about X". No auth required.

alahmadiq8 Bundle

Edit and manage Obsidian vaults — create, read, update, and delete notes, manage properties/frontmatter, handle links and backlinks, work with tags, tasks, daily notes, templates, bases, and more. Uses the Obsidian CLI for safe vault operations when available, with direct file editing as fallback. Use this skill whenever the user mentions Obsidian, vault, knowledge base notes with wikilinks, frontmatter/properties on markdown files, daily notes, or any task involving an Obsidian vault — even if they just say "my notes" or reference a folder that looks like a vault (has .obsidian/ directory).

alexsmedile Bundle

Update project documentation after changes — CHANGELOG.md entries (Keep a Changelog, [Unreleased] or versioned), README, STATUS.md, AGENTS/CLAUDE/GEMINI files, and docs/. Use for "update the changelog", "write a changelog entry", "update the docs", "document these changes", or doc refresh before a release. Resolves symlinks and edits the real file. Does not commit, push, or tag.

alfredzhang98 Skill

Search, download, and extract text from academic papers across arXiv, PubMed, Semantic Scholar, Crossref, OpenAlex, and other scholarly sources. Use when the user asks to find literature, compare search results, resolve a DOI or paper identifier, download a paper PDF, or read paper text through the installed paper-search CLI.

alfredzhang98 Bundle

Extract numbered figures and tables from a local academic-paper PDF into named PNG files by detecting caption blocks and cropping the associated page regions. Use when a paper note needs inline figures or tables, when raw page images are not useful, or when the user asks to extract figure-level assets from a PDF.

alfredzhang98 Skill

Extract clean Markdown from web pages and supported media URLs with the installed Defuddle integration, optionally saving a structured note and local images into an Obsidian vault. Use when the user provides an article, documentation page, repository page, YouTube URL, Apple Podcasts URL, DOI, or arXiv URL to read, summarize, or archive.

alo-exp Skill

Generic Multi-Source Consolidator: synthesizes content from any set of input sources — documents, research notes, interview transcripts, meeting summaries, AI platform responses, or any mix — into a unified, well-structured report. When invoked with a raw AI responses archive (produced by the orchestrator or a specialist skill), operates in AI-Responses mode and produces a Consolidated Intelligence Report (CIR) or structured synthesis per a consolidation guide. When invoked directly by the user with arbitrary source content, operates in Generic mode and produces a synthesis report tailored to the content type. If a consolidation guide (.md file) is provided, follows its prescribed output structure exactly — the guide is the sole structural authority.

alvarezgzx-lab Bundle

Procesa una actividad práctica de un curso/bootcamp (página, lectura, PDF) y entrega siempre 5 salidas en este orden: transcripción literal, resumen ejecutivo, prompts avanzados para Claude, ideas de skills, y recursos descargables. Úsala cuando el usuario pida analizar o preparar una actividad, tarea o proyecto de un curso.

alvarezgzx-lab Bundle

Evalúa módulos, cursos o secuencias didácticas de Diseño Instruccional (DI) usando una rúbrica de 20 criterios ponderados que integra Bloom, SOLO, Fink y Marzano, más criterios de microlecciones, instrumentos de evaluación, UX/atención, analítica y humanización de tono. Úsala siempre que el usuario pida evaluar, auditar, revisar, dar retroalimentación pedagógica, o darle una segunda opinión a un módulo/curso/secuencia didáctica propia o ajena — aunque no mencione la palabra "rúbrica" explícitamente. También aplica cuando pegue objetivos de aprendizaje, microlecciones, actividades o instrumentos de evaluación y pregunte si están bien diseñados, o cuando suba un PDF/DOCX/PPTX de un curso y pida una revisión de calidad pedagógica.

ameistad Bundle

Rewrite text that sounds generic, formulaic, overly polished, or AI-generated into natural, specific writing while preserving the author's meaning and voice. Use when users ask to "make this sound human", "de-AI this", "reduce AI tone", "rewrite naturally", "spot AI tells", or improve authenticity in emails, essays, posts, documentation, and product copy. Return a revised version with concise improvement suggestions. Do not use for grammar-only proofreading, plagiarism checks, authorship detection, or fact-check-only requests.

antiwork Skill

Draft GitHub issues for the Gumroad codebase. Outputs to an unstaged markdown file in the repo root. Never creates issues on GitHub. Triggers on: "create issue", "write issue", "draft issue", "write a bug report", "file an issue", "create a ticket", or when the user describes a problem or feature they want to turn into a GitHub issue.

argent-gnome Skill

The house v2 build session — implement ONE plan unit from a kickoff brief, self-review it, reconcile that unit's docs, and report back through the house records. Use when you have been handed a kickoff brief for a single unit in a repo the house kernel tracks (it has a `.house/` dir). Do NOT use to drive a whole slice (that is house-orchestrator), to shape new work (house-shaper), or for non-build chat.

arm-software Skill

Validate the lavatube documentation

espressif Skill

Run make test to green first, then make itest; report all failures and re-run failing tests one by one to form an RCA and fix where the cause is clear.

evotecit Bundle

Use when retiring PSWritePDF behavior into OfficeIMO and PSWriteOffice, comparing PDF gaps, or deciding where PowerShell-facing PDF features should live. Keep reusable PDF behavior in OfficeIMO and PSWriteOffice cmdlets thin and friendly.

fabienjuif Skill

At the end of a session, capture what was learned into the repo's documentation so it isn't lost and future sessions start cheaper. Use when the user says "capture docs", "save what we learned", "update docs", "sync docs", or runs "/capture-docs", typically when wrapping up. Relies on the conversation already in context plus cheap git signals — it does NOT re-research the codebase. Updates human-facing docs (READMEs, docs/) and AI-facing docs (CLAUDE.md, AGENTS.md), keeping AI docs as pointers to human docs, and ensures what it writes is discoverable from the nearest CLAUDE.md/AGENTS.md.

faiz-sayyad Skill

Generate a structured end-of-day summary of outreach activity. Use whenever the user asks to wrap up the day, get a daily digest, summarize outbound work, prep a Slack update, or track what happened across sends, replies, and meetings. Also use for weekly summaries or when the user says "give me a report on today's outreach."

faiz-sayyad Skill

Classify an incoming outbound signal by tier (T1/T2/T3), set the SLA, and recommend the outreach channel. Use whenever the user pastes signal data, describes a buying signal, mentions a target account firing a signal, or asks how to prioritize incoming outbound signals — even if they don't explicitly use the word "triage." Also use for questions like "should I reach out?", "how fast should I respond?", or "is this a hot lead?"

fivetran Skill

Use this skill as part of the Copy Connections workflow to execute a validated copy plan. Creates connection shells (without credentials), installs Quickstart packages, and produces a results file with next steps. Refuses to run without a passing validation report. Invoke from the copy-connections coordinator.

foreveryh Bundle

Generate comprehensive analysis articles from Claude skills. This skill should be used when you want to analyze a skill from the Anthropic skills repository and create a detailed tutorial article explaining its structure, design patterns, and usage. Perfect for creating documentation, tutorials, and educational content about existing skills.

foreveryh Bundle

Automate article validation, semantic commit generation, and git publishing for MDX documentation. Validates syntax, runs build checks, creates semantic commits, and pushes to remote repositories.

foreveryh Bundle

Import external articles into a Fumadocs project with automatic multi-language translation (en, zh, fr), AI-powered classification into 8 categories, image processing, and MDX conversion. Use this skill when the user wants to import an article from a URL into their Fumadocs documentation site.

frankxai Skill

Create Markdown-first skill trees, progression tracks, node cards, trials, rewards, prerequisites, YAML frontmatter schemas, and git-friendly mastery systems. Use when the user wants MD-based gamification, skill progression, learning paths, or portable skill-tree repos.

frankxai Skill

Design Unity-compatible progression, skill tree, ability, achievement, leaderboard, reward, and data-driven gameplay systems from Markdown/YAML source. Use when building Unity skill systems, ScriptableObject adapters, game progression prototypes, or engine-ready mastery specs.

frankxai Skill

Use when authoring or updating a Blue Life Commons species page (cetacean, pinniped, turtle, shark/ray, reef). Produces schema-valid Markdown with sourced claims and honest review status. Triggers — "write a species page", "add a species to the commons", "document <species>".

gaofeng21cn Bundle

Use when turning academic or medical-research materials into defense deliverables, including timed oral scripts, PPT speaker notes, narrative/storyline rewrites, reviewer-facing questions with background notes, or paired slide-notes plus script outputs. Trigger on PPT/PPTX plus source PDFs, thesis zip packages, proposal/application materials, dissertation defenses, project defenses, or requests such as “5分钟逐字稿”, “讲者备注”, “答辩问题”, “控制节奏”, or “叙事逻辑”. Pair with Office/PPTX/PDF extraction skills for file operations.

gcrft123 Skill

The Tailr review loop — wait for the reviewer's batch of visual markup on the running dev server, apply each mark, and report it as it lands. Use whenever a Tailr session is running or being started, whenever a batch of marks arrives, and whenever the user talks about marking up the app, the review URL, or handing you visual feedback from the browser.

getpaykit Skill

Implement usage-based billing with PayKit's check and report methods, gate features by entitlements, track and decrement usage, handle balance resets, and build metered billing flows. Use when users need to add usage limits, API rate limiting, or consumption-based billing with PayKit.

ghosttypes Bundle

Professional-grade Python development with Ruff (v0.14.10) - an extremely fast Python linter and formatter. Use when working with Python codebases for (1) linting and fixing code quality issues, (2) formatting Python code, (3) configuring Ruff settings, (4) understanding and resolving specific rule violations, (5) integrating Ruff into projects or editors, (6) migrating from other tools (Black, Flake8, isort, etc.), or (7) any Ruff-related development tasks. Includes complete documentation for 937+ lint rules, formatter settings, configuration options, and editor integrations.