The catalog
608,253 rows, by stacks then stars
nakane1chome/claude-skills/skills/_template Skill
0★ repoWhat this skill does and when to use it. Claude uses this to decide when to load the skill automatically.
The same file is in 2 other repositories
rohitguta2432/agentgrade/skills/agentgrade Skill
0★ repoAudit any AI agent codebase for production readiness. Grades the repo against five pillars — evaluation, observability, data foundation, orchestration, governance — plus an incident playbook check, then reports the gaps ranked by risk with the exact artifact to build next. Use when the user says "audit my agent", "agentgrade", "is this agent production ready", "production readiness check", "agent gap analysis", or is about to deploy/launch an AI agent to real users.
zjy1020/claude-code-skills/skills/agent-skill-creator Skill
0★ repoCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
Clinical-Quality-Artifical-Intelligence/nhs-clinical-safety-skills/skills/crm-plan Skill
no license0★ repoClinical Risk Management Plan (CRMP) creator for health IT systems. Produces a structured CRMP aligned with NHS England DCB0129/DCB0160 and the NHS Digital CRMP template. Covers scope, safety roles, risk management activities, tools and methods, documentation requirements, and review schedule.
YussufSassi/ibexa-agent-skill/skills/ibexa-dxp Skill
0★ repoExpert-level Ibexa DXP (formerly eZ Platform / eZ Publish) development assistant. Use this skill for ANY task involving an Ibexa DXP codebase — content management, PHP API usage, data migrations, SiteAccess configuration, templating, search, commerce, PIM, permissions, custom field types, Page Builder blocks, events, workflows, and more. Trigger whenever the user mentions: ibexa, ibexa dxp, ibexa experience, ibexa commerce, ez platform, ezpublish, ContentService, LocationService, ibexa_string, ibexa_richtext, ibexa:migrations:migrate, siteaccess, content_view, ibexadesign, content type creation, ibexa repository, or any Ibexa-specific namespace (Ibexa\Contracts, Ibexa\Core, etc.). Even if they just say "I'm working on an Ibexa project", use this skill.
alexe-ev/product-plugins/ai-product/skills/assess-model-capabilities Skill
0★ repoEvaluate AI model capabilities, limitations, and trade-offs relevant to a product decision. Use this skill when a team needs to understand what an AI model can and cannot reliably do for their use case.
opahimmel/experience-database/xp-system/skills/xp-index Skill
0★ repoSets up the XP database (.xp/db.jsonl) and indexes the entire codebase in a fast first pass — one candidate entry per file, for immediately visible value. Use it with /xp-index, or when a repo has no .xp/db.jsonl yet, or when a fresh codebase needs to be fully onboarded into the XP system.
maskar/cc-plugins/sawkit/skills/diagram-expert Skill
0★ repoThis skill should be used when the user needs to create, generate, or visualize diagrams. It actively generates diagrams using the right tool for the right complexity level, following a tiered approach from simple ASCII to complex rendered images. Triggers on: drawing flowcharts, architecture diagrams, sequence diagrams, ER diagrams, state machines, mind maps, data charts, visualizing data, adding diagrams to READMEs, or any visual documentation. Also available as /sawkit:diagram-expert.
fennal/biblio-check Skill
0★Verify, correct, and reformat academic bibliographies. Use when the user asks to check, audit, validate, or verify citations or references in a paper, or asks whether a bibliography contains hallucinated, fabricated, or wrong sources. Also triggers on "check my references", "audit my works cited", "are these citations real", "fix the bibliography", "convert citations to APA/MLA/AMA/Chicago/Vancouver/IEEE/Harvard", "format my works cited", or any task that involves a .bib file, .ris file, or a references/works-cited section of a paper. Use this skill whenever the user mentions citations, references, bibliography, works cited, DOI lookup, or worries about hallucinated sources, even if they do not explicitly use the word "check". For papers that have no references and need them, use the suggest subcommand to find candidate sources, but never auto-insert citations without human review.
jonaskahn/agent-context/agent-context-plugin/skills/agent-context Skill
no license0★ repoGenerate evidence-driven context files (AGENTS.md, CLAUDE.md, GEMINI.md, docs/agents/, .claude/settings.json, cross-vendor configs) from Understand-Anything knowledge graphs. Use when the user runs /agent-context, asks to "bootstrap agent context", "generate AGENTS.md", "initialize Claude Code context", or "make this repo AI-agent-ready". Requires $PROJECT_ROOT/.understand-anything/knowledge-graph.json — produced by running /understand on the target repo first.
deokjinlog/intent-locked-workflow/skills/api-auto-testing Skill
0★ repoUse when /api-test is invoked after /executing-plans has implemented APIs. Drives the 6-step pipeline — API inventory from <slug>-implementation-plan.md and code → SQL guides for test data acquisition (user pastes results) → pytest scenario code generation (with conftest.py auth fixture auto-selected via detect_auth.py) → execution → result recording in <slug>-implementation-plan.md change-history → fail-handling proposal.
WoopSocial/woopsocial-social-media-skill Skill
0★Publish, schedule, and manage social media posts across Facebook, Instagram, LinkedIn, X/Twitter, Pinterest, TikTok, and YouTube through the WoopSocial MCP. Use this skill whenever the user wants to post to social media, schedule content, build a content calendar, manage social accounts, upload media for social posts, or automate multi-platform publishing. Also triggers when the user mentions WoopSocial, cross-posting, social scheduling, or wants to turn any content (blog posts, ideas, announcements) into social media posts. If the user asks to "post this", "share this on social", "schedule for next week", or anything involving publishing content to social platforms, use this skill.
cismontane-harris2642/signal-prospecting-kit/skills/outreach Skill
no license0★ repoTakes the prospect list and writes personalized cold emails and/or LinkedIn connection requests. Signal-driven, product-specific, in the user's voice. Asks channel preference (email, LinkedIn, or both) before drafting. Batch mode for multiple prospects, single mode for one. Triggers: /outreach, "write emails", "draft outreach", "write linkedin", "draft linkedin", "outreach email", "outreach linkedin", "outreach both". Reads: ./gtm/icp.md, ./gtm/voice.md, ./gtm/company.md, ./gtm/signals.md, ./gtm/prospects.md, ./gtm/learnings.md. Writes: updates prospects.md status, appends to learnings.md. Standalone: yes — works with just a name + company.
The same file is in 1 other repository
clever-cc-plugins/cc-concept/plugins/cc-concept/skills/cc-concept-audience Skill
0★ repoUse this skill to develop one or more audience personas or ICPs from scratch — interviewing the owner or synthesizing from pasted customer data (support tickets, sales call notes, survey results). Invoke when the user asks to "build a persona", "define our ICP", "who is our target audience", "develop buyer personas", or when another cc-concept skill reports that its "target audience" need is missing. Produces `context/audience-personas.md` for every other skill's existing audience gate to consume — this skill is the producer other skills already assumed existed.
simonstrumse/vibelabs-skills/skills/agent-browser Skill
0★ repoAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
evnchn-agentic/whiteboxing Skill
0★Use when iteratively POLISHING a skill toward "jade" over multiple passes — refining one that already exists (created by writing-skills or by hand), pass after pass, each driven by feedback or fresh review, converging it for eventual publish. Also when white-boxing a tacit in-the-head process into a shippable skill you expect to refine repeatedly. NOT for first-time creation from scratch — that's superpowers:writing-skills. Triggers: polish/refine this skill, another pass on it, make it jade, get it publish-ready, whitebox my process.
TheBitcoinBreakdown-95/update-claude-code/skills/update-claude-code Skill
0★ repoUse when updating Claude Code to a new version, when a brand-new model "isn't available in this environment" or doesn't appear in /model, or after an Anthropic release the user wants to pick up. Encodes the non-obvious fact that the VS Code extension runs its OWN bundled binary (separate from the PATH CLI and from any npm-global copy), so `claude update` alone does not change what a VS Code chat session runs — and that a full VS Code restart (not Reload Window) is required to activate a freshly-installed extension version. Diagnoses all install surfaces, updates each, and verifies.
yumih1129/skills-repo/skills/loop-engineering Skill
0★ repo当用户指定使用 Loop Engineering 方式推进任务,或在请求中明确出现 Loop Engineering、闭环工程、八步闭环、Loop Engineering 工程协作等关键词时立即触发。强制按闭环八步(理解目标、读取上下文、拆最小闭环、执行任务、验证结果、核对目标、修正偏差、交付结论)推进工程任务,覆盖编码、改文件、跨文件调试与任何需要交付物的工作流。同时锁定行为红线(先读后做、最小闭环、风险即暂停、复用既有、失败必回环)与按风险等级选择验证手段的纪律,并在交付时强制输出完成内容、关键路径、验证结果、未验证项四段式报告。
azadmotala/claude-code-team-builder/examples/saas-dashboard/.claude/skills/dashboard Skill
0★ repoGenerate the visual dashboard for TenantFlow. Copies the fixed dashboard template to the workspace. The dashboard reads tasks.json and progress.log from disk and auto-refreshes every 5 seconds.
telefrek/vallorcine/.claude/skills/script-dev Skill
0★ repoTDD pipeline for vallorcine scripts (bash/python/node)
bokuwalily/claude-code-skills/skills/agents-tools-quoted-json Skill
0★ repo~/.claude/agents/ の各 agent frontmatter `tools:` フィールドが bare-bracket (`[Read, Edit]`) や `allowed-tools:` 旧式で不統一なとき、quoted JSON 配列形式に一括正規化したいとき。
sushil930/my-claude-skills/skills/prd-maker Skill
no license0★ repoGenerates a dynamic, professional Product Requirements Document (PRD) for any task, feature, product, or project described by the user. Use this skill whenever the user mentions "PRD", "product requirements", "write requirements for", "create a spec", "feature doc", "product doc", "requirement document", or asks to plan/document any feature, app, tool, or system. Also trigger when users say "I want to build X — help me plan it", even if they don't say PRD explicitly. Always use this skill before writing any structured product or feature document.
jhhuh/experiment-driven-skill-development/skills/blind-skill-assessment Skill
no license0★ repoUse when comparing two versions of agent output to determine which is better, or when evaluating whether a skill produces higher quality results than baseline
shibayamalicht/hubble-trademark-analysis Skill
0★J-PlatPat の商標CSVから、企業ポートフォリオのブランドイメージ空間分析 (8軸ルーブリックへのLLM採点・重心/分散・時系列ドリフト・ホワイトスペース)を行い、 APOLLO CAPCOM デザインのコンサル品質レポート(PDF)とビジュアルサマリーを生成する。 ユーザーが「商標CSV」「商標分析」「商標ポートフォリオ」「ブランドイメージ」 「イメージ空間」「競合の商標」「出願動向のイメージ面」「ネーミングの傾向」 「リブランディングの兆候」「ホワイトスペース」「J-PlatPatのデータを分析」などに 言及したら、スキル名を明示されなくても必ずこのスキルを参照すること。 区分件数の統計分析のみが目的の場合(TradeMark Evolution の領分)は対象外。
jorgenosberg/shakespeare/skills/expand Skill
0★ repoInflate a memory file (CLAUDE.md, AGENTS.md, notes, todo lists) from plain English into ornate Early Modern English prose, while keeping every code block, URL, path, command, identifier, heading, date, and table untouched. A human-readable backup is written to `<file>.original.md`. Trigger: /shakespeare-expand <filepath> or "expand memory file".
cskwork/claude-minimal-plugin/skills/agent-browser Skill
0★ repoBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
eruto-skills/marp Skill
0★Handle all Marp (Markdown) slide tasks: creating new decks, editing existing slides, theme creation, outline-to-slide conversion, and reading/summarizing. Trigger on: "create slides", "fix slide 3", "create a theme", "convert this outline to slides", "what is this slide about", "make a presentation", "build a deck", "write a script", "export to PDF", "edit slide", "review slides". For presentation structure planning and content strategy, use a presentation-planning skill as the entry point. For .pptx file operations, use a pptx skill.
elliotboney/adhd_project_overwhelm_skill/skills/overwhelmed Skill
0★ repoExternalize a project that has become a hairball into a visible map plus one concrete next action. Use when the user says they are "overwhelmed", "lost", "stuck", "drowning", "buried", "spinning", "don't know where to start", "can't see the shape", "too many pieces/things/tabs", "spending too many cycles", or asks to "map this project" / "zoom out" / "what's next". Sub-actions: map (default), next, park, resume.
y-a-v-a/stern-code-review Skill
no license0★Rigorous senior-level code review for production risk. Use when asked for a stern code review, PR review, diff review, or review of files focused on correctness, data safety, security, operational reliability, unnecessary abstraction, weak tests, maintainability, and operational failure modes. Do not use for brainstorming, greenfield implementation, or purely stylistic feedback.
LOVAHE/JustDoIt/skills/just-do-it-agent Skill
no license0★ repoAutonomous execution protocol for general AI agents. Use when the user explicitly invokes JustDoIt Agent, asks for autonomous or end-to-end handling, asks for a standard work loop, wants agent-readable entrypoints or handoff, or when the user has not named another skill and the task is complex enough to need multi-step investigation, functional-boundary clarification, action, review, verification, or future-agent operability through stable keys, commands, selectors, schemas, manifests, APIs, tests, runbooks, or JDI.md.
Layton2617/shield-scan Skill
0★AI-powered security scanner — detect vulnerabilities, leaked secrets, and dependency risks in any codebase
gauravs19/spring-boot-microservices-skill/spring-boot-microservices Skill
0★ repoDesign, scaffold, and review modern Java Spring Boot microservices. Use this skill for ANY Spring Boot, Spring Cloud, or Java backend work — building or reviewing REST APIs in Java, Spring Data JPA / Hibernate (including N+1 and @Transactional issues), Spring Security (OAuth2, JWT), Spring Cloud Gateway, Resilience4j circuit breakers and timeouts, Kafka consumers and the transactional outbox, Micrometer / Actuator / OpenTelemetry observability, Testcontainers tests, caching with Redis, containerizing a Java service, Kubernetes probes, or zero-downtime deploys and database migrations. Trigger it whenever the user says things like "design a service", "scaffold a Spring Boot project", "add a gateway / config server / tracing / circuit breaker", "review my Spring Boot code", "is this service production-ready", "fix this N+1 or slow endpoint", "secure this API with JWT", "split this monolith", or "upgrade Spring Boot 2 to 3" — even when they never say the word "microservice". Targets the current GA generation (Spring Boot 4.x on Spring Framework 7, Java 25 LTS) with Maven and Gradle. Do NOT use for non-Spring Java, Android, Kotlin-only, or pure frontend work.
arhuman/claude-plugins/plugins/10x/skills/10x-docker Skill
no license0★ repoDocker and docker-compose best practices. Use for any Docker task: Dockerfiles (multi-stage builds, alpine, non-root), docker compose services (Go API, frontend, MariaDB, Oracle), healthchecks, volumes, networks, and K8S-compatible configurations.
payals/cursor-prompt-queue/skill/prompt-queue Skill
0★ repoUse when user says "execute prompt queue", "resume prompt queue", "run the queue", "reset prompt queue", "reset queue prompt", or has a docs/prompt_queue.md file with sequential prompts to execute. Orchestrates multi-step prompt pipelines with dynamic variable passing between steps, fresh subagent per step, and cross-session resumability via state file.
madeinoz67/madeinoz-recordmanager-skill/.claude/skills/add-language Skill
no license0★ repoGuide for implementing a new language parser in Codanna. Use when adding language support, implementing parsers, or extending language capabilities. Covers the six-file architecture (mod.rs, definition.rs, parser.rs, behavior.rs, resolution.rs, audit.rs), trait implementation patterns, resolution scope design, and integration workflow. Triggers on requests to add language support, implement new parser, extend language capabilities, or create language implementation.
zeybek/apex/plugins/apex/skills/apex-design Skill
0★ repoUse this skill when turning a software change or new initiative into an implementable, reviewable plan before building — including a short or one-line request (such as a feature or page asked for in a single sentence) that should be scoped through clarifying questions first. Apply it to feature planning, architecture decisions, technical designs, API or schema evolution, data migrations, service boundaries, build-versus-buy choices, and reliability planning that need explicit requirements, alternatives, risks, contracts, and a sequenced task plan. It can be invoked directly or as a command, and it produces a persistent planning workspace that the implementation, review, and investigation workflows consume. Do not use it when a change is already decided and only needs implementation.
yisean/claude-spec-skills/spec-change Skill
no license0★ repo统管需求变更的回流:把对已有特性的任何改动按「先文档后代码」的铁律同步回 PRD → 原型 → 设计 → plan,复用原 NNN、续编 R/F 与 AE/AC、不重排。Use when 客户/内部对已上线或在研特性提出改动、原型评审后要变更需求、开发中发现需求漏洞要回流。全新特性请改用 /spec-prd。
specdd/plugin-claude/skills/specdd-adopt Skill
0★ repoUse when Claude Code needs to add SpecDD to a project or update SpecDD framework files through the CLI before normal SpecDD work begins.
opendatadiscovery/odd-team/.claude/skills/align Skill
0★ repoCompute the cross-corpus ALIGNMENT scorecard — a deterministic, no-LLM roll-up that scores how well the ontology bridges CODE ↔ DOC ↔ ADR ↔ TEST bi-directionally, surfaces the Test-Traceability Ledger (no orphan tests; every test gates an ontology relationship), and emits a Contract-Test Readiness verdict + ranked actionable items + a trend series. Run it as a periodic heartbeat to see what blocks moving forward to contract tests. Writes lineage/{repo}/alignment-scorecard.{md,yaml}.
srinivas-dev-stack/pull-context-skill Skill
no license0★Pull the context of another Claude Code session into the current one. Lists recent sessions (by topic hint), lets the user pick one, distills that session's transcript in a subagent, and injects the digest here. Use when the user says "pull context from", "bring in the other session", "import that session about X", or wants to merge work from a parallel session.
otar/clarify-skill/skills/clarify Skill
0★ repoInterrogate the request with structured clarifying questions (via the AskUserQuestion tool) in rounds until the task is unambiguous, before producing any code, research, or other output. Leans toward asking. Manually invoked only via slash command. Useful when the cost of getting the work wrong is higher than the cost of a few extra messages. Applies to coding, research, design, writing, refactoring, and analysis.
Saturate/skills/azure-init Skill
no license0★ repoInitialize local dev environment from Azure DevOps by cloning all project repositories. Use when user asks to "initialize Azure project", "clone Azure repos", "setup Azure project locally", or wants to download all repositories from an Azure DevOps project.
deltafly/doom-cheats-for-claude-code/plugins/doom-cheats/skills/idbehold Skill
0★ repoIDBEHOLD — "power-up menu." The central menu of the DOOM pack: it lists all the Doom-themed cheat skills and what each does, like the in-game power-up selector. Pure reference/menu, it does no work. Use when the user types /idbehold, or asks "what cheats do I have", "show the doom pack", "list the doom skills", "what can the cheats do", "doom menu", or in Hungarian "milyen cheatek vannak", "mutasd a doom packot", "mik a doom skillek" — and when the user doesn't know which Doom mode to call for a situation.
realraelrr/knot-skills/skills/office-docx Skill
0★ repoCreate, edit, fill, validate, or format native Word DOCX files. Use only when the requested input or final deliverable is a .docx/.doc Word file, or when the user explicitly asks for Word document formatting, placeholders, template application, tracked changes, comments, headers, footers, tables, or DOCX validation. Do not use for plain text drafting, general reports, Markdown, PDF, or knowledge extraction unless DOCX output is explicitly required.
burythehammer/claude-code-plugins/plugins/claude-md-slim/skills/claude-md-slim Skill
0★ repoAudit and slim down bloated CLAUDE.md files — and other overlong project markdown like READMEs — by applying progressive disclosure. Use whenever the user asks to audit, trim, shrink, slim, refactor, declutter, restructure, or optimise a CLAUDE.md (or AGENTS.md / project memory) file, says their CLAUDE.md or README is too long or bloated, mentions context bloat or token waste from project instructions, wants rules moved into .claude/rules/ or subdirectory CLAUDE.md files, wants long docs split into linked pages, or asks about @imports or progressive disclosure — even if they don't name the file explicitly (e.g. "my project instructions are getting out of hand").
gordon1210/agent-goodies/plugins/idea-workbench/skills/develop-idea Skill
0★ repoRoute an idea through the idea-workbench workflow by assessing its current maturity and recommending the single next skill. Use when a user has a vision, brief, options note, design doc, review, or implementation plan but is unsure what to do next, or asks for help taking an idea from concept toward implementation.
Honorboxx/crew/skills/crew-git Skill
0★ repoUse whenever committing, branching, or repairing git history. Enforces atomic commits, the staged-diff read-through, honest messages, and the safe-repair table (including the rotate-first rule for leaked secrets).
xonack/wp-php8-migration-claude-skill/skills/wp-php8-migration Skill
0★ repoPHP 8.x migration guide for WordPress — covers PHP 8.0 through 8.3 features, breaking changes, backward compatibility patterns, dynamic properties fixes, and step-by-step migration strategy for themes, plugins, and custom code.
eruto-skills/research-note Skill
0★Research any topic from the web, YouTube transcripts, PDFs, X/Twitter posts, or GitHub repos — then generate a footnoted Markdown note with a Mermaid mindmap. Trigger on: "research this", "look into", "summarize this video", "read this PDF", "summarize this tweet", "what is X", "I want to learn about". This skill is for external information gathering and note creation — not for personal journaling, recipe planning, or other specialized content types.
simplevaad-debug/superskills/skills/api-designer Skill
no license0★ repoUse when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling, versioning strategies, pagination patterns, error handling standards.
The same file is in 3 other repositories
uplift-technology-company-limited/uplift-plugins/plugins/uplift-repo-polish/skills/uplift-repo-polish Skill
0★ repoPolish a GitHub repository's presentation so it reads like a well-maintained project — README badges (static ones for private repos) + scannable structure, the About sidebar (description, topics, homepage), a LICENSE it always asks about first (OSS, or an explicit proprietary one for private/internal repos), GitHub Releases cut/backfilled from existing tags, and — with a small deploy-pipeline change — real GitHub Deployment records so the Deployments tab isn't empty. Use this WHENEVER the user wants to make a repo "look professional / more legit / เรียบร้อย", add shields/badges, fill in the About section or topics/tags, add a license, turn vX.Y.Z tags into Releases so the Releases sidebar shows up, make the Deployments tab reflect real deploys, or points at a nice reference repo and says "make mine look like that". Trigger on phrases like "ตกแต่ง repo", "แต่ง readme ให้สวย", "ใส่ badge", "set up the About section", "add topics", "add a license", "make a release", "wire deployments", "polish this repo", "ทำ repo ให้ดูดี" — works on private repos too — even if they don't name every element; infer the rest and fill gaps.
mitulgarg/agent-ninja/skills/ninja-advisor Skill
0★ repoInterprets Agent Ninja routing recommendations injected via hooks. When you see [Agent Ninja] context in the conversation, follow the model/pattern/thinking recommendations. Use when routing decisions appear in context, when deciding which model to use, or when considering subagents vs direct execution.
Oliviaiii/bopomofo-rescue Skill
0★Detect and recover text that was accidentally typed with the Taiwanese Bopomofo / Zhuyin (注音) keyboard while the input method (IME) was stuck in English/ASCII mode — what Taiwanese users call 注音亂碼 or 注音文 — producing meaningless-looking letter+digit sequences such as "su3cl3a8", "cl3", "g4", "2k7", "vu,4", or such garbled runs embedded in an otherwise normal request (e.g. "help me fix su3cl3a8", "看看這個 PR qk4ru.6", "幫我改 su3cl3a8xk7"). Use this skill whenever a user message contains short ASCII tokens that look like keyboard gibberish, do not form real English words, and cannot be understood normally — especially tokens with digits interspersed among letters (tone keys 3/4/6/7 or vowel keys 8/9/0), which are a strong sign of Mandarin phonetic keystrokes typed in the wrong input mode. Run scripts/decode_bopomofo.py to deterministically map the keystrokes back to 注音 symbols with a confidence score, then interpret the intended Traditional Chinese in context and continue the user's original request without making them retype. Do NOT trigger on genuine technical strings — code, file paths, URLs, git hashes, CLI flags, package names, version numbers — the script's exclusion rules and confidence tiers already filter these out. Especially valuable for Taiwanese developers who forget to switch input methods when prompting AI coding agents.
kennyolofsson23-netizen/claude-code-config/skills/accessibility Skill
no license0★ repoAudit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
The same file is in 2 other repositories
keiththompson/video-to-cooklang/skills/cooklang-formatting Skill
0★ repoFormat recipes using Cooklang markup syntax. Use when creating, editing, or converting recipes to Cooklang format. Covers ingredients, equipment, timers, metadata, and file organization.
taewanu/skills/skills/engineering/step-back-as-user Skill
0★ repoStep out of the current solution frame and re-enter from the user's side. Two modes, (1) **friction**: become the end user and walk a specific moment, noticing where they stall; (2) **reference**: anchored to a specific moment, surface how 2–3 well-known products solve it and the tradeoff each took. Use when the user asks to "think from the user's perspective", wants a fresh angle on a flow or screen, is reviewing for friction, is stuck on how to handle a UX moment ("how do others do this"), or whenever the current line of thinking has gotten too internal and risks losing sight of who it's for.
galangster/paper-to-code/skills/paper-to-code Skill
0★ repoConvert Paper designs into production-ready websites with animations. Use when the user wants to build a website from a Paper design, convert Paper frames to code, implement a landing page from Paper, or says "build this from Paper", "convert my Paper design", "paper to code". Reads designs via Paper MCP, generates React + Tailwind + Framer Motion code with responsive breakpoints and polished scroll animations.
sandalsoft/skill-selector/skill-selector Skill
no license0★ repoAnalyze an implementation plan (defaults to .flow/specs/), discover relevant skills from the ecosystem, install them, and rewrite the plan to leverage installed skills. Use when user has a build plan, flow-next epic spec, or feature request and wants to equip the agent with the best available skills before building. Triggers on 'select skills for', 'equip for plan', 'find skills for this plan', 'skill up', or when reviewing a plan file before implementation.
jimmynotjames/simple-recurring-budgets/.claude/skills/app-intents Skill
no license0★ repoImplement App Intents for Siri, Shortcuts, Spotlight, widgets, Control Center, and Apple Intelligence on iOS. Covers AppIntent actions, AppEntity and EntityQuery models, AppShortcutsProvider phrases, IndexedEntity Spotlight indexing, WidgetConfigurationIntent, SnippetIntent, and assistant schemas. Use when exposing app actions or entities to system surfaces.
hsnuhow/how-skills/plugins/media-tools/skills/compress-pdf Skill
no license0★ repoShrink a PDF so it's small enough to email or share, using Ghostscript to downsample and recompress the images inside it while keeping fonts and text intact. Use this whenever a PDF is too big to send — "compress this pdf", "my pdf is too large to email", "shrink this pdf under 25MB", "make this exported pdf smaller for the client", "this PDF won't attach to Gmail", or when a freshly exported/printed PDF needs to fit an attachment limit. Trigger whenever someone wants a PDF to be smaller or complains it's too big to send, even if they don't say the word "compress". For shrinking PowerPoint decks or images (not PDFs), use the compress-files skill instead.