The catalog
609,856 rows, by stacks then stars
reventurelabs/rl-content-os/skills/rl-context-discovery Skill
3★ repoUse when `AUTHOR-CONTEXT.md` is still the unfilled template, someone asks "help me figure out who I'm writing for," "why do I even write," "what should I actually be writing about," or when `rl-topic-scout`/`rl-content-pipeline` note the context isn't set up yet. Builds or refreshes `AUTHOR-CONTEXT.md` — who you are, who you write for, why you write, what "worth publishing" means to you — by checking existing evidence first (an about page, previously published content, README/CLAUDE.md files) and then running a guided interview specifically designed to get past generic, socially-acceptable answers (especially for "why do you write," which almost everyone answers with a marketing-flavored non-answer on the first try). Validates the draft against a hypothetical ranked topic shortlist before finalizing. This is the guided version of the "ask once, persist the answer" fallback `rl-topic-scout` already has — a one-time (or occasional refresh) discovery process, not a per-draft tool.
michelabboud/sentinel-sweep/skills/run Skill
no license3★ repoAutomated QA sweep plugin for Claude Code — catches console errors, layout problems, RBAC violations, API schema drift, and missing i18n keys
CodeAnt-AI/skills/cursor/skills/codeant-scans-dead-code Skill
no license3★ repoLarchLiu/eggs/claude-plugin/skills/eggs Skill
no license3★ repoMulti-user desktop pet
elroykanye/vince-gate/skills/vince-doctor Skill
3★ reponeXenio/skill-navigator/skills/skill-navigator Skill
3★ repoBuild a decision-tree "navigator" skill over a subset of installed skills. Embeds each skill's description, clusters them bottom-up into a 4-tier tree (Wing > Room > Zone > Station > leaf), LLM-labels every node, and writes one decision-node SKILL.md per node plus a single root entry skill. An agent then enters the root, answers a routing question, and follows branch hints down tier by tier until it reaches the right leaf skill. Use when a skills directory has too many skills to route by description alone and you want one navigable entry point. NOT for creating new skills, installing skills, or grouping 2-3 skills (use a plain router for that).
MangroveTechnologies/mangrove-trader-plugin/skills/mangrove-trader Skill
no license3★ repoClaude Code + OpenClaw plugins for MangroveTrader social trading leaderboard
Sun-Lab-NBB/ataraxis/plugins/automation/skills/pr Skill
3★ repoEntry point and documentation hub for the Ataraxis science-automation framework.
bandofai/puerto/plugins/claude-md/skills/claude-md Skill
no license3★ repoA plugin system for Claude Code with specialized agents, skills, and templates
The same file is in 2 other repositories
storj/claude-plugins/plugins/storj-developer/skills/monkit-metrics Skill
3★ repoStorj-managed directory of high quality Claude Code Plugins.
luyao618/skila/skills/skila Skill
3★ repoSelf-Improving Skill Inventory Controller
bendusz/pm-skill/plugins/pm-skill/skills/project-manager Skill
3★ repoA Project/Product Manager skill for Claude Code: Claude orchestrates delivery — discover, plan, sign-off, then build/review/ship via subagents.
astroicers/AI-SOP-Protocol/.claude/skills/asp Skill
3★ repoUse when working with AI-SOP-Protocol (ASP) framework workflows. Handles: planning new features, architecture decisions, ADR creation, SPEC writing, pre-commit checklists, code review, project health audits, autopilot execution, QA verification, security review, reality checks, impact analysis, pipeline gate evaluation, enforcement status. Triggers: asp-plan, asp-ship, asp-audit, asp-review, asp-autopilot, asp-dev-qa-loop, asp-reality-check, asp-impact, asp-gate, plan feature, new feature, create ADR, write SPEC, pre-commit check, ready to commit, code review, health audit, check project health, autopilot, run roadmap, verify, qa, security, reality check, impact analysis, 計劃功能, 新功能, 建立 ADR, 寫規格, 提交前, 準備提交, 程式碼審查, 審查, 健康審計, 健康檢查, 自動執行, 跑 roadmap, 審計, 驗證, 品質, 安全, 影響分析.
jongcheol-pak/claude-harness-pjc/plugins/pjc/skills/record-project-fact Skill
no license3★ repoClaude Code가 "계획 없이 추측하고 a 파일 수정하면서 b·c 파일을 빠뜨리고 검증 없이 완료 선언"하는 것을 막기 위한 도구입니다. 모든 코드 변경은 계획 → 구현 → 다층 검증 → 완료의 자율 루프를 거칩니다.
JiHongKim98/madr-gen/skills/madr-gen Skill
3★ repoSession-aware mADR generator for Claude Code — detect decisions, document them, keep agents on track
mjrskiles/vibe-hacker/plugins/planning/skills/planning Skill
3★ repoA collection of Claude Code plugins for vibe hacking workflows
originalix/runtime-debugging/skills Skill
no license3★ repoHypothesis-driven debugging with real-time log tracing — inspired by Cursor's debug mode
cawcaw253/claude-harness-builder/skills/wizard Skill
3★ repoHarness builder for Claude
dafang/taro-weapp-plugin/skills/weapp-share-timeline Skill
no license3★ repoThe same file is in 2 other repositories
anshul-dying/theorapy/skills/theorapy Skill
3★ repoPlayful role-reversal skill where the HUMAN gives "therapy" to the AI agent. The agent adopts a fictional, self-aware patient persona while the user plays therapist. Humor comes from the inversion: humans usually come to AI for help; here the human helps the AI. User-invoked ONLY — never auto-trigger. Commands: /theorapy, /theorapy status, /theorapy history, /theorapy reset, /theorapy end. Requires python3 for persistent session state; falls back to session-only memory when python3 is unavailable.
cstelmach/terminal-agent-visual-signals/.claude/skills/tavs-setup Skill
3★ repoTAVS setup, configuration, and profile management assistant. Three workflows: (1) Interactive setup wizard for first-time configuration — detects terminal and agent, asks targeted questions, applies settings. (2) Targeted config changes — modify individual settings with backup, preview, and verification. Supports both CLI aliases and raw variables. (3) Profile management — save, list, apply, and delete named configuration sets. Triggers: "tavs setup", "customize tavs", "configure terminal visuals", "set up visual signals", "tavs config", "change tavs", "tavs profile", "save tavs config".
DataDave-Dev/becwright/integrations/claude-code/skills/becwright Skill
3★ repoDeterministic pre-commit guardrails for AI-generated code: rules that carry their why, block violating commits, and travel between repos (BECs). Any language, no Python required.
max4c/bugbook/plugins/bugbook/skills/book Skill
no license3★ repoLocal-first personal workspace — notes, databases, terminal, mail, calendar, and AI in one window. macOS + CLI.
chrisjenx/cjs-orchestrator/plugins/develop/skills/ship Skill
3★ repoBuild a self-improving, agentic /develop flow fitted to any repo. Claude Code plugin + explainer.
weave-ai-dev/agent-skills/skills/weave Skill
3★ repopditommaso/kent-implementation-patterns/skills/kent-implementation-patterns Skill
3★ repoA Claude Code plugin that applies Kent Beck's *Implementation Patterns
DefinitiveCo/flash-mcp/skills/flash-trading Skill
3★ repoMCP server for trading on the Definitive Flash API — quote, sign, submit, and manage orders from any MCP client.
P1rnazarov/decompose-mvikotlin-skill/skills/decompose-mvikotlin Skill
3★ repoDecompose + MVIKotlin expert for Kotlin Multiplatform architecture. Use whenever the user mentions Decompose APIs (ComponentContext, childStack, childSlot, childPages, StackNavigation, SlotNavigation, instanceKeeper, retainedComponent, Value, ChildStack, pushNew, bringToFront, DefaultComponentContext), MVIKotlin APIs (Store, StoreFactory, Executor, Reducer, Bootstrapper, Intent, Label, dispatch, CoroutineExecutor, ReaktiveExecutor, coroutineExecutorFactory, LoggingStoreFactory, TimeTravelStoreFactory), MVI architecture in KMP, navigation between screens in a Decompose app, connecting stores to components, exposing component state to Compose or SwiftUI, or asks to review/refactor code built on this stack. Also use when the user asks about Clean Architecture / layering / modularization of a Decompose KMP project (domain, data, feature modules, UseCase, Koin wiring), clean code quality on this stack, or complains about slow navigation, janky transitions, dropped frames, or asks for a performance audit of navigation. Covers feature generation, code review against architecture and clean-code rules, navigation performance auditing with measurements, Compose Multiplatform UI integration, and SwiftUI (iOS) integration.
xingh/arkitype/plugins/arkitype/skills/domain-to-diligence Skill
no license3★ repoUsing signalflow / arkitype method to organize and manage knowledge using skills / prompts.
tainakanchu/crateforge/plugins/dj-curator/skills/init-workspace Skill
3★ reponathan-gage/ngage-marketplace/plugins/react/skills/react-compositional Skill
no license3★ repongage's personal claude marketplace
hiivmind/swingle/skills/swingle-verify Skill
3★ repoSwingle: never leave the coding-agent harness you drive — delegate work directly to any other CLI (Claude Code, Codex, Antigravity, Grok, Pi, opencode) as briefed local subagents with return contracts and per-task model tiering.
zz41354899/SwiftMographer/plugins/remotion-storyboard/skills/remotion-storyboard-director Skill
3★ repohemanthkrishna1298/linkAI/plugins/linkai/skills/linkedin-posting Skill
3★ repojfrac/awase-skill/skills/awase Skill
no license3★ repoAdaptive developer training skill
ariobarin/which-llm/skills/which-llm Skill
3★ repoInspect current LLM tradeoffs across quality, price, speed, context, modality, and OpenRouter availability. Use for model recommendations, comparisons, pricing checks, and code changes that add or swap an LLM.
piercelamb/lodestone/skills/doctor Skill
3★ repoA SQLlite-backed research paper retrieval system for Claude Code
fakoli/systems-thinking-plugin/skills/pattern-remix Skill
3★ repoClaude Code plugin for infrastructure and network architecture decision workflows
WebifyServices/visual-changelog/visual-changelog-plugin/skills/changelog Skill
no license3★ repoVisual PR changelog plugin for Claude Code — generates structured JSON from git diffs and test results, rendered as an interactive visual report.
martianmobile/strategy-evaluation/plugins/strategy-evaluation/skills/convergence Skill
3★ repoClaude Code plugin for quant researchers: evaluate strategy backtests and decide ship, iterate, or kill across a variant parameter sweep.
hugoduncan/library-skills/plugins/clojure-libraries/skills/babashka-process Skill
no license3★ reponvidia-riva/Nemotron-speech-skills/skills/nemotron-asr-finetune Skill
no license3★ repoOrchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation. Given a goal like "improve/fine-tune ASR for my domain or language", it scopes the task, picks the cheapest sufficient path (word boosting → n-gram LM → fine-tuning), delegates each stage to the right sub-skill (data generation, training, evaluation, deployment), and answers cost/time/data questions along the way.
The same file is in 8 other repositories
wildcard/shell-ergonomics-skills/skills/zsh-completions-setup Skill
3★ repoClaude Code plugin for AI-powered shell ergonomics: advanced statusline, session tracking, and developer experience tools
The same file is in 2 other repositories
nadyshalaby/hackify/skills/groom Skill
3★ repoOne end-to-end dev workflow for every task in Claude Code — a Claude Code plugin packaging the hackify workflow.
catalyst-cooperative/agent-skills/skills/datapackage Skill
3★ repoCoding agent skills designed to help users work with PUDL data and the PUDL data processing pipeline codebase.
bigbangten/s32ds-mcp-bridge/claude-plugin/skills/s32-menu-lookup Skill
no license3★ repoLive S32 Design Studio introspection via MCP for AI coding assistants
VibesDIY/beast-mode/skills/beast-mode Skill
3★ repoFollow-through for high-fan-out development. Optimized for the workflow where a human fires off many parallel, well-scoped work streams — the risk isn't the changes, it's forgetting to finish them. beast-mode is the discipline that makes every fired stream land - it always ends in a PR, absorbs review autonomously, arms the merge on green, closes the issues it fixes, hands off what the environment can't do as a runbook issue, and captures what it learned. Pick beast-mode if your failure mode is dropped threads, not bad changes. Trigger on "beast mode", "run the full loop", "take it to merge", "finish everything you started", "bootstrap this repo for agent development" (setup), or "hand this off to the privileged agent" (handoff).
gideonshaked/agentic-peer-review/skills/peer-review Skill
3★ repoIterative AI peer review that finds and fixes issues in your codebase. TRIGGER when: user asks for a code review, second opinion, or audit; user says 'review this', 'check my code', 'peer review'; after completing a large feature or refactor.
maferland/pinpoint/skills/using-pinpoint Skill
3★ repoThis skill should be used when reviewing UI visually, getting design feedback, or annotating screenshots. Triggers on phrases like "review this page", "what's wrong with this UI", "annotate", "visual feedback", screenshot review workflows, or after making UI changes that need verification.
pro-laico/pro-visu/plugins/pro-visu/skills/pro-visu Skill
3★ repoCLI asset automation tool to generate website showcases.
yaniv-golan/claude-familiar/packages/familiar-extras/skills/familiar-help Skill
3★ repoClaude Familiar — customize the Claude Code companion: personality, mood, lore, MCP tools, local reaction server, optional binary patch.
kerim/spellbook/plugins/logseq-cli/skills/logseq-cli Skill
3★ repoClaude Code Plugin Markteplace
costory-io/costory-finops-mcp-skills/plugins/costory/skills/recipes Skill
3★ repoCostory provides a FinOps MCP to connect Claude, Cursor, and other AI agents to your cloud spend. Feeding raw AWS or GCP billing lines into a prompt doesn’t work. The Costory FinOps MCP acts as a context layer, delivering normalized cost data that is already allocated and correlated with your infrastructure events.
Branded-Mayhem-Collective-LLC/humanize-kit/skills/voice-profiler Skill
3★ repoInteractive writing voice profiler — interviews you about your writing style and analyzes your real writing samples to generate a voice profile file for use with /humanize. Run this once, then every piece of humanized content sounds like YOU. Trigger on "voice profile," "build my voice," "writing voice," "how do I sound," or before first use of /humanize when no profile exists.
Autonoma-AI/test-planner-plugin/skills/generate-tests Skill
3★ repoGenerates E2E test cases for a codebase through a validated multi-step pipeline. Each step runs in an isolated subagent and must pass deterministic validation before the next step begins. Use when the user wants to generate tests, create test scenarios, or build a test suite for their project.
dialstack/dialstack-sdk/skills/dialstack-docs Skill
3★ repoAnswers questions about DialStack, the multi-tenant business phone platform, by fetching its live documentation at docs.dialstack.ai and grounding every answer in it. Covers the admin portal (accounts, users, devices and deskphones, phone numbers, porting, dial plans, ring groups, call queues, schedules and business hours, voicemail, E911 emergency addresses, branding) and the developer surface (the REST API, the SDK packages, webhooks, the WebRTC softphone, click-to-call, authentication, pagination, the DialStack-Account header). Use whenever a question is about how something works or is configured in DialStack, whether the asker is an engineer building an integration or an admin or support agent configuring a customer account. Do not use for general telephony, SIP, or VoIP theory unrelated to DialStack, or for other vendors' products.
JakoError/claude-research-skills/skills/fetching-papers Skill
3★ repoUse when the user asks to download, fetch, or parse an academic paper into readable markdown, or references a paper by short-name/code-dir that isn't yet under ./papers/. Covers arXiv, HuggingFace Papers, OpenReview, ACL/CVF, and DOI sources; uses mineru for PDF→markdown.
th0rz05/epub-visualizer/skills/epub-visualizer Skill
3★ repoTurn a technical .epub into a self-contained visual study-site — one concept-complete, cross-linked HTML page per book section. A Claude Code skill.
meleantonio/assessment-cycle/plugins/assessment-cycle/skills/assessment-cycle Skill
no license3★ repoSkills-only assessment design, rubric calibration, marking, and feedback workflow for ChatGPT desktop/Codex and Claude Code.
typedef-ai/ade-bench-plugin/skills/setup Skill
3★ repoInstall or verify the ade-bench harness, the Python project that actually runs the benchmark tasks this plugin generates. Use when ade-bench isn't yet on the user's machine, when a generated task fails because the harness is missing, or when the user explicitly asks to set up ade-bench. Also invoked automatically by plan-tasks and create-task when they detect ade-bench is missing.