The catalog
612,213 rows, by stacks then stars
sequenzia/agent-alchemy/claude/claude-tools/skills/claude-code-tasks Skill
43★ repoReference for Claude Code's 6 Task Management tools — TaskCreate, TaskGet, TaskList, TaskUpdate (structured tracking) and TaskOutput, TaskStop (background execution). Covers tool parameters, status lifecycle, completion rules, dependency management, and conventions
The same file is in 2 other repositories
cgallic/kai-cmo-harness/harness/skills/kai-abm Skill
no license43★ repoPlan and execute account-based marketing campaigns for enterprise targets — account selection, personalized outreach, multi-channel touch sequences, and deal acceleration. Use when "ABM", "account-based marketing", "enterprise marketing", "target accounts", "named accounts", "enterprise outreach", "key accounts", or any request to build personalized campaigns for specific companies.
brycewang-stanford/AER-Skills/skills/aer-consistency Skill
43★ repoUse when auditing a finished or near-finished AER, AER:Insights, or AEJ manuscript for internal consistency: headline numbers across abstract, introduction, results, and tables; sample sizes; log-point and percentage-point conversions; cross-references; and in-text-citation/bibliography matching. Apply after the body and exhibits exist, before aer-referee-sim and aer-submission.
The same file is in 3 other repositories
sup3x/claude-code-eco/skills/eco-max Skill
43★ repoMaximum-savings variant of /eco - the same frugality rules PLUS a low reasoning-effort override for the invoked task. Use for routine chores (rename, small fix, quick question, boilerplate) when the user wants absolute minimum token spend; prefer plain /eco for hard or high-stakes work. Works in any language.
PangenomeAI/academic-skills-food-nutrition/agri-deep-research Skill
43★ repoDeep research producing a fully written, source-validated literature review on an agricultural question, as a senior agricultural scientist of the relevant discipline: scope, design the method, discover and screen by journal ranking, validate every source, extract and verify evidence, synthesize, stress-test, then write and format the review through an editorial and integrity loop. Same 12-subagent machinery as food-deep-research, grounded in agriculture and multidisciplinary literature (Q1/Q2 preferred, Q4 avoided). Use standalone for an agricultural deep dive, or as the engine called by agri-research. Triggers: deep research agriculture, investigate this agronomy question, agricultural literature review, state of the evidence in soil science, deep dive crop research.
moeru-ai/alint/.agents/skills/pnpm Skill
43★ repoNode.js package manager with strict dependency resolution. Use when running pnpm specific commands, configuring workspaces, or managing dependencies with catalogs, patches, or overrides.
The same file is in 3 other repositories
hyyhf/agent-book-code/chapter06/.funharness/skills/karpathy-guidelines Skill
43★ repoBehavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
The same file is in 17 other repositories
joeseesun/qiaomu-model-cli Skill
43★Call local Grok CLI, Kimi Code CLI, and Claude Code CLI with the strongest current default models and native tools. Use this qiaomu skill workflow when the user wants to run Grok 4.5 for X/web search, image/video generation, research, or multi-tool agent work; run Kimi K3 (1M) for frontend UI/CSS/React/Vue work; run Claude Fable 5, Opus 4.8, or Sonnet 5 for coding/review/refactors; run independent multi-model comparisons concurrently with native stream progress, artifact verification, private logs, cancellation, and failed-job retry; choose between the three CLIs; or wrap non-interactive CLI invocations. Trigger on phrases like "用 grok cli", "用 kimi cli", "grok 搜 X", "kimi 写前端", "qiaomu-model-cli", "调用 grok4.5", "调用 k3 1m", "用 claude code", "用 fable 5", "opus 4.8 改代码", "分别调用三个模型", "多模型横评". Not for generic cloud API registry management (use qiaomu-llm) or OpenCLI site adapters.
LeonardNJU/code-humanizer Skill
43★Use when AI-written code needs structural cleanup or when implementing a change under a guard against AI coding slop — duplicated reimplementations of existing helpers, try-import fallbacks, broad exception swallowing, speculative abstraction layers, _v2 copies, dead "for future use" code, narrating comments — including requests to "deslop", "remove AI slop", "humanize code", review an AI-generated PR beyond tests passing, or prevent these patterns in the current change.
DevExpress/agent-skills/plugins/dx-blazor/skills/devexpress-blazor-ai-chat Skill
43★ repoDevExpress AI Skills for coding agents (.NET, JS/TS)
VLab-Software/easyeda_mcp/io.github.VLab-Software/easyeda-pro-mcp MCP server
43★ repoMCP server and EasyEDA Pro extension bridge for live project assistance.
Wuesteon/lean-memory/io.github.Wuesteon/lean-memory MCP server
43★ repoEmbedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.
bitrise-io/bitrise-mcp/io.github.bitrise-io/bitrise-mcp MCP server
43★ repoSet up & manage mobile CI/CD on Bitrise: build, test, distribute iOS, Android, Flutter, RN apps.
cafferychen777/ChatSpatial/io.github.cafferychen777/chatspatial MCP server
43★ repoNatural language-driven spatial transcriptomics analysis with 60+ methods via MCP
chrisgleissner/c64bridge/io.github.chrisgleissner/c64bridge MCP server
43★ repoMCP server for Commodore 64 Ultimate hardware and VICE emulator control.
mhajder/librenms-mcp/io.github.mhajder/librenms-mcp MCP server
43★ repoMCP server for LibreNMS network monitoring - query devices, ports, alerts, and manage infrastructure
jiahao-shao1/sjh-skills/skills/handoff Skill
43★ repoGenerate a structured handoff summary for the next session. Triggered when user says "handoff", "交接", or "写个交接".
juliusz-cwiakalski/agentic-delivery-os/.ados-claude/skills/pr Skill
43★ repoADOS Turn AI into a repeatable, auditable SDLC: ticket → spec → plan → PR → quality gates → release. Agents, templates, skills, scripts, and reference workflows.
LiorCohen/sdd/.claude/skills/agents-standards Skill
no license43★ repoSpec-driven development (SDD) plugin for Claude Code — a collection of specialized AI agents, phased implementation plans, and verified code generation for full-stack teams
paradigmshift-labs/platty/plugins/platty-design/skills/platty-design-system-setup Skill
no license43★ repolinxule/kimi-plugin-cc/plugins/kimi-codex/skills/kimi-replay Skill
43★ repoClaude Code plugin that delegates read-only review, adversarial review, free-form ask, and write-capable rescue work to the local Kimi CLI. Includes an opt-in stop-time review gate.
foyzulkarim/skills/dev-pipeline/skills/session-stats Skill
no license43★ repoPersonal Claude Code plugin marketplace
m3talux/superbrain/skills/superbrain-recall Skill
43★ repoSession memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.
codelably/harmony-claude-code/skills/strategic-compact Skill
43★ repo建议在逻辑间隔进行手动上下文压缩(Context Compaction),以便在任务阶段中保留上下文,而不是依赖随机的自动压缩。
ccq1/cn-financial-services-plugins/cn-equity-research/skills/morning-note Skill
no license43★ repo代理技能skills,一键研报撰写,docx,excel,ppt输出
yandex/implicits/.claude/skills/create-release Skill
no license43★ repoCut a new release of the Implicits library — draft categorized release notes from changes since the last tag, create a draft GitHub release, and trigger the Release workflow that tests, tags, and publishes. Use when asked to release implicits, cut/create a release, or via /create-release <version>.
honeydew-ai/honeydew-ai-coding-agents-plugins/skills/query-debugging Skill
43★ repoUse when the user wants to review or inspect past query executions in Honeydew — what ran, from which client (BI tools, SQL interface, MCP, deep analysis), the semantic definition or compiled SQL behind a run, who ran it and when — and to debug failures. Uses the list_query_history MCP tool. For running new queries or analysis use the query skill.
chopratejas/vitals/skills/scan Skill
43★ repoDeep codebase health analysis — identifies hotspots, reads the riskiest files, diagnoses root causes, and prescribes specific refactoring actions. Use when reviewing code quality, planning refactoring, or understanding technical debt.
NeuroAIHub/awesome_cognitive_and_neuroscience_skills/skills/act-r-model-builder Skill
43★ repoThe same file is in 1 other repository
GoogleCloudPlatform/db-context-enrichment/plugin/skills/context-engineering-bootstrap Skill
43★ repoA context engineering agent designed to generate, manage, and optimize structured context sets from your database schemas. It bridges the gap between Large Language Models (LLMs) and databases by compiling, evaluating, and maintaining the precise operational context needed for highly accurate natural language-to-SQL query generation.
az9713/addyosmani-agent-skills/skills/using-agent-skills Skill
43★ repoLocal clone of addyosmani/agent-skills with additional documentation
The same file is in 15 other repositories
itsmostafa/qi/skills/qi-cli Skill
43★ repoquery search engine cli for humans and ai agents
selvarajmurugesan90/ops-engineering-skills/plugins/ai-agent/skills/agent-architecture-design Skill
43★ repoOpen-source, cross-agent Agent Skills for DevOps, DevSecOps, Cloud, Kubernetes/platform engineering, CI/CD tooling, GitOps/Argo, policy, security scanning, SRE, standards/compliance, MLOps, AgentOps, and enterprise collaboration. Build once, use in Claude Code, GitHub Copilot, OpenAI Codex, Cursor and Gemini CLI.
firecrawl/last30flames/skills/last30flames Skill
43★ repoAgent skill that researches what's actually new about any topic in a recent time window - keyless, harness-agnostic.
nwp/suno-song-creator-plugin/skills/suno-song-creator/skills/review-song Skill
43★ repoThis skill should be used when the user asks to "review my Suno song", "check Suno prompt quality", "evaluate song lyrics", "review this prompt", "check for AI-slop", "validate my Suno prompt", or wants independent quality assessment of Suno prompts and lyrics. Launches the quality-reviewer sub-agent to evaluate material against professional production standards including AI-slop detection, cliché detection, poor quality lines, rhyme assessment, style-lyric consistency, gender-pronoun consistency, and general taste.
The same file is in 1 other repository
AugustusW/audio-tldr-skill/skills/audio-tldr Skill
43★ repoSummarize videos, audio files, and podcasts into key takeaways. Give it a YouTube/podcast URL or a local audio/video file — it transcribes locally (cached; repeat requests reuse the transcript) and distills the transcript into key points, summaries, or translations. Use when the user asks to summarize, get key points from, translate, or TL;DR any audio or video content.
OutSystems/outsystems-mcp/cursor/skills/outsystems Skill
43★ repoPlugins for the OutSystems remote MCP.
bstevescherer/heycounsel-community/skills/SKILL_TEMPLATE Skill
43★ repoOpen-source legal AI skills — built by attorneys, for attorneys.
wuchubuzai2018/expert-skills-hub/skills/toutiao-news-trends Skill
no license43★ repo一些个人制作整理的AgentSkills技能仓库包,最新gpt-image-2 skills现在可用,nanobananapro的skills、微信文章搜索skills、。微信公众号关注:无处不在的技术
The same file is in 5 other repositories
Mat-Wong/Business-Academic-Skill/skills/paper-reading-companion Skill
43★ repoUpdated skills for Business Phd academic research, mainly IS/OM/Marketing, based on 1,000+ UTD papers. 基于1000+商科顶刊打造,商科Phd专属科研skill!
LjyYano/skill-pack/skills/article-to-anki Skill
43★ repoClaude Code / Codex / OpenCode skill collection — video-to-note, article-to-note, and more
netresearch/file-search-skill/skills/file-search Skill
no license43★ repoClaude Code skill: Fast code and file search using ripgrep, ast-grep, fd, rga, tokei
umutbozdag/agent-skills-manager/skills/manage-skills Skill
43★ repoDiscover, list, create, edit, toggle, copy, move, and delete AI agent skills across 11 tools (Cursor, Claude, Agents, Windsurf, Copilot, Codex, Cline, Aider, Continue, Roo Code, Augment)
The same file is in 21 other repositories
serejaris/justdoit/skills/justdoit Skill
43★ repoStandalone Codex skill that turns vague tasks into an execution pack and asks before running
tyroneross/pyramid-principle/skills/pyramid-principle-core Skill
43★ repoBarbara Minto's Pyramid Principle as composable Claude Code skills — short-form, long-form, presentations, and audit
aaPanel/btpanel-skills/skills/btpanel_files Skill
43★ repoThe skill's code and runtime instructions match its stated purpose (BT-Panel monitoring) and do not request unrelated credentials or installation downloads, but you should review how it stores API tokens and confirm the unknown source before installing.
KBRmau/linkedin-resume-optimizer/skills/linkedin-resume-optimizer Skill
no license43★ repoSkill de otimização de LinkedIn e currículo, usável em Claude Code, Cursor e Codex
The same file is in 1 other repository
brettdavies/crawl4ai-skill Skill
no license42★Use when scraping JavaScript-heavy pages or SPAs, crawling multiple URLs concurrently, extracting structured data with reusable CSS/JSON schemas, or building automated web data pipelines. Wraps the Crawl4AI library (`crwl` CLI and Python SDK) with schema-generation patterns for LLM-free extraction. Triggers on crawl4ai, crwl, scrape JS-heavy site, scrape SPA, headless browser scrape, schema-based extraction, batch crawl, sitemap crawl, web data pipeline. SKIP when a static HTML page can be read with `defuddle` / `fetch-web` — those are faster cold-start and don't need a browser.
CK42BB/procedural-clouds-threejs Skill
42★Generate beautiful procedural clouds in Three.js using WebGPU raymarching with WebGL2 billboard/mesh fallbacks. Covers all 10 major cloud genera (cumulus, stratus, cirrus, cumulonimbus, stratocumulus, altocumulus, altostratus, nimbostratus, cirrostratus, cirrocumulus) with physically-inspired lighting including silver linings, god rays, sunset coloring, and Mie/Rayleigh scattering approximation. Provides volumetric raymarching, billboard impostor, and mesh-cluster rendering paths with animated drift, morphing, and dynamic formation/dissipation. Use when building skies, cloudscapes, weather systems, flight scenes, atmospheric backgrounds, or any scene requiring clouds. Triggers: "procedural clouds", "cloud rendering", "volumetric clouds", "skybox clouds", "cloudscape", "cumulus", "cirrus", "storm clouds", "cloud shader", "cloud billboard", "raymarched clouds", "cloud lighting", "god rays", "sky rendering".
skinnerlee1225/enterprise-prd-toolkit/skills/enterprise-prd-writer Skill
42★ repo企業 PRD Writer — 受監管 / 金流 / 風控 / 跨職能團隊等級的產品需求文件撰寫與強化工具, 用於產出可直接進入 Refinement、Engineering Design、Development、QA 與 UAT 的 「施工藍圖」等級文件。相對於輕量版 prd-writer,此版本額外涵蓋權限矩陣、NFR、 依賴管理、合規、Analytics/Observability、Rollout/Migration/Rollback 與 UAT/Release Readiness。 預設以 interactive-html-report 規格輸出互動式 HTML(含常駐目錄側欄、捲動高亮)。 ⚠️ 版本選擇(重要): 當使用者說「幫我寫 PRD」但未指明版本時,先問使用者要用「輕量版(prd-writer)」 還是「企業版(本 skill)」再開始。判斷提示:個人專案 / 單一功能 / 無合規需求 → 輕量版; 多團隊 / 金流 / 風控 / 合規 / 需上線維運全鏈路 → 企業版。使用者已明確指定版本時直接照做,不必再問。 當使用者提出以下需求時,應優先使用此 skill: - 幫我寫 PRD - 產品需求文件 - 寫 spec / feature spec - 功能規格 / 需求規格書 - write a PRD / product requirements - 產品設計文件 - 幫我整理這個功能的規格 - 把這個想法寫成文件 - 我要交一份產品文件給工程團隊 - 寫個規格讓工程師可以直接開工 - 補 AC / 驗收標準 - 補 Out of Scope - 補畫面狀態 - 補 Edge Cases - 補權限矩陣 - 補 NFR - 補 Rollout / Rollback - 強化既有 PRD 此 skill 的目標不是產出冗長文件,而是建立可執行、可測試、可追蹤、 可討論且邊界明確的產品規格,降低因需求模糊造成的返工與認知落差。 核心強制項目包含: - Acceptance Criteria - Edge Case Analysis - Screen / System States - In Scope / Out of Scope - Assumptions / Open Questions / Decisions - Dependencies - Roles & Permissions - Non-functional Requirements - Analytics / Observability - Rollout / Rollback - Complexity Assumption
lbiz-partners/hometax-doum/skills/hometax-tax-hub Skill
no license42★ repo한국 홈택스 세무 작업 통합 진입점. 부가세 신고, 종합소득세 신고, 전자세금계산서 발급, 신고 준비, 영수증·카드 분류 요청을 받아 적절한 하위 스킬로 라우팅. 세무 도와줘, 세금 신고, 홈택스, 부가세, 종소세, 세금계산서 발행, 영수증 정리, 신고 준비 등 포괄 요청 시 사용. 동료·일반 사업자 범용. 자동 제출·발급 금지.
LeadMagic/gtm-skills/skills/abm/abm-1-to-1 Skill
42★ repoExecute Strategic ABM (1-to-1) for 5-15 high-value accounts — custom microsites, executive engagement, direct mail, board-level connections, custom content. Triggers on: "1-to-1 ABM", "strategic ABM", "custom ABM", "key account marketing", "named account".
Pythoughts-labs/react-frontend-skills/skills/feature-arch Skill
42★ repoReact feature-based architecture guidelines for scalable applications (formerly feature-architecture). This skill should be used when writing, reviewing, or refactoring React code to ensure proper feature organization. Triggers on tasks involving project structure, feature organization, module boundaries, cross-feature imports, data fetching patterns, or component composition.
stjbrown/agent-knowledge/skills/kb-ingest Skill
42★ repoPortable Agent Skills for building and maintaining Open Knowledge Format project wikis in plain Markdown.
master5d/claude-design-skills/skills/baseline-ui Skill
no license42★ repoValidates animation durations, enforces typography scale, checks component accessibility, and prevents layout anti-patterns in Tailwind CSS projects. Use when building UI components, reviewing CSS utilities, styling React views, or enforcing design consistency.
The same file is in 2 other repositories
xiongQvQ/-b2b-lead-hunter-skill Skill
no license42★Use when researching foreign-trade B2B leads, buyer companies, distributors, importers, wholesalers, reachable decision makers, customs/import signals, and outreach-ready contacts from product, region, ICP, website, or document inputs. Use for evidence-backed lead hunting, qualification, exportable lead files, regional/language email templates, company-personalized email drafts, and controlled SMTP sending after approval.
Hanyuyuan6/remote-gpu-trainer Skill
42★Use when a user runs, debugs, verifies, or ships a DL experiment on a GPU they OWN or RENT (AutoDL, RunPod, vast.ai, Lambda, Paperspace, 恒源云/矩池云/Featurize/揽睿星舟, bare SSH, Slurm, K8s; single/multi-instance). Triggers (multilingual): 本地训练/local training, 远程 GPU 训练/租卡/GPU rental, spot 抢占/preemption, 断点续训/resumable, 防 SSH 断线/tmux 守护, 多实例 ablation, 关机/销毁/stop-vs-terminate billing, checkpoint 磁盘满, CUDA OOM/显存不足, loss NaN/spike/不收敛, overfit 单 batch, FSDP/DeepSpeed/torchrun, 多卡 hang, 训练太慢/GPU util 低, dataloader/数据增广 bug; 消融结果异常/ablation looks wrong, 复现/reproducibility, 数据泄漏/leakage/test-set tuning, mAP=0/全零指标, 输出恒定/model-ignores-input, train-good/val-collapse, 对比不公平/unfair baseline, 单 seed/no error bars, loss 太好/too-good-to-be-true, 跨文档对账/cross-doc drift; 交付产物/deliverable, 唯一真源/single source of truth, best ckpt 拉回, 结果可视化/论文图脚本, manifest/provenance, 一键复现/repro, EVIDENCE.json. NOT for multi-cloud price-shopping + auto spot-recovery (SkyPilot), BYOC dev environments (dstack), or zero-ops serverless inference (Modal).
longhang2004/vietnamese-humanizer/skills/grammar-checker-vi Skill
42★ repoKiểm tra chính tả, dấu câu, khoảng trắng, cấu trúc câu, tham chiếu đại từ và kết hợp từ trong văn bản tiếng Việt. Dùng khi người dùng yêu cầu soát lỗi hoặc proofread; không dùng để áp một phong cách, đổi nội dung, sửa code/URL/identifier, hay coi lựa chọn register và phương ngữ là lỗi ngữ pháp.
The same file is in 1 other repository
niuma996/nium-wiki/skills/nium-wiki Skill
42★ repoAnalyze source code and produce an enterprise-quality, domain-organized Wiki under `.nium-wiki/`. Trigger on: "generate wiki", "create docs", "update wiki", "rebuild wiki", or any documentation generation request. Capabilities: - Semantic code analysis — understands logic, not just structure - Auto-generated Mermaid diagrams (architecture, data flow, class, dependency) - Bidirectional cross-linking across all documents - SHA256-based change detection for incremental rebuilds - Every section traces back to source via relative path links - Multi-language output (zh/en/ja/ko/fr/de and more)
mfarzanansari/prompt-polish Skill
42★Rewrite a rough prompt into a polished, model-specific prompt grounded in the official Anthropic prompting guides. Use when the user invokes prompt-polish, types an invocation like "prompt-polish/FABLE 5/[prompt]" or "prompt-polish/OPUS 4.8/[prompt]", or asks to polish, improve, rewrite, optimize, or tune a prompt for a named model ("make this prompt better for Fable 5", "tune this for Opus"). Supports Claude Fable 5 and Claude Opus 4.8 (Opus 4.7 routes to 4.8 guidance). If no draft prompt is provided, ask for it rather than inventing one.