Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
45,100 skills from 2,196 repositories · updated 13 hours ago
2,564 skills
- announce-draftUpdatedapache/magpieDraft the `[ANNOUNCE]` email and open (never merge) the site-bump PR for a promoted release of `<upstream>`. Never sends mail.ProductivityReview first★ 127↓ —
- connectECNU-ICALK/AutoSkillConnect Claude to any app. Send emails, create issues, post messages, update databases - take real actions across Gmail, Slack, GitHub, Notion, and 1000+ services.ProductivityNo warnings★ 606↓ —
- obsidian-doc-routerdengyie/awesome-skillsMANDATORY documentation router for the user's Obsidian vault and any ops/deploy/infra task, or ANY action involving reading, writing, creating, updating, or refactoring knowledge base notes in Obsidian. BEFORE answering ops questions from memory or grepping the vault, you MUST Read 00.MOC/AI-DOC-ROUTER.md and open only the canonical entry it names. WHENEVER writing/creating/modifying Obsidian docs or notes, you MUST strictly follow the Anti-Orphan Recording SOP (frontmatter, path, summary, and two-way link mounting to AI-DOC-ROUTER and MOC). Triggers when: user mentions ainovel, ai-novel, novel 部署/备份/生产, CPA, tebi, pxed, Bohrium, google-vps, novel.mangoq, ainovel.mangoq, 查文档, 查知识库, Obsidian, 运维文档, 部署手册, 备份仓, 记录文档, 写笔记, 记录到obsidian, 更新文档, 记到知识库, 新建笔记, 整理文档, supervisord, cloudflared token, /personal/pxed.ProductivityNo warnings★ 67↓ —
- baoyu-infographicECNU-ICALK/AutoSkillGenerates professional infographics with 21 layout types and 20 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", "可视化", or "高密度信息大图".ProductivityNo warnings★ 606↓ —
- woz-feedbackWithWoz/wozcode-pluginSend feedback or a bug report to the WOZCODE team. Bug reports are tagged for triage and auto-attach session context (session id, anonymous id, OS, arch, Node version).ProductivityNo warnings★ 209↓ —
- backlog-statsUpdatedapache/magpieRead-only maintainer dashboard for the open general-issue backlog of <issue-tracker>. Surfaces a health rating, prioritised recommendations, age and staleness breakdowns, area pressure ranking, and a triage-funnel summary. Output is HTML by default; markdown fallback available.ProductivityReview first★ 127↓ —
- optimize-skillUpdatedapache/magpieMake an existing framework skill leaner without changing its behavior. Diagnose context-cost smells, propose the applicable optimization passes, and validate before and after every approved change.ProductivityReview first★ 127↓ —
- import-memoryRazshy/WiggleImport a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data.ProductivityNo warnings★ 98↓ —
- evo-jax-computeOpenLAIR/OpenSkillImplements all five JAX computation tasks - row-wise mean reduction, element-wise squaring, logistic loss gradient via jax.grad, RNN forward pass via jax.lax.scan, and JIT-compiled 2-layer MLP forward pass.ProductivityNo warnings★ 97↓ —
- alterlab-workflow-orchestrationAlterLab-IEU/AlterLab-Academic-SkillsComposes existing AlterLab skills into multi-agent agentic workflows using current Claude Code orchestration primitives — subagents (including nested subagents), dynamic workflow scripts, agent teams, forks, and the Claude Agent SDK: parallel fan-out, sequential pipelines, judge panels, adversarial verification, and loop-until-clean review cycles. Maps each pattern onto real skills (alterlab-research-pipeline, alterlab-deep-research, alterlab-citation-verifier, alterlab-paper-reviewer, alterlab-peer-review) with copyable delegation prompts, agent-definition frontmatter, workflow-script skeletons, and SDK query() snippets. Use when the request mentions multi-agent, subagents, agent team, dynamic workflow, workflow script, parallel agents, orchestration, pipeline of skills, judge panel, adversarial verification, devil's advocate, loop until clean, chaining skills, or composing skills into a custom workflow. Part of the AlterLab Academic Skills suite.ProductivityReview first★ 78↓ —
- evo-sec13f-analyzerOpenLAIR/OpenSkillToolkit for parsing SEC Form 13F-HR quarterly TSV datasets. Loads COVERPAGE/INFOTABLE/SUMMARYPAGE with safe dtypes (CUSIPs as zero-padded strings, VALUE as numeric dollars), fuzzy-matches fund manager names with RapidFuzz, retrieves fund AUM, deduplicates equity holdings (filtering options), compares holdings across quarters, and ranks top holders of a given CUSIP. Use whenever working with /root/2025-qN 13F TSV files.ProductivityNo warnings★ 97↓ —
- sherpasimota/agent-skillsGuiding workflows by decomposing complex tasks (Epics) into Atomic Steps under 15 minutes each, with progress tracking and drift prevention. Use when complex decomposition is needed.ProductivityReview first★ 95↓ —
- using-agent-skillsnota-america/forgecat-agent-profilesDiscovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or workflow applies to the piece of work at hand. This is the meta-skill that governs how all other skills are discovered and invoked.ProductivityNo warnings★ 93↓ —
- hamkromahlusenii-ops/hamSet up and maintain Hierarchical Agent Memory (HAM) for Codex using scoped local memory files. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM savings", "HAM stats", "HAM dashboard", "HAM sandwich", "HAM insights", "HAM carbon", or "HAM audit".ProductivityNo warnings★ 70↓ —
- hamkromahlusenii-ops/hamSet up Hierarchical Agent Memory (HAM) — scoped CLAUDE.md files per directory that reduce token spend. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM savings", "HAM stats", "HAM dashboard", "HAM sandwich", "HAM insights", "HAM carbon", or "ham sync".ProductivityNo warnings★ 70↓ —
- import-projectgavishap/omnia-vaultAdopt an EXISTING project — codebases, recordings, documents, loose notes — into this Omnia Vault. Use when the user says "import my project", "bring in this repo", "build the vault from what we already have", or drops folders/files into the vault root and wants them wired into the knowledge system.ProductivityNo warnings★ 82↓ —
- pest-controller-suitlegioncodeinc/vibe-coding-toolsRoute Wasp Nest tasks to the right Drone, arm its Stinger, and enforce the Ship Gate. Use before multi-Drone work. Read README.md for the guide map.ProductivityNo warnings★ 94↓ —
- good-first-issue-authorUpdatedapache/magpieDraft one net-new *good first issue* on the configured `<upstream>` repo from one supplied gap or small maintainer-named task. Run suitability and readiness checks before showing the draft. File via `gh` only after explicit maintainer confirmation. Never curate or relabel the existing backlog.ProductivityReview first★ 127↓ —
- google-calendar-skillaisa-group/skill-injectManage Google Calendar - search, create, update events and answer calendar questions. Use when user wants to interact with their Google Calendar for scheduling and calendar operations.ProductivityNo warnings★ 100↓ —
- obsidian-organizerAgents365-ai/365-skillsFile notes into the right folder in the user's Obsidian vault and audit/reorganize its structure, via the `obsidian` CLI and the `00_Index/Folder_Map.md` map note. Use when a note needs filing, when the user asks where a note belongs, or wants to tidy, deduplicate, audit, or restructure folders. Requires the Obsidian app to be running.ProductivityNo warnings★ 92↓ —
- evo-jax-computing-basicsOpenLAIR/OpenSkillComplete utility for JAX numerical computation tasks - handles I/O (problem.json, .npy/.npz), and implements all five JAX computations (row-wise mean, element-wise square, logistic loss gradient, RNN scan, JIT MLP) with robust error handling and domain-aware edge case coverage.ProductivityNo warnings★ 97↓ —
- memory-managerGulajavaMinistudio/awesome-copilot-idStandardized workflow for discovering, reading, writing, and compacting the project's memory file (memory.instructions.md) to persist context across AI chat sessions, with a permanent Knowledge Base for cross-session decisions and lessons learned.ProductivityReview first★ 90↓ —Also in 1 other repo
- repo-context-ledgergviiisen/repo-context-ledgerRecord every behavior-changing feature addition, fix, and adjustment as durable, evidence-based repository knowledge, then use that ledger to continue accurately across AI windows, tools, Git collaboration, and pull requests. Use the deterministic runtime to route bounded context, isolate private drafts, publish verified change records, refresh stable feature knowledge, and keep native Codex, Claude, Cursor, Copilot, Grok, and other Agent entry points aligned without asking the user to run bookkeeping commands.ProductivityNo warnings★ 104↓ —
- vote-tallyUpdatedapache/magpieAfter the approval window closes, fetch the approval signal for an RC of `<upstream>`, classify each reply as +1 / 0 / -1 and binding or non-binding against the configured roster, produce the tally summary, and draft the `[RESULT] [VOTE]` email. Never sends mail and never applies a label without explicit RM confirmation.ProductivityReview first★ 127↓ —