New This Week
Skills added or updated in the last 7 days
Showing 901–960 of 1,797 skills · Page 16 of 30
tinyhumansai / openhuman
42.3kThe fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
yamadashy / repomix
29.0k📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.
t8y2 / dbx
27.6k25 MB lightweight cross-platform database client for 100+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker.
triggerdotdev / trigger.dev
16.6kTrigger.dev – build and deploy durable AI agents and workflows
CursorTouch / Windows-MCP
10.1kMCP Server for Computer Use in Windows
xerrors / Yuxi
7.5k可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
decodingai-magazine / building-a-coding-agent-from-scratch-course
683Learn harness engineering by building Claude Code from scratch. Free, open-source course: 8 articles, 6 videos, 1 codebase.
agent-sh / agnix
457The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plugin for all major IDEs included, with autofixes.
KbWen / agentic-os
218Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.
jpicklyk / task-orchestrator
209Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce — the server blocks the call if they don't. Works with any MCP-compatible client.
samanhappy / mcphub
2.6kSelf-hosted MCP gateway and control plane for connecting, controlling, and operating MCP servers.
ollaya-dev / ollaya
1.4kJev-compatible API server for open decision models. Ollama for decision models: pull and serve 25 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/systemone. The TypeSafe SDK works unchanged: set its base URL and pick an open model.
jatechan / ai-data-extractor
526Free open-source extractor for AI coding assistant chat histories. Supports Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more
CherryHQ / gh-create-pr
52.7kCreate or update GitHub pull requests using the repository-required workflow and template compliance
CherryHQ / cherry-tool-guide
52.7kCherry Studio first-party tool and bundled-shell routing for general agents. For straightforward local work in shell-capable sessions, run JS/TS with `bun <file>` and one-off JS tools with `bun x`; run Python with `uv run [--with <pkg>] python` and one-off Python CLIs with `uvx`; search with `rg`.
JuliusBrussee / caveman
113.5kTerse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".
thedotmack / childhood
101.6kBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.
Leonxlnx / redesign-existing-projects
98.8kRetired: redesigns, restyles and design reviews are part of design-taste-frontend. Runs only when called by name.
heygen-com / captions-overlay
67.0kOverlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of the film, never a reserved bottom band you shift content up to avoid.
sickn33 / anti-ui-slop
47.9kStop coding agents from shipping generic UI. Extend the product's design system, use UIZZE evidence only when useful, cover required states, and inspect the rendered result.
sickn33 / app-builder
47.9kMain application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
wanshuiyin / arxiv
17.7kSearch, download, and summarize academic papers from arXiv
wanshuiyin / embodiment-description
17.7kWrite detailed embodiment descriptions for patent specifications
wanshuiyin / exa-search
17.7kAI-powered web search via Exa with content extraction
wanshuiyin / jurisdiction-format
17.7kCompile patent application into jurisdiction-specific filing format
wanshuiyin / paper-compile
17.7kCompile LaTeX paper to PDF, fix errors, and verify output
AgriciDaniel / canvas
15.7kCreate, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
AgriciDaniel / save
15.7kSave a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest.
AgriciDaniel / think
15.7kApply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or ambiguous reasoning and decisions. Use for think this through, deep think, architecture review, postmortem, tradeoff analysis, or challenges to assumptions.
AgriciDaniel / wiki-lint
15.7kRun a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit.
YaoApp / yao-agent
8.2kAgent management expert. ALWAYS invoke this skill when you need to list available agents, download or reference agent source code, deploy agent code to the host, or query the LLM connector matrix. Do not guess agent structures — use this skill first.
YaoApp / yao-workspace-config
8.2kWorkspace Git identity and credential management. ALWAYS invoke this skill when the user asks about configuring Git user info, adding HTTPS tokens, importing SSH keys, or managing workspace-level Git authentication.
Gentleman-Programming / gentle-ai-collab-perfect
7.9kTrigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage.
Devin-AXIS / ipollowork-video-component-authoring
7.1kDevelop or update reusable visual components for iPolloWork Video, including maps, charts, rankings, diagrams, openings and endings. Use for component authoring rules, manifests, editable variables, shared data forms, inherited design themes, AI editing slots and seekable HyperFrames timelines.
Devin-AXIS / daytona-cloud-server
7.1kDaytona cloud server, Den sandbox, desktop plus cloud e2e, marketplace server, worker proxy, cloud auth, org policies, connect Electron to Den. Use for server-side setup in validated flows.
Devin-AXIS / daytona-electron-den
7.1kElectron and Den, desktop plus cloud, two-sandbox e2e, cloud auth, marketplace, org policy, worker proxy, provider sync, desktop handoff. Validate Electron against a Daytona Den server with unified proof.
Devin-AXIS / run-evals
7.1kdo e2e tests, run e2e, validate feature, prove it works, PR proof, frame proof, pnpm evals. Launches iPolloWork on Daytona or local Electron and runs the coded eval flows via CDP. Launch + run mechanics; the proof loop itself is the fraimz skill.
Devin-AXIS / voiceover
7.1kwrite the voice-over, demo script first, voiceover instead of PRD, voiceover-first development, align on the demo, script the demo, ship a feature demo-first.
tech-leads-club / tactical-ddd
7.1kDetects anemic domain models, validates and refactors them into rich domain models, and enforces tactical DDD patterns (Entities, Value Objects, Aggregates, Domain Services, Domain Events)
tech-leads-club / learning-opportunities
7.1kFacilitates deliberate skill development during AI-assisted coding. Offers interactive learning exercises after architectural work (new files, schema changes, refactors)
tech-leads-club / seo
7.1kOptimize for search engine visibility and ranking
ThinkInAIXYZ / deepchat-cli
6.4kUse DeepChat's bundled CLI control plane for model inference, image/video/speech generation, transcription, OCR, artifact inspection, public configuration, Skills, and MCP operations.
alexgreensh / fleet-auditor
2.7kAudits token waste and cost across Claude Code, Codex, OpenClaw, Hermes and OpenCode, with dollar savings
davepoon / agentwhy-session-audit
3.7kChecks which private files (.env, keys, secrets) Claude Code and its subagents reached in this project, whether a value came into an agent's context, and which key to change, by running the open source agentwhy CLI over the session records Claude Code already keeps on disk
davepoon / freshservice-automation
3.7kAutomate Freshservice ITSM tasks via Rube MCP (Composio): create/update tickets, bulk operations, service requests, and outbound emails. Always search tools first for current schemas.
davepoon / hexanon-x402-apis
3.7kPay-per-call access to the Hexanon family of eight x402 APIs for autonomous agents — no signup, no API keys, USDC on Base.
davepoon / postmark-automation
3.7kAutomate Postmark email delivery tasks via Rube MCP (Composio): send templated emails, manage templates, monitor delivery stats and bounces. Always search tools first for current schemas.
openclaw / 1password
392.9kSet up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
openclaw / apple-notes
392.9kCreate, view, edit, delete, search, move, or export Apple Notes via the memo CLI on macOS.
openclaw / apple-reminders
392.9kList, add, edit, complete, or delete Apple Reminders and reminder lists via remindctl.
openclaw / blogwatcher
392.9kMonitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
openclaw / blucli
392.9kBluOS CLI (blu) for discovery, playback, grouping, and volume.
openclaw / camsnap
392.9kCapture frames or clips from RTSP/ONVIF cameras and local webcams, including USB pan/tilt/zoom control.
anthropics / claude-opus-4-5-migration
153.2kMigrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5
google-gemini / behavioral-evals
107.6kGuidance for creating, running, fixing, and promoting behavioral evaluations
google-gemini / docs-changelog
107.6kGenerates and formats changelog files for a new release based on provided version and raw changelog data.
google-gemini / tui-tester
107.6kExpert guidance for testing Gemini CLI behavior and visual output using terminal automation.
NousResearch / hermes-agent
256.6kThe agent that grows with you
JCodesMore / ai-website-cloner-template
37.2kClone any website with one command using AI coding agents
slopus / happy
24.3kOrchestrate Claude, Codex and Grok in one app. Open-source (MIT), reuses the subscriptions you already pay for.