Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
open-steps
SkillsPlain-language agent skills for Claude Code, Codex, Cursor and Gemini CLI: honest session reports, straight verdicts, steps you can follow. MIT.
git clone https://github.com/kharmanskyi/open-steps.git -
rezero-subscribe-claude
Skills非官方的 Claude 订阅分步教程:从准备节点、住宅 IP 到注册和订阅,一步一页,按你的方案、设备和手机系统走对应路线;也可以装成 Agent Skill,让你的 AI Agent 带你走完。
git clone https://github.com/Finderlzy/rezero-subscribe-claude.git -
skill-router
SkillsSkill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90% routing accuracy, per-step model enforcement, 30%+ savings on multi-step chains.
git clone https://github.com/hussi9/skill-router.git -
SAMOSA
SkillsA step auditor for matrix algebra, stochastics and algebra. Checks every step of a derivation, exactly, over finite fields.
git clone https://github.com/Hussain004/SAMOSA.git -
skill-recorder
SkillsDesktop app that records your on-screen work session and uses the GitHub Copilot SDK to reconstruct it as an intent + ordered steps, then builds a reusable Skill or Automation for Microsoft Autopilots like Scout, Microsoft Copilot Cowork, or Copilot Studio.
git clone https://github.com/microsoft/skill-recorder.git -
Flowtrace
SkillsRun a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.
git clone https://github.com/AIScientists-Dev/Flowtrace.git -
context-docs
SkillsAgent skills for Codex and Claude Code that preserve project context, decisions and next steps across AI sessions in plain Markdown.
git clone https://github.com/jaredchu/context-docs.git -
ego-jev
Skillsego lite skill — each DOM step decided in ~0.4s, no LLM turn
git clone https://github.com/ZephyrDeng/ego-jev.git -
nWave
SkillsAI agents that guide you from idea to working code, with you in control at every step.
git clone https://github.com/nWave-ai/nWave.git -
founder-pipeline
SkillsA gated 25-step pipeline for validating and launching a business idea with Claude Code. Evidence over assumption, a fresh-context critic and a human signature at every step, three gates that can kill the idea. 23 skills, 4 subagents, 2 workflows, an approval hook, evals and CI. MIT.
git clone https://github.com/marian-kamenistak/founder-pipeline.git -
yantra
SkillsMake your AI show its work. Yantra turns a description, from you or your coding agent, into interactive step-by-step diagrams, answer pages and books: laid out automatically, validated, and easy to share. CLI, MCP server, playground and Python SDK.
git clone https://github.com/niyankhadka/yantra.git -
Traqu
Skills“Turns big plans into small daily wins. Bring your roadmap, find today’s next step, and build a rhythm that lasts.”
git clone https://github.com/Gurtejhundal/Traqu.git -
skillranker
SkillsRust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.
git clone https://github.com/Dicklesworthstone/skillranker.git -
wizard
SkillsGenerate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
-
jev-social
SkillsOpen-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only steps; socai CLI captures cited browser evidence.
git clone https://github.com/socai-io/jev-social.git -
claude-booping
SkillsA playbook framework for Claude Code and the sprint loop built on it — deterministic state machinery, model-driven steps, plain-markdown vault
git clone https://github.com/A/claude-booping.git -
claude-plan-skills
SkillsAgent skills for managing multi-step tasks as GitHub issues. Create, implement, update, and close execution plans that survive across sessions.
git clone https://github.com/gjoranv/claude-plan-skills.git -
writing-plans
SkillsUse when you have a spec or requirements for a multi-step task, before touching code
-
recall-loom
SkillsProject memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local project files.
git clone https://github.com/Frappucc1no/recall-loom.git -
claude-dd
SkillsPortable Claude Code profile — 8-step dev loop, CLAUDE.md pre-commit gate, zero-hallucination policy. Install once, carry it to any machine.
git clone https://github.com/kopp0510/claude-dd.git -
agentic-brownfield-coding
SkillsClaude Code scaffolding and first steps for complex brownfield projects
git clone https://github.com/ralfstrobel/agentic-brownfield-coding.git -
HealthClawGuardrails
SkillsOpen-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.
git clone https://github.com/aks129/HealthClawGuardrails.git -
justskill-design
SkillsDesign with your coding agent — A skill, not a product: no MCP server, no app to install, no account, no build step, no npm install.
git clone https://github.com/justskill-ai/justskill-design.git -
projectops
SkillsOne install: issue → branch → release PR → deploy, with agent skills that drive each step. npx projectops
git clone https://github.com/Cassiiopeia/projectops.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.