Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
executing-plans
SkillsUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
-
llm-wiki-pm
SkillsPM knowledge base skill for Claude Code. Karpathy's LLM Wiki pattern with supersession, privacy, crystallize, and qmd hybrid search.
git clone https://github.com/anh-chu/llm-wiki-pm.git -
ginno
SkillsLocal-first personal AI agent desktop app — Claude Code's shape with a visual workflow studio, local knowledge base, and zero cloud. Tauri + Next.js + Python.
git clone https://github.com/robscc/ginno.git -
Prompt-sensei
SkillsLocal-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analyzes local history with explicit consent.
git clone https://github.com/chengzhongwei/Prompt-sensei.git -
receiving-code-review
SkillsUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
-
using-git-worktrees
SkillsUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
-
gaia
SkillsA serious harness for Claude Code. Specs before code, gates on every commit, the Code Audit Team on every merge. Ships as a monorepo with a React frontend. Bring your backend.
git clone https://github.com/gaia-harness/gaia.git -
brainstorming
SkillsYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).
-
podcast-wiki
SkillsClaude Code plugin that turns the podcasts you listen to on Spotify into a cited LLM wiki: one page per topic, every claim linked to its episode.
git clone https://github.com/HagaiHen/podcast-wiki.git -
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
-
commune-wiki
SkillsA personal wiki engine for Astro with a link graph, a CLI that finds connections while you write, and agent skills that turn dictated dumps into maintained notes. MIT. It runs devon.md.
git clone https://github.com/dmthepm/commune-wiki.git -
loom
SkillsOrchestrate a fleet of real Claude Code agents on your Claude subscription, not per-token API bills - local-first.
git clone https://github.com/DanielC000/loom.git -
crux
SkillsA scientific-method lab notebook your AI agent drives — research as a tree of questions and falsifiable hypotheses in plain markdown, with an LLM literature wiki, a task manager, and a local browser GUI cockpit.
git clone https://github.com/mehdiforoozandeh/crux.git -
sanmu-skills
SkillsSanmu's Agent Skills collection. Academic PDFs, textbooks and slides to Markdown with LaTeX validation, high-resolution figures and Zotero workflows.
git clone https://github.com/luffysolution-svg/sanmu-skills.git -
superpowers-plus
SkillsSkills, hooks, and git-enforced quality gates for AI coding assistants. Extends obra/superpowers.
git clone https://github.com/bordenet/superpowers-plus.git -
swiftui-macos-skill
SkillsAgent skill for writing and reviewing SwiftUI code on macOS — runtime-level understanding of observation, concurrency, view identity, and platform integration
git clone https://github.com/kageroumado/swiftui-macos-skill.git -
aigent-os
SkillsClaude Code harness and alternative to context compaction: at 80% context it writes a verified capsule, runs /clear and resumes with persistent memory in git. Long-running and multi-agent Claude Code sessions, auto clear instead of auto-compact. MIT, local, Node 18+. Codex adapter.
git clone https://github.com/wrg32786/aigent-os.git -
model-citizen
SkillsThe control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and Codex with your own primitives: hook-enforced guardrails, usage telemetry, cost postures and model tiering, under any rules library or orchestration layer.
git clone https://github.com/JakeSelby/model-citizen.git -
second-brain-starter-kit
SkillsA second brain for Claude Code and Codex that keeps receipts, following Karpathy's LLM Wiki pattern: the agent keeps your markdown vault. Skills as a plugin marketplace, opt-in memory over MCP, vault templates, a CRM engine. MIT.
git clone https://github.com/tonydzi/second-brain-starter-kit.git -
culiops-skills
SkillsClaude Code skills for SRE, DevOps and FinOps on AWS and Kubernetes: incident RCA, Terraform/Helm pre-flight checks, safe IaC changes, AWS cost investigation, service discovery and runbooks. Read-only by default, every finding evidence-backed
git clone https://github.com/culiops/culiops-skills.git -
diagnosing-superpowers
SkillsUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
-
superpowers
SkillsJesse Vincent's Superpowers skills (brainstorm, plan, TDD, debug, verify, review) adapted for GitHub Copilot agent mode, with project-scoped installers. MIT, adapted from obra/superpowers.
git clone https://github.com/autovant/superpowers.git -
Agent Skill: App Store screenshot sets as one flowing panorama — light/dark, iPhone 6.9"/6.3" and iPhone Duo, 3D objects from the app's own context, pixel-exact UI
git clone https://github.com/zaferayan/store-screenshots-panorama-skill.git -
done-means-done
SkillsResumable completion protocol for coding agents: obligations live in a durable task record, completion is computed by a validator, and a Stop hook routes execution back to unfinished work.
git clone https://github.com/PyModel/done-means-done.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.