Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
tinybase
SkillsA reactive data store & sync engine.
git clone https://github.com/tinyplex/tinybase.git -
dsh-adult-tension
SkillsDeepSeek 自带破甲 18+ 互动叙事:活人感 NPC(自主决策/拒绝迎合)、211个世界与上万素材、开局随心定制、世界自行运转、零漂移存档。
git clone https://github.com/daha1216/dsh-adult-tension.git -
ego-lite
SkillsThe fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config.
git clone https://github.com/citrolabs/ego-lite.git -
Tri-state circuit breaker router managing LLM provider failure cascades, sliding error windows, and half-open probes
git clone https://github.com/Alpha-Park/genpark-tri-state-circuit-breaker-router-skill.git -
Continuous-Claude-v3
SkillsContext management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
git clone https://github.com/parcadei/Continuous-Claude-v3.git -
building-flutter-apps
SkillsFlutter clean architecture skill for AI agents. Riverpod 3.x codegen, Freezed 3.x sealed classes, and GoRouter patterns.
git clone https://github.com/sgaabdu4/building-flutter-apps.git -
OpenART
SkillsOpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.
git clone https://github.com/AI45Lab/OpenART.git -
admissions-ops
SkillsGraduate-application planning workspace for AI agents — the LLM does the judgement, deterministic validators keep it honest. Sourced program evaluations, evidence-grounded CVs and statement drafts, nothing final without human review.
git clone https://github.com/TianCZeng/admissions-ops.git -
better-github-skill
SkillsOptimized GitHub skill for coding agents: fewer tool calls, less context burned, lower cost, faster answers. One bounded call each for PR state, review threads, and CI failures.
git clone https://github.com/AVGVSTVS96/better-github-skill.git -
modulo
SkillsModulo lets agents running local models try modifying their own activations to change their inner state. Changes decay after a certain time and can be undone at any time.
git clone https://github.com/EigenformAI/modulo.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 -
finance-ai-skills
Skills한국 회계사 · 세무사용 Claude Code 스킬(오픈소스). 법인세 · 부가세 · 양도소득세 · 원천세 신고 검토, 현금흐름표 · 리스 · 결산, 외부감사 JET · DART DSD 푸팅. Claude Code skills for Korean accounting, tax and audit.
git clone https://github.com/hany202507/finance-ai-skills.git -
mavericks-os
SkillsOrchestrate Claude Code sub-agents across long-running, single- or multi-repo projects. Artifact-first state, task lifecycle, cross-repo dependencies and QA gates that survive every session - not buried in chat history.
git clone https://github.com/yahor-punko/mavericks-os.git -
dispatching-parallel-agents
SkillsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
-
OpenClaw GenPark Latent Intent Orchestrator - POMDP belief state estimator and disambiguation engine with Shannon entropy thresholding.
git clone https://github.com/alphaparkinc/openclaw-genpark-latent-intent-orchestrator.git -
veriflow-cc
SkillsVeriFlow-CC: A Claude Code-driven RTL design pipeline. Automates Chip-on-Chat from architecture to synthesis (iVerilog/Yosys) using a stateful, zero-dependency LLM orchestration skill. Features sub-agent nesting for code gen and behavioral-driven verification.
git clone https://github.com/bjwanneng/veriflow-cc.git -
Orient
SkillsA living map of what you're building: state, decisions, and the why for Claude Code, opencode, and Codex. Cheap enough that it never gets in the way.
git clone https://github.com/Chaitanya299/Orient.git -
aihappey-ai
SkillsStateless unified multi-provider AI runtime with OpenAI & Anthropic-compatible APIs, Vercel UI streaming, managed agents and Skills across 150k+ models.
git clone https://github.com/achappey/aihappey-ai.git -
context-summary
SkillsA Claude.ai Personal Skill that generates a structured, seven-block session handoff so you can continue work in a new conversation without losing context, rediscovering decisions, or re-explaining your project state.
git clone https://github.com/thebpandey/context-summary.git -
skills
SkillsAgent Skills for the Upbound Platform — Kubernetes control plane fleets, starting with Claude Code. So your agent gets fleet state right instead of confidently wrong.
git clone https://github.com/upbound/skills.git -
triage
SkillsMove issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
-
claw-consensus
SkillsRun AI agents across machines without state drift: consensus protocol (propose/counter/accept/commit), dual-rail message bus, ACK discipline, self-healing sync. Formerly claude-consensus. Free, MIT.
git clone https://github.com/tonydzi/claw-consensus.git -
ai-html-annotation
SkillsAgent Skill (html-prototype-build): generate, annotate, review & deliver native HTML prototypes for Claude Code, Cursor & Codex — real-DOM notes, AI-ready selectors, UI packs, multi-state screenshots.
git clone https://github.com/Lisuiwen/ai-html-annotation.git -
vibeweaver
SkillsA bounded, hard-gated graph-engineered state machine, written as a skill — runs on any agent harness, tuned best for opencode so far: full skill, mini variant, and A/B benchmark harness
git clone https://github.com/logandoo/vibeweaver.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.