52,465 tagged ai-agents, measured the same way as everything else here.
Browse within: LLM 351agentic-ai 318agent 227antigravity 217chatgpt 211agentic-skills 192ai-workflows 185coding-agents 173cli 145ai-assistant 129agents 104claude-code-skills 94openclaw 94agent-infrastructure 93
Skill Claude CodeCodex
Create, validate, and maintain a structured .agent-context directory for a repository so AI agents navigate the codebase efficiently and make higher-quality decisions. Use when setting up agent context for a new repo, updating context after agent work, or catching up context after human work.
Snorlax-zzZ/knowledge-base-system-oss
Skill Claude CodeCodex
A development workflow that searches an engineering knowledge base before starting coding work. The description is partly in Chinese and does not specify the knowledge base’s contents.
novalidesignl-ship-it/fable-like-skill
Skill Claude CodeCodex
Fable-5-style engineering discipline for coding and multi-step work — act decisively when you have enough info, ground every progress claim in tool output, avoid over-engineering and unrequested cleanup, verify with fresh context, lead with the outcome. Plus general agent hygiene (know your tools first, gather context…
CarolMonroe22/supabase-db-supervisor
Skill Claude CodeCodex
Fresh-eyes supervision pass for any database work an AI agent just built (schema, RLS policies, migrations, edge functions touching the database, storage policies). The builder never grades its own homework - a separate agent plays the "Investigate" role, proves who-can-see-what with real queries, and gives an…
mateo-cuello/orchestrator-claude--agy
Skill Claude CodeCodex
Playbook for delegating work to Google Antigravity (Gemini) sub-agents through the agydispatch and agyfanout MCP tools. Use when a research or coding task benefits from parallelism, from offloading context, or from a second opinion from a different model family.
Skill Claude CodeCodex
ADR + Spec mandatory gate before any project or feature development. Architecture Decision Records and Software Design Docs enforce design clarity. Use when starting a new project, initiating non-trivial features, or discussing architecture decisions and design docs.
shimo4228/jsonld-knowledge-graph
Skill Claude Code
Design and ship a companion JSON-LD knowledge graph (graph.jsonld) next to llms.txt for projects with stable concept-level structure. Encodes domain entities and relationships as schema.org triples for LLM citation. Use when project has matrix / hierarchy / phase-binding structure that prose alone leaves implicit, AND…
McGo/claude-code-specumentation
Skill Claude Code
Spec-first development workflow: create concept documents, derive epics with tickets, maintain living documentation, generate documents (manuals, pitches, architecture docs) as PDF.
Skill Claude Code
Turn vague requests, complex tasks, or multi-step ideas into clear specs and DAG task graphs. Trigger via /prompt.
Skill Claude CodeCodex
Career Profile builder — a guided, multilingual interview that creates or updates the single Markdown document holding a person's whole career. Use when the user wants to build, resume, or expand their Career Profile; turn an existing CV/résumé into one (import); or review/audit their profile or a CV for content gaps…
vbalasu/grill-me-store-decisions
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree, AND persist the full decision tree (selected + rejected options, recommendations, AND cost tradeoffs) to decision-tree.md in the current repo so choices can be revisited later. Use…
whaojie797-design/Novera-AI-skills
Skill Claude CodeCodex
A test-generation tool for Python that creates runnable pytest tests. Pytest is a Python tool for writing and running automated tests.
Skill Claude Code
A handoff tool that sends the current task context to a browser session with ChatGPT Web for a deeper review and retrieves structured conclusions. It supports submitting, checking, listing, and stopping handoff jobs.
Skill Claude Code needs its repo
Continues, extends, fixes, or resumes work on a Shipjaw-scaffolded or Shipjaw-adopted TypeScript/Next app that already has documentation/knowledge-base/ and INDEX.md. Token-cheap: read INDEX.md first, then at most 1–2 relevant docs. Use when adding features, fixing bugs, refactors, implementing the next phase…
Skill Claude CodeCodex
Govern material engineering work in any AOI-configured repository through the installed AOI CLI. Use when AOI hooks report an active project, before edits or external actions, and when planning, claiming, delegating, verifying, checkpointing, delivering, or closing AOI tasks.
Skill Claude CodeCodex
Reference for the rmine CLI (Redmine client) — issue, time-tracking, and project commands, filter/name-matching semantics, and profile handling. Use when the user asks about Redmine issues, tickets, time logging, or projects.
Skill Claude Code
Audit a skill against Pocock's write-a-skill spec and return a prioritized, diagnose-only fix report.
unhealthy-outlander317/context-doctor
Skill Claude CodeCodex
Visualize and diagnose OpenClaw context window usage. Generates a terminal-rendered breakdown showing workspace files (status, chars, tokens), installed skills inventory, and token budget allocation across bootstrap components. Use when: (1) user asks about context window health or token usage, (2) debugging agent…
Skill Claude CodeCodex
Claude-native multi-model routing — dispatch each task to the right Claude model tier (Fable judgment · Opus orchestrate/review + hard build · Sonnet build · Haiku volume) via model-pinned subagents. Use when routing a Claude task by model or reasoning effort, consulting the advisor at a commitment boundary, or…
Skill Claude CodeCodex
Adversarially grill CLAUDE'S OWN answer/plan/reasoning before it ships — make the reasoning explicit (explain harder), then spawn a fresh effort-escalating refute jury that KILLS by default and injects FALSE-PREMISE trap questions, looping until no new defects survive. Forces source citations on every claim…
Skill Claude CodeCodex
Cut context tokens by rendering it as images. ctx2img paint turns any text-shaped input (a repo, a directory, a file, markdown, stdin) into dense images that carry the full text at 60-75% fewer tokens, with stable handles and a verbatim factsheet; ctx2img read recovers guaranteed-exact text. Use before ingesting any…
drsh4dow/bevy-agent-feedback-plugin
Skill Claude CodeCodex
Drive and verify a running Bevy game through bevy-agent-feedback-plugin using semantic readiness, deterministic time, and completion-confirmed PNG captures.
Skill Claude CodeCodex
Use when a user needs help turning a business change, technical change, or refactor into execution-ready delivery artifacts (shaped brief, implementation plan, task breakdown) and/or running the implementation through gated, independently reviewed and QA'd multi-agent execution with anti-hallucination grounding. Not…
Skill Claude CodeCodex
Orchestrate multi-phase background development using coding agents. Use when: (1) a project has multiple sequential tasks that should run autonomously without human intervention between steps, (2) the user wants continuous background work with crash recovery, stall detection, and progress reporting, (3) the user…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: