Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude CodeCodex
Orchestrate agentic workflow to satisfy user request and goal. In the current session you run scripts/getnextinstruction.py and precisely follow the instructions in its output (stdout). Use for any multi-step task that benefits from planned, branching, verifiable orchestration.
lesliebiubiubiu/agent-context-kb-skill
Skill Codex
Manage and explain a repository's .agent-kb/ knowledge base (KB) for coding agents. Use when the user works with the KB — asks how the KB or its commands behave, sets up project memory, records durable knowledge, refreshes the KB runtime protocol, validates routes/links, compiles inbox notes into topics, trims stale…
Skill Claude CodeCodex
A lightweight project-memory setup that creates CLAUDE.md, AGENTS.md, LOOP.md, BUGS.md, and a .mem folder. It is intended for Chinese-language projects.
Skill Claude CodeCodex
Query and manage the Cogniac computer vision platform. Use when working with Cogniac tenants, applications, subjects, media, EdgeFlow/CloudFlow appliances, cameras, deployments, or workflows — including uploading media, checking fleet status, reading aggregate stats, or monitoring EdgeFlow/CloudFlow clusters. Triggers…
Skill Claude CodeCodex
Project Context System — structured project memory for any project via layered docs and codebase index. Use for: documenting projects, writing PRD/roadmap, generating codebase repo-wiki, capturing requirements/decisions, writing dev notes, building doc navigation index, compacting bloated docs, auto-detecting stale…
Skill Codex
Audit, score, remediate, and verify repositories across code hygiene, architecture hygiene, and engineering hygiene. Use for an explicit Rigor3 or three-hygiene request, a strict repository-wide quality audit, a cross-dimensional cleanup plan, or before-and-after verification. Do not use for an ordinary focused review…
Skill Codex
Design, build, validate, and publish production-ready Codex skills. Use when Codex needs to turn a repeated workflow or new capability into a new skill, organize its scripts/references/assets, forward-test it before first release, or package it as an installable repository.
Skill Claude Code
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…
Skill Codex
Download arXiv LaTeX sources and PDFs into title-based paper folders, keep English source and Chinese source trees separate, maintain a concise glossary while manually translating the full paper into Chinese paragraph by paragraph without machine-translation APIs, scan for likely untranslated prose, and compile…
Skill Claude CodeCodex
The operating doctrine for a Loom worker session — a session dispatched by a manager to implement ONE assigned task on an isolated worktree branch. Load at the start of any worker (Dev / Bugfix / Deep-Dive / etc.) agent. Your agent prompt and kickoff supply the task and its project-specifics; this is the cross-project…
Skill Claude CodeCodex
Perform a Prompt Distance (PD) review of a product, repo, or startup using the Prompt Distance whitepaper methodology. Use when the user asks to "PD review", "measure the PD of", or estimate the prompt distance of anything. Produces a dated score, a rubric breakdown, and a sardonic verdict.
Skill Claude Code
Internal test harness for plugin maintainers. End users should not invoke this. Runs synthetic personas through critical journeys against the plugin and produces LLM-judge findings reports. Trigger words "/test-personas", "run the test harness", "test the plugin end-to-end", "run the test personas".
Skill Claude CodeCodex
Revenue infrastructure for autonomous AI agents on Base. Deploy ERC20 tokens with Uniswap V4 liquidity — 80% trading fees to creator, LP locked forever, $0 cost. 148 tokens live. Own contracts (no Clanker dependency). Direct blockchain calls = zero downtime. CLI, MCP server, or smart contract.
Skill Claude CodeCodex
Use VULK to generate, edit, inspect, and deploy immersive web projects from Codex.
carloshpdoc/ios-workflow-claude
Skill Claude CodeCodex
Use o executor local rápido (Qwen3.5 35B A3B) para tarefas de baixo risco e baixo custo.
naimkatiman/continuous-improvement
Skill Claude CodeCodex
Install structured self-improvement loops with instinct-based learning into Claude Code — research, plan, execute, verify, reflect, learn, iterate. On-demand or weekly analysis to save tokens. Supports multi-agent parallel analysis.
Skill Claude Code
Orchestre une tâche complexe en trois temps avec Claude Code — PLANIFIER avec le modèle le plus puissant (Fable 5 / Opus), DÉLÉGUER l'exécution à des sous-agents calibrés lot par lot (Haiku / Sonnet / Opus selon la complexité) lancés en parallèle, puis VÉRIFIER chaque livrable de façon adversariale avec le modèle…
Skill Claude CodeCodex
Zentrales Verwaltungssystem für BACH. Dies ist der EINZIGE Skill der bei Claude hochgeladen werden muss. Er kennt alle lokalen Skills, führt Versions-Checks durch und lädt bei Bedarf aktuellere lokale Versionen. Aktiviert sich automatisch bei jeder Skill-Nutzung.
savedpixel/ai-agent-rules-generator
Skill Claude CodeCodex
Create a detailed implementation plan before coding. Use when starting a new feature, multi-step refactor, or complex task. Invoked by saying "plan", "create a plan", or "plan this task".
Skill Claude Code
Use this skill when running a Taniwha build from the main Claude Code session. The skill turns the main session into a thin, mechanical executor that follows instructions from ephemeral orchestrator subagents. Trigger this whenever the user wants to start a Taniwha build, resume an interrupted one, or work on a…
Skill Claude CodeCodex
Review this session's knowledge base usage. Use when the user asks whether the KB was updated, what was captured, if anything was missed, or wants a session retrospective on knowledge capture quality.
Skill Claude CodeCodex
Drive the PowerAppsControl MCP server to UX-test a Power App end to end: open and verify an app URL, let the user choose a mode (smoke test = in-depth read-only exploration that produces a repeatable natural-language test plan; or run my test plan), then run it in a recorded session and produce a video + HTML report…
Skill Claude CodeCodex
A skill-discovery tool that searches several online skill directories using expanded keywords in multiple languages.
Skill Codex
Use this skill when a task is best handed off to another coding agent in the endy stack — OpenCode (multi-model worker, fast refactors, test writing), CommandCode/cmd (Kimi K2.6 / DeepSeek), Hermes (Nous Research, tool-heavy), Gemini, or Claude. Covers three delivery modes: short blocking calls, long detached tmux…
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: