context-graph
Use when storing decision traces, querying past precedents, or implementing learning loops. Load in COMPLETE state or when needing to learn from history. Covers semantic search with Voyage AI embeddings, ChromaDB for cross-platform vector storage, and pattern extraction from history.
determinism
Use when verifying outcomes with code instead of LLM judgment, versioning prompts with hashes, or ensuring reproducible agent behavior. Load for any critical verification. Scripts return boolean exit codes, not subjective assessments. Prompts use semantic versioning with SHA256 validation.
enforcement
Use when implementing hooks that BLOCK invalid actions, creating quality gates for state transitions, or enforcing tested:true verification. Load when designing enforcement mechanisms. Uses exit code 2 to block, JSON permissionDecision:deny, or updatedInput modification. Rules are instructions; hooks are enforcement.
implementation
Implement the next pending feature from feature-list.json. Lean loop: pick feature, implement with tests, verify all checks pass, commit, mark done. Use when features are pending and you're ready to build. Also use when user says 'build next feature', 'implement', 'start coding', 'what's next', or after /init-project has created the feature list.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
mcp-setup
Use when setting up MCP servers for the first time or verifying MCP configuration. Runtime-aware: writes Claude .mcp.json or Codex .codex/config.toml, referencing central mcp-servers only (no per-project cloning).
scroll-storyteller
Use when creating interactive scroll-based storytelling experiences with mouse-following spotlight effects, animated SVG art, and the Anthropic design language. Load for explainer pages, product showcases, visual narratives, or any content needing immersive scroll storytelling with organic shapes and smooth animations. Supports GSAP-powered or lightweight CSS-only animations.
token-efficient
Use when processing 50+ items, analyzing CSV/log files, executing code in sandbox, or searching for tools. Load for data processing tasks. Achieves 98%+ token savings via in-sandbox execution, progressive disclosure, and pagination. Supports heredocs for multi-line bash.
tufte-slide-design
This skill applies Edward Tufte's data visualization principles from "The Visual Display of Quantitative Information" to create high-impact slides. Use when designing presentations, creating charts/graphs, reviewing slides for clarity, or transforming data into visual displays. Triggers on phrases like "make a slide", "create presentation", "design chart", "visualize data", "review my slides", or "make this more impactful".
mcp-setup
Use when setting up MCP servers for the first time or verifying MCP configuration. Ensures token-efficient and context-graph MCP servers are properly installed and configured with API keys.
applying-brand-guidelines
This skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messaging
async-programming-skill
This skill provides async/await patterns and best practices for concurrent programming
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
browser-testing
Use when testing web applications, debugging browser console errors, automating form interactions, or verifying UI implementations. Load for localhost testing, authenticated app testing (Gmail, Notion), or recording demo GIFs. Requires Chrome extension 1.0.36+, Claude Code 2.0.73+, paid plan.
claude-md-creator
Use when creating CLAUDE.md files, updating existing CLAUDE.md, validating CLAUDE.md structure, or auto-fixing CLAUDE.md issues. Load for setting up project instructions, global guidelines, local overrides, or modular rules. Handles global (~/.claude/CLAUDE.md), project (.claude/CLAUDE.md), local (CLAUDE.local.md), and rules (.claude/rules/*.md) with smart project detection and template generation.
context-graph
Use when storing decision traces, querying past precedents, or implementing learning loops. Load in COMPLETE state or when needing to learn from history. Covers semantic search with Voyage AI embeddings, ChromaDB for cross-platform vector storage, and pattern extraction from history.
determinism
Use when verifying outcomes with code instead of LLM judgment, versioning prompts with hashes, or ensuring reproducible agent behavior. Load for any critical verification. Scripts return boolean exit codes, not subjective assessments. Prompts use semantic versioning with SHA256 validation.
duotone-identity
Use when designing app pages, typography, spacing, or any UI look and feel for the Identity Platform. Load for creating landing pages, chapter sections, SVG illustrations, or applying the duotone cream/charcoal design system. Keywords: design, ui, styling, theme, colors, layout
enforcement
Use when implementing hooks that BLOCK invalid actions, creating quality gates for state transitions, or enforcing tested:true verification. Load when designing enforcement mechanisms. Uses exit code 2 to block, JSON permissionDecision:deny, or updatedInput modification. Rules are instructions; hooks are enforcement.
full-stack-debugger
This skill should be used when debugging full-stack issues that span UI, backend, and database layers. It provides a systematic workflow to detect errors, analyze root causes, apply fixes iteratively, and verify solutions through automated server restarts and browser-based testing. Ideal for scenarios like failing schedulers, import errors, database issues, or API payload problems where issues originate in backend code but manifest in the UI.
global-hook-setup
Use when setting up global hooks for Claude Code enforcement. Load when ~/.claude/hooks/ is missing or incomplete, or when explicitly requested. Installs 7 project-agnostic hooks (state transitions, git hygiene, outcome tracking). Run once per machine.
implementation
Use when implementing features from feature-list.json, writing code following project patterns, or using MCP tools efficiently. Load in IMPLEMENT state. Covers coding patterns, test writing, health checks, and token-efficient MCP usage (defer_loading for 85% savings).
initialization
Use when starting a new session without feature-list.json, setting up project structure, or breaking down requirements into atomic features. Load in INIT state. Detects project type (Python/Node/Django/FastAPI), creates feature-list.json with priorities, initializes .claude/progress/ tracking.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
orchestrator
Use when managing agent state transitions (START/INIT/IMPLEMENT/TEST/COMPLETE), triggering context compression at 80% capacity, or handling session lifecycle. Load at session start, on state change, or when context exceeds threshold. Core skill for single-orchestrator architecture.
postgresql-skill
This skill provides PostgreSQL-specific patterns for database design, optimization, and transaction management
project-hook-setup
Use when setting up project-specific hooks for Claude Code enforcement. Load during INIT state when .claude/hooks/ is missing, or when creating new project. Installs 5 hooks that read from .claude/config/project.json (tests, health, dependencies).
scroll-storyteller
Use when creating interactive scroll-based storytelling experiences with mouse-following spotlight effects, animated SVG art, and the Anthropic design language. Load for explainer pages, product showcases, visual narratives, or any content needing immersive scroll storytelling with organic shapes and smooth animations. Supports GSAP-powered or lightweight CSS-only animations.
skill-creator
Use when creating a new skill, updating an existing skill, or learning skill best practices. Load for extending Claude's capabilities with specialized workflows, tool integrations, or domain expertise. Covers skill anatomy, progressive disclosure (98% token savings), and the critical description-as-trigger pattern.
terminal-ui-design
Use when creating CLI tools, terminal user interfaces (TUI), or any command-line applications. Load for terminal UI design, ASCII art, color schemes, box drawing characters, and polished terminal output. Also use for refactoring boring CLIs into distinctive experiences.
testing
Use when running tests to validate implementations, collecting test evidence, or debugging failures. Load in TEST state. Covers unit tests (pytest/jest), API tests (curl), browser tests (Claude-in-Chrome), database verification. All results are code-verified, not LLM-judged.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
token-efficient
Use when processing 50+ items, analyzing CSV/log files, executing code in sandbox, or searching for tools. Load for data processing tasks. Achieves 98%+ token savings via in-sandbox execution, progressive disclosure, and pagination. Supports heredocs for multi-line bash.
tufte-slide-design
This skill applies Edward Tufte's data visualization principles from "The Visual Display of Quantitative Information" to create high-impact slides. Use when designing presentations, creating charts/graphs, reviewing slides for clarity, or transforming data into visual displays. Triggers on phrases like "make a slide", "create presentation", "design chart", "visualize data", "review my slides", or "make this more impactful".
two-agent-harness
This skill sets up a complete two-agent development system based on the "Effective Harnesses for Long-Running Agents" research. It creates initializer-agent (for project planning) and coding-agent (for incremental implementation), along with enforcement hooks and progress tracking infrastructure. Use when users ask to "set up two-agent system", "install agent harness", "configure Opus delegation", or want to implement the two-agent architecture pattern.
claude-glm-agent
Use when configuring apps to use z.ai GLM 4.7 proxy instead of standard Anthropic API. Works with any frontend (Next.js, Vite) or backend (Python, Node.js) framework.
accenture-slides
Create premium Accenture-branded PowerPoint presentations following Tufte data visualization principles and Dieter Rams design philosophy. Use when creating slides, presentations, or decks for Accenture corporate settings that require (1) Accenture brand identity (purple A100FF chevron logo clean layouts) (2) Minimal data-focused design (Tufte less but better) (3) Executive-ready aesthetics for boardroom presentations client pitches or internal reports
add-to-global-trigger
Route proposed additions to the global Codex control plane by deciding whether a request belongs in `~/.codex/AGENTS.md`, a global workflow or reference doc under `~/.codex/docs`, `~/.codex/bin/workflow.py`, or an enforceable non-prose surface. Use when asked to "add this to global AGENTS", "promote this workflow to global", "add a new global trigger", or decide whether something should be a trigger, workflow, reference, hook, lint rule, or runtime guard.
agent-feedback-artifact
Add, remove, serve, test, and operate a server-backed in-page agent feedback capability for HTML artifacts, static pages, or local app builds. Use when the user wants Browser-style annotation inside the artifact/app itself, marker-local chat, comment-triggered agent work, queued marker processing, deterministic install/remove scripts, preflight/closeout checks, browser acceptance evidence, or progressive-disclosure access to marker context.
agentharness-audit
Audits any agent harness codebase against 13 meta-principles of quality, scores each 0 to 10 with code citations, generates a self-contained HTML report for operators, and writes an agent-readable AGENTS.md improvement directive with file-level architecture recommendations to reach 9.5 or better. Use when the user wants to audit or rate an agent harness, evaluate harness quality, score an agent framework, get a roadmap for improving a harness, run agentharness-audit, audit this harness, rate Hermes, audit Codex, or audit a Claude Code harness. Not for individual skill audits or general code review.
aspnet-core
Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.
atlas-computer-use
Use when controlling ChatGPT Atlas through Codex Computer Use, especially browser tasks where context efficiency matters: fewer screenshots, fewer UI snapshots, fewer clicks, and cleaner browser state.
audit
Audit project against golden principles, produce scorecard. Use for /audit, "check project quality". NOT for system setup health (/harness-audit) or eval scoring (/eval-score).
autoresearch
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.
builder-design-system
Apply the Autonomous Agent Builder design system to the autonomous-agent-builder codebase. Use when building or restyling Builder dashboard pages, adding or auditing primitive components, generating theme presets, wiring status language, motion hooks, or validating a screen against the locked Builder design system.
chatgpt-apps
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.
chronicle
|
cli-creator
Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.
cli-for-agents
>-
cloudflare-deploy
Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.
Page 1 of 2 · 100 results