think
Extended thinking mode - deep reasoning for complex problems requiring careful analysis
ultrathink
Ultra-deep multi-perspective analysis for complex architectural and strategic decisions
mastering-langgraph
Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and production monitoring. Use when - (1) building agents that use tools and loop until task complete, (2) creating multi-step workflows with conditional branches, (3) adding persistence/memory across turns with checkpointers, (4) implementing human approval with interrupt(), (5) debugging via time-travel or LangSmith. Covers StateGraph, nodes, edges, add_conditional_edges, MessagesState, thread_id, Command objects, and ToolMessage handling. Examples include chatbots, calculator agents, and structured workflows.
bacchus
Multi-agent coordination for parallel development. Use when asked to parallelize work, coordinate multiple agents, or manage tasks across a codebase.
ship-review
Pre-ship deep review pass. Runs the ambitious structural quality review (thermo-nuclear, advisory) then bug review (code-review) on the settled diff, with a human checkpoint between. Use once before opening a PR. Invoke for "ship review", "deep review before PR", "review before shipping".
tighten
Per-iteration code-tightening pass optimized for an AI-maintained codebase. Strips slop (deslop), applies local simplifications (simplify), then invests context the next agent needs (contextualize). Use after a round of iteration to keep the working tree tight before continuing. Invoke for "tighten", "tighten this up", "clean pass".
leychile
Queries Chilean legislation from the Biblioteca del Congreso Nacional using SPARQL and Linked Data. Use when searching for Chilean laws, decrees, regulations, congressional information, or when user mentions specific Chilean legal codes.
mis-documentos
Manages client case database in mis_documentos/ directory. Use when starting new legal work, creating documents, or generating proposals to find similar cases and maintain consistent style.
vlex
Interacts with vLex legal APIs for document search, anonymization, citation extraction, and classification. Use when needing international legal documents, PII removal, or legal text analysis. Requires VLEX_API_KEY environment variable.
mastering-aws-cli
|
code-reviewer
Reviews code for style, bugs, and best practices. Use when asked to review or analyze code quality.
hello-world
A minimal test skill that demonstrates the basic skill structure
pi-extensions
>-
update-agent-tools
Update curated agent CLIs and binaries used by these dotfiles.
agents-md
>-
code-review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo''s documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
codebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
commit
Stage all changes, commit, then push.
domain-modeling
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
grill-with-docs
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
handoff
Compact the current conversation into a handoff document for another agent to pick up.
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
land-worktree
Land a git worktree — push, merge PR, sync main, teardown environment.
playwriter
Control the user own Chrome browser via Playwriter extension with Playwright code snippets in a stateful local js sandbox. Use this over other Playwright MCPs to automate the browser — it connects to the user's existing Chrome instead of launching a new one. Use this cli for navigating JS-heavy websites (Instagram, Twitter, cookie/login walls, lazy-loaded UIs) instead of webfetch/curl. ALWAYS load this skill before using any playwriter commands
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
quality-baseline
Establish a quality baseline with runner commands, pre-commit auto-fix, and GitHub Actions CI.
readme
Rewrite a repository README so a technical reader can see what is in it.
simplify
>-
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
unslop
Cut AI tells from any writing. Must always apply.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
creo-memories
【最優先】コンテクストを超える永続記憶。 2-layer architecture + 4-scene mental model + 4-cadence self-improvement loop で ecosystem を継続改善。 Context Engine が自動で context 提供。
auto-commit
Automatically commits changes using conventional commits format (feat:, fix:, docs:, chore:, refactor:, test:, style:). Use after completing bug fixes, feature implementations, or documentation updates. Triggered automatically via Stop hook.
documentation-standards
Markdown documentation standards for LLM-optimized architecture including section numbering rules for Pandoc PDF generation. Use when writing markdown documentation, creating skills, or authoring content that may be converted to PDF.
pandoc-pdf-generation
Generates professional PDFs from Markdown using Pandoc with XeLaTeX. Use when creating PDFs, needing section numbering, table of contents, bibliography, or custom LaTeX styling.
skill-architecture
Comprehensive guide for creating effective Claude Code skills with security best practices, CLI-specific features, and structural patterns. Use when creating skills, needing security guidance, understanding skill architecture, or learning best practices.
gurume-cli
Use the `gurume` CLI to search Japanese restaurants on Tabelog. Trigger this whenever the user wants to find, recommend, or research restaurants/eateries in Japan — by area (Tokyo, Osaka, Kyoto, 三重, etc.), by cuisine (ramen, sushi, yakiniku, izakaya...), or with a vague request like "where should I eat in Shibuya" or "any good unagi spots near Tokyo Station". Use this even when the user does not explicitly mention Tabelog or the `gurume` tool, as long as the intent is finding Japanese restaurants.
spacing-scale
Generates consistent spacing tokens using base values and ratios. Use when creating margin/padding systems, gap tokens, or layout spacing. Outputs CSS custom properties, Tailwind config, or JSON tokens.
type-scale
Generates typography scales using modular ratios with auto-calculated line heights. Use when setting up font-size tokens, heading hierarchy (h1-h6), or text sizing systems. Outputs CSS, Tailwind, or JSON.
dark-mode
Implements theme switching with semantic tokens and prefers-color-scheme detection. Use when adding dark mode, light/dark themes, color scheme toggles, or converting hardcoded colors to theme-aware tokens.
aria-patterns
Provides ARIA roles, states, and properties for interactive components. Use when building custom widgets, fixing screen reader issues, or implementing modals, tabs, accordions, menus, or dialogs accessibly.
color-contrast
Validates WCAG 2.1 contrast ratios and generates accessible color pairings. Use when checking accessibility compliance, fixing contrast issues, or selecting text/background combinations for AA or AAA levels.
focus-states
Generates accessible focus indicators meeting WCAG 2.4.7 and 2.4.11 requirements. Use when styling :focus-visible, keyboard navigation indicators, or fixing focus ring visibility issues.
component-docs
Generates component API documentation with props tables, usage examples, and guidelines. Use when documenting component libraries, creating API references, or building component documentation for designers and developers.
token-docs
Generates design token documentation with visual swatches and code examples. Use when documenting token values, creating token reference guides, or building searchable design system documentation.
angular
Builds token-driven Angular components with signals and standalone components. Use when creating Angular component libraries, integrating design tokens, or building design system components with new control flow syntax.
react
Builds token-driven React components with TypeScript and modern patterns. Use when creating React component libraries, integrating CSS custom properties, or building Next.js design system components with forwardRef and composition.
svelte
Builds token-driven Svelte 5 components with runes ($state, $props) and TypeScript. Use when creating Svelte component libraries, integrating design tokens, or building SvelteKit design system components.
Page 9 of 1705 · 85239 results