Skills de Claude Code · página 108

|

|

|

|

|

|

|

|

|

|

|

|

|

Active context curation to fight context rot. Curates what goes into limited context window from constantly evolving information universe. 39% improvement, 84% token reduction.

Systematic methodology for identifying, capturing, and documenting reusable patterns from implementations. Enables automatic learning and knowledge-core.md updates. Claude invokes this after successful implementations to preserve institutional knowledge.

Systematic approach for creating minimal-change, reversible implementation plans. Claude invokes this skill when transforming requirements/research into executable blueprints. Emphasizes simplicity, safety, and clear verification steps.

Systematic validation methodology for ResearchPacks and Implementation Plans. Provides scoring rubrics and quality gates to ensure outputs meet standards before proceeding to next phase. Prevents garbage-in-garbage-out scenarios.

Systematic approach for gathering authoritative, version-accurate documentation. Claude invokes this skill when research is needed before implementation. Ensures truth over speed while achieving both.

>-

>-

Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\"

Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: \"Why is X failing?\", \"Where does this error come from?\", \"Trace this bug\"

Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: \"How does X work?\", \"What calls this function?\", \"Show me the auth flow\"

Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: \"What GitNexus tools are available?\", \"How do I use GitNexus?\"

Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: \"Is it safe to change X?\", \"What depends on this?\", \"What will break?\"

Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: \"Rename this function\", \"Extract this into a module\", \"Refactor this class\", \"Move this to a separate file\"

Base procedures for all mission agents: startup, cleanup, and handoff. REQUIRED skill for all mission feature implementations.

Generate visual HTML blueprint pages and structured plan specs for maestro project features. Explores the codebase, produces a `.md` plan in maestro format (Context, Critical Files, Design Decisions, Phases with Tasks and acceptance criteria) saved to `.maestro/plans/`, plus a visual HTML presentation. Use when the user asks to blueprint a maestro feature, plan an implementation for this project, or says "blueprint X" while working in the maestro codebase. Also use proactively for non-trivial maestro changes that span multiple files or architectural concerns.

Enter conductor mode: plan, decompose, and dispatch -- sub-agents implement, not you. Use when user says 'you orchestrate', 'conduct this', 'delegate this', 'don't code yourself', 'break this into sub-agents', 'run this milestone without doing it yourself', or wants to stay in the driver seat while you manage agents. Works for formal mission/milestone execution and ad-hoc decomposition.

Define and register custom skills for use in Mission Control missions. Create skill definitions with frontmatter, procedures, and validation rules.

Plan and structure new missions. Brainstorm raw ideas into decomposed missions with milestones, features, agent types, constraints, and the exact `maestro handoff` command for the first external agent.

Run code scrutiny validation during mission checkpoints. Spawns review subagents, synthesizes results, and produces validation reports.

Run user testing validation during mission checkpoints. Determines testable assertions, sets up test environment, spawns flow validators, and synthesizes results.

Development workflow for maestroCLI itself. Encodes the hexagonal architecture pattern (port -> adapter -> use-case -> command -> MCP tool -> test) and project-specific conventions. Use when implementing new maestro features, adding CLI commands, extending the MCP server, creating new adapters, modifying ports, writing use-cases, or debugging maestro's own code. Also use when you need to understand how maestro's layers connect or where to put new code.

Create, update, or debug maestro built-in skills. Covers SKILL.md frontmatter, reference directory structure, step-file architecture, build-time embedding, naming conventions, alias management, and registry validation. Use when creating a new maestro built-in skill, modifying an existing SKILL.md, adding reference files, debugging skill loading failures, updating the skills registry, or working on the skills full port. Also use when frontmatter validation fails, skills don't appear in skill-list, or reference files fail to load.

Guide for working with maestroCLI's v2 architecture. Covers the context-to-memory rename, 4-state task model, plain file backend, pre-agent hooks, research phase, and memory promotion. Use when touching v2 code, encountering legacy patterns (e.g. 'context' instead of 'memory', old task states), adding new v2 features, or debugging v2 behavior. Also use when you see imports from adapters/fs/context, references to 'contextAdapter', or task states that don't match the 4-state model.

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).

>-

Strengthen a raw user prompt into an execution-ready instruction set for Amp, Claude Code, Codex, or another AI agent. Use when the user wants to improve an existing prompt, build a reusable prompting framework, wrap the current request with better structure, add clearer tool rules, or create a hook that upgrades prompts before execution.

Use for design or brainstorming in a Maestro repo before implementation starts. Map current behavior, decide one fork at a time, record decisions and notes, then hand the approved contract to maestro-feature.

Use for the Maestro feature lifecycle: author, accept, prepare, start, amend, ship, cancel, archive, and inspect a feature contract plus its child-task rollup.

Use after Maestro init/install or doctor warnings to tune a repository harness from verified repo evidence.

Use for the Maestro task loop: create, explore, accept, claim, update, complete, block, verify, terminal task verbs, and harness self-improvement tasks.

Use to prove a Maestro task or feature gate with recorded evidence, repair failed proof, and run adversarial verification for high-risk claims.

Use before feature accept to capture baseline.md: a short real-scenario behavior contract with stable bl-NNN ids for the later ship gate.

Use after implementation waves to replay affected baseline scenarios and record qa-slices.yaml evidence for every shipped behavioral bl-NNN.

Use for read-only Maestro repo audits that propose harness backlog improvements without implementing them.

Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries, reduced motion, or cognitive accessibility.

Agent orchestration patterns for agentic loops, multi-agent coordination, alternative frameworks, and multi-scenario workflows. Use when building autonomous agent loops, coordinating multiple agents, evaluating CrewAI/AutoGen/Swarm, or orchestrating complex multi-step scenarios.

AI-assisted UI generation patterns for json-render, v0.app, Google Stitch, Bolt Cloud, and Cursor workflows. Covers prompt engineering for component and full-stack app generation, review checklists for AI-generated code, design token injection, refactoring for design system conformance, and CI gates for quality assurance. Use when generating UI components with AI tools, rendering multi-surface MCP visual output, reviewing AI-generated code, or integrating AI output into design systems.

Queries local analytics across OrchestKit projects for agent usage, skill frequency, hook timing, team activity, session replay, cost estimation, and model delegation trends. Privacy-safe with hashed project IDs. Supports time-range filtering and comparative analysis. Use when reviewing performance, estimating costs, or understanding usage patterns.

Animation and motion design patterns using Motion library (formerly Framer Motion) and View Transitions API. Use when implementing component animations, page transitions, micro-interactions, gesture-driven UIs, or ensuring motion accessibility with prefers-reduced-motion.

API design patterns for REST/GraphQL framework design, versioning strategies, and RFC 9457 error handling. Use when designing API endpoints, choosing versioning schemes, implementing Problem Details errors, or building OpenAPI specifications.

Use this skill when documenting significant architectural decisions. Provides ADR templates following the Nygard format with sections for context, decision, consequences, and alternatives. Use when writing ADRs, recording decisions, or evaluating options.

Architecture validation and patterns for clean architecture, backend structure enforcement, project structure validation, test standards, and context-aware sizing. Use when designing system boundaries, enforcing layered architecture, validating project structure, defining test standards, or choosing the right architecture tier for project scope.

ASCII diagram patterns for architecture, workflows, file trees, and data visualizations. Use when creating terminal-rendered diagrams, box-drawing layouts, progress bars, swimlanes, or blast radius visualizations.

Assesses and rates quality 0-10 across multiple dimensions (correctness, maintainability, security, performance, testability, simplicity) with pros/cons analysis. Compares against project conventions and prior decisions from memory. Produces structured evaluation reports with actionable improvement suggestions. Use when evaluating code, designs, architectures, or comparing alternative approaches.

Async job processing patterns for background tasks, Celery workflows, task scheduling, retry strategies, and distributed task execution. Use when implementing background job processing, task queues, or scheduled task systems.

Single-pass codebase analysis leveraging Opus 4.8 1M context for comprehensive security scanning, architecture review, and dependency auditing. Loads entire codebases for cross-file pattern detection and generates structured audit reports with severity-ranked findings. Use when you need whole-project analysis before releases or security reviews.

Audits all OrchestKit skills for quality, completeness, and compliance with authoring standards. Use when checking skill health, before releases, or after bulk skill edits to surface SKILL.md files that are too long, have missing frontmatter, lack rules/references, or are unregistered in manifests.

Run isolated eval and grading calls using CC 2.1.81 --bare mode. Constructs claude -p --bare invocations for skill evaluation, trigger testing, and LLM grading without plugin/hook interference. Use when running eval pipelines, grading skill outputs, benchmarking prompt quality, or testing trigger accuracy in isolation.

Design exploration using parallel agents through a 7-phase process: topic analysis, memory context, divergent ideation (10+ ideas), feasibility filtering, evaluation with devil's advocate scoring (0-10 across 7 dimensions), synthesis of top approaches, and trade-off comparison. Supports open exploration, constrained design, comparison, quick ideation, and iterative optimization modes. Use when brainstorming ideas, exploring solutions, or comparing alternatives.

OrchestKit security wrapper for browser automation. Adds URL blocklisting, rate limiting, robots.txt enforcement, and ethical scraping guardrails on top of the upstream agent-browser skill. Use when automating browser workflows that need safety guardrails.

Business case analysis with ROI, NPV, IRR, payback period, and TCO calculations for investment decisions. Use when building financial justification, cost-benefit analysis, build-vs-buy comparisons, or sensitivity analysis.

Chain patterns for CC 2.1.71 pipelines — MCP detection, handoff files, checkpoint-resume, worktree agents, CronCreate monitoring. Use when building multi-phase pipeline skills. Loaded via skills: field by pipeline skills (fix-issue, implement, brainstorm, verify). Not user-invocable.

Rate-limit-resilient pipeline with checkpoint/resume for long multi-phase sessions. Saves progress to .claude/pipeline-state.json after each phase. Use when starting a complex multi-phase task that risks hitting rate limits, when resuming an interrupted session, or when orchestrating work spanning commits, GitHub issues, and large file changes.

Diagnose a failing CI run against a 10-pattern playbook. Classifies the failure, cites the relevant memory entry, proposes the exact fix command — but NEVER applies without explicit user approval. Use when a specific PR check or GitHub Actions run failed and you want a diagnosis instead of speculation. Don't use for org-wide CI sweeps (that's /status) or for app-level test failures (the playbook is CI-infra-specific).

Hourly autonomous classifier for failing PRs across your repos. Runs /ci-debug headless against every open PR with red required checks, posts the verdict as a collapsed PR comment, and appends to a per-repo .sentinel/ledger.jsonl. v1 is propose-don't-apply — NEVER auto-pushes a fix. Use when you're tired of /status sweeps catching the same 10 CI failure patterns over and over.

Use this skill when conducting or improving code reviews. Provides structured review processes, conventional comments patterns, language-specific checklists, and feedback templates. Use when reviewing PRs or standardizing review practices.

Creates commits with Conventional Commits format (feat/fix/docs/refactor/test/chore), automatic scope detection, co-author attribution, and pre-commit hook compliance. Validates staged changes, generates descriptive messages focusing on the 'why', and prevents secrets or generated-only files from being committed. Use when committing changes or generating commit messages.

Strategic analysis frameworks including Porter's Five Forces (industry attractiveness), SWOT (internal positioning), and competitive landscape mapping with battlecard generation. Produces competitor profiles, feature gap analysis, and positioning recommendations. Use when analyzing market position, evaluating threats, or building sales battlecards.

Search 21st.dev component registry for production-ready React components. Finds components by natural language description, filters by framework and style system, returns ranked results with install instructions. Use when looking for UI components, finding alternatives to existing components, or sourcing design system building blocks.

Interactive configuration wizard for OrchestKit plugin settings including MCP server enablement, hook permissions, keybindings, and installation presets (Complete/Standard/Lite). Supports preset shortcuts, per-category skill customization, and webhook configuration. Use when customizing plugin behavior or managing settings.

Generate and run comprehensive test suites — unit tests, integration tests with real services (testcontainers/docker-compose), and Playwright E2E tests. Analyzes coverage gaps, spawns parallel test-generator agents per tier, runs tests, and heals failures (max 3 iterations). Use when generating tests for existing code, improving coverage after implementation, or creating a full test suite from scratch. Chains naturally after /ork:implement. Do NOT use for verifying/grading existing tests (use /ork:verify) or running tests without generation (use npm test directly).

Creates GitHub pull requests with pre-flight validation, conventional title formatting, and structured summary generation. Runs parallel checks (tests, lint, type-check, security) before opening. Supports feature, bugfix, refactor, and hotfix PR types with milestone assignment via gh CLI. Use when opening PRs or submitting code for review.

Database design and migration patterns for Alembic migrations, schema design (SQL/NoSQL), and database versioning. Use when creating migrations, designing schemas, normalizing data, managing database versions, or handling schema drift.

Universal demo video creator for skills, agents, plugins, tutorials, CLI commands, and code walkthroughs. Generates scripts, storyboards, VHS terminal recordings, and Remotion video compositions with task-tracked production phases. Use when producing video showcases, marketing content, or terminal recordings.

Extract design DNA from existing app screenshots or live URLs using Google Stitch. Produces color palettes, typography specs, spacing tokens, and component patterns as design-tokens.json or Tailwind config. Use when auditing an existing design, creating a design system from a live app, or ensuring new pages match an established visual identity.

Imports a Claude Design (claude.ai/design) handoff bundle and scaffolds the proposed components into the project. Accepts a bundle URL or local file, parses and validates the schema, deduplicates components against the existing codebase via component-search, then pipes the survivors through the design-to-code pipeline. Writes provenance metadata so future imports can detect drift between design versions. Use after exporting a handoff bundle from claude.ai/design — this is the entry point that turns a design into code.

End-to-end Claude Design handoff to pull request: imports a handoff bundle from claude.ai/design, generates Storybook stories and Playwright tests, runs diff-aware browser verification, and opens a PR with the bundle URL, before/after screenshots, and coverage delta embedded in the body. The one-shot 'design URL in, reviewable PR out' workflow. Use when a designer or PM hands you a Claude Design URL and you want a PR back without intermediate steps.

Design token management with W3C Design Token Community Group specification, three-tier token hierarchy (global/alias/component), OKLCH color spaces, Style Dictionary transformation, and dark mode theming. Use when creating design token files, implementing theme systems, managing token versioning, or building design-to-code pipelines.

Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts screenshots, descriptions, or URLs as input and produces production-ready React components. Checks existing Storybook components before generating, orchestrates design extraction via Stitch MCP, component matching via 21st.dev registry, adaptation to project design tokens, and self-healing verification via run-story-tests. Use when converting visual designs to code, implementing UI from mockups, or building components from screenshots.

One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session — all using the current git branch as the namespace key. Replaces the 4-terminal manual setup with a single `/ork:dev` invocation. Use when starting a new feature branch, switching worktrees, or returning to a project after a break. Skip silently when prerequisite binaries (portless, emulate, agent-browser) are missing — emits install hints.

Use when setting up CI/CD pipelines, containerizing applications, deploying to Kubernetes, or writing infrastructure as code. DevOps & Deployment covers GitHub Actions, Docker, Helm, and Terraform patterns.

Distributed systems patterns for locking, resilience, idempotency, and rate limiting. Use when implementing distributed locks, circuit breakers, retry policies, idempotency keys, token bucket rate limiters, or fault tolerance patterns.

OrchestKit doctor for health diagnostics across manifest integrity, hook configuration, skill validation, agent frontmatter, MCP server connectivity, CC version compatibility, and permission rules. Reports issues with severity levels and auto-remediation suggestions. Validates component counts, detects orphaned entries, and checks CC version matrix compliance. Use when diagnosing plugin health, troubleshooting configuration issues, or running pre-release checks.

Technical documentation patterns for READMEs, ADRs, API docs (OpenAPI 3.1), changelogs, and writing style guides. Use when creating project documentation, writing architecture decisions, documenting APIs, or maintaining changelogs.

DDD tactical patterns for complex business modeling including entities, value objects, aggregates, domain services, repositories, specifications, and bounded contexts. Python dataclass implementations with TypeScript alternatives. Use when building rich domain models, enforcing invariants, or separating domain logic from infrastructure.

Nightly memory consolidation — prunes stale entries, merges duplicates, resolves contradictions, rebuilds MEMORY.md index. Use when memory files have accumulated over many sessions and need cleanup. Do NOT use for storing new decisions (use remember) or searching memory (use memory).

Generate emulate seed configs for stateful API emulation. Wraps Vercel's emulate tool for GitHub, Vercel, Google OAuth, Slack, Apple Auth, Microsoft Entra, AWS (S3/SQS/IAM), Okta, Clerk, Resend, Stripe, and MongoDB Atlas APIs. Not mocks — full state machines where create-a-PR-and-it-appears-in-the-list, send-an-email-and-retrieve-from-local-inbox. Use when setting up test environments, CI pipelines, integration tests, or offline development.

Error pattern analysis and troubleshooting for Claude Code sessions. Categorizes errors (network, auth, model, tool, memory, permission) with known resolution patterns, searches memory for prior occurrences, and suggests recovery steps. Delegates to debug-investigator agent for complex root cause analysis. Use when handling errors, fixing failures, or troubleshooting session issues.

Diff-aware AI browser testing — analyzes git changes, generates targeted test plans, and executes them via agent-browser (Rust daemon + CDP, ARIA-tree-first). Reads git diff to determine what changed, maps changes to affected pages via route map, generates a test plan scoped to the diff, and runs it with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, running regression checks on changed components, or validating that recent code changes don't break the user-facing experience.

Multi-angle codebase exploration spawning 3-5 parallel agents for code structure, data flow, architecture patterns, and health assessment. Generates ASCII visualizations, import graphs, and design pattern detection with cross-session memory storage. Use when exploring a repo, discovering architecture, onboarding to a new codebase, or analyzing design patterns.

Manages OrchestKit learning system including feedback status, usage pattern tracking, and privacy/analytics consent. Supports pause/resume learning, data export, privacy policy display, and bug reporting. Tracks learned patterns and agent performance metrics. Use when reviewing learned patterns, pausing learning, or managing data consent.

Figma-to-code design handoff patterns including Figma Variables to design tokens pipeline, component spec extraction, Dev Mode inspection, Auto Layout to CSS Flexbox/Grid mapping, and visual regression with Applitools. Use when converting Figma designs to code, documenting component specs, setting up design-dev workflows, or comparing production UI against Figma designs.

Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.

GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.

Golden dataset lifecycle patterns for curation, versioning, quality validation, and CI integration. Use when building evaluation datasets, managing dataset versions, validating quality scores, or integrating golden tests into pipelines.

OrchestKit help directory with categorized skill listings. Use when discovering skills for a task, finding the right workflow, or browsing capabilities.