CLI command development specialist. Use when creating commands, designing
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →CLI command development specialist. Use when creating commands, designing
Orchestrates correct usage of .claude/commands during spec-driven workflows.
Operate the StateSet autonomous engine (jobs, workflows, policies, approvals). Use when starting/stopping `stateset-autonomous`, inspecting scheduler state, or running autonomous MCP tools.
Deep expertise in E-commerce domain logic (Cart, Checkout, SKU). Trigger this when building shopping features on top of MVC or ADR.
Building commissioning workflows including MBCx procedures, testing protocols, report generation, and energy conservation measure verification following ASHRAE Guideline 0 and NEBB standards
Use this skill when the user needs help formatting git commit messages according to Conventional Commits specification. Provides guidance on commit types, scope, and message structure.
Commit and push files modified in this session
Create comprehensive commit message from spec phases and commit all changes
**Reference files**: `.deepwork/jobs/commit/job.yml`, `.deepwork/jobs/commit/steps/test.md`
Expert at crafting clear, meaningful git commit messages following conventional commit standards and repository conventions. Use when user asks to create commit messages, write commits, or needs help with git commit text. Analyzes git diffs and repository history to generate contextual, well-structured commit messages.
Conventional Commits specification. Covers commit structure, types, breaking changes. Keywords: feat, fix, BREAKING CHANGE.
Troubleshoot frequent Anchor runtime errors: discriminator mismatch, constraint failures, account deserialization, and CPI issues. Use when tests or txs fail with Anchor errors.
Application security testing coordinator for common vulnerability patterns including XSS, injection flaws, and client-side security issues. Orchestrates specialized testing agents to identify and validate common application security weaknesses.
<purpose>
Use when parsing or generating Markdown following the CommonMark specification - AST structure, block/inline elements, and extensions
Playbook for activating current students, alumni, and partners as advocates.
Discover and rank companies in a target industry. Evaluates fit against your constraints and generates optimized job search queries.
Compare two technical perspectives with evidence from the codebase; use when deciding between options.
>
Cross-browser, cross-platform, and cross-device compatibility testing ensuring consistent experience across environments. Use when validating browser support, testing responsive design, or ensuring platform compatibility.
Expert competitive analyst specializing in competitor intelligence, strategic analysis, and market positioning. Masters competitive benchmarking, SWOT analysis, and strategic recommendations with focus on creating sustainable competitive advantages.
Porter's Five Forces, SWOT analysis, and competitive positioning matrix for strategic market analysis. Identifies threats, opportunities, and recommends positioning strategy.
Interactive conversation to resolve [NEEDS CLARIFICATION] markers using /speckit.clarify command. Claude asks questions about missing features, UX/UI details, behavior, and priorities. Updates specs in .specify/memory/ with answers to create complete, unambiguous documentation. This is Step 5 of 6 in the reverse engineering process.
Completion checklist - when is a task truly done
Verifies implementation completion by running acceptance tests and triggers retry loop on failure.
Comprehensive toolkit for creating multi-tab Excel workbooks for startups and scale-ups. Use this skill when building financial models, operational dashboards, board reports, or analytics workbooks that require data organization, complex calculations, pivot tables, visualizations, and documentation across multiple interconnected sheets. Specialized for startup metrics (ARR, MRR, CAC, LTV), board-level reporting, and data-driven decision making.
Enterprise compliance architecture for SOC 2, HIPAA, GDPR, and PCI-DSS regulated systems. Use when designing compliant systems, preparing for audits, or implementing regulatory requirements. Covers compliance checklists, data protection controls, audit evidence collection, and security policies.
Verifies code and configurations comply with security standards and regulations
Check regulatory compliance across finance, tax, employment, data privacy, and industry-specific requirements
Track regulatory compliance for construction projects. Monitor permits, certifications, inspections, and regulatory requirements with automated alerts and reporting.
Write professional documentation including README files, Storybook stories, API docs, usage examples, and migration guides for component libraries
Conditionally installs GitHub Packages component library at latest version. Adds to package.json when user requests it.
指定されたコンポーネントのリファクタリングを設計する。
Guia refatoração de componentes React seguindo padrões do Ultrathink, reduzindo duplicação e criando componentes genéricos reutilizáveis
Generate production-ready component skeletons with types, variants, tests, and documentation.
指定されたコンポーネントの全テスト(unit, a11y, vrt, interaction)を実行し、結果をレポートする。
Design composable agentic primitives for flexible workflows. Use when creating reusable workflow building blocks, designing SDLC primitives, or building agent operations that can be combined in different ways.
Expert knowledge for testing Composable Rust applications. Use when writing unit tests for reducers, setting up integration tests with real dependencies, using test utilities (TestStore, FixedClock, mocks), working with testcontainers for PostgreSQL/Redpanda, property-based testing, or questions about testing patterns and best practices.
Server-side rendering patterns for Composable Svelte. Use when implementing SSR, hydration, server rendering, isomorphic code, or working with meta tags and SEO. Covers renderToHTML, hydrateStore, server-side routing, state serialization, and avoiding common SSR pitfalls.
Compare data structures (DuckDB, LanceDB) via ACSets with persistent homology coverage analysis and geometric morphism translation.
Generate a CompoundSpec v2 JSON-only autolearn proposal from git diffstat + existing skills, while respecting strict file-scope constraints.
Exhaustive multi-dimensional project auditor covering code, runtime, infrastructure, security, performance, business logic, and human processes across 12 dimensions with confidence-tracked findings and explicit blind spot documentation. Includes dead code detection (Knip/depcheck), file size/token limit analysis for AI editing compatibility, and honest system health reporting.
Build with Solana compressed NFTs (cNFTs) - Merkle trees, minting at scale, transfers, and metadata. Use when creating large NFT collections or reducing mint costs.
Claude Computer Use tool integration for desktop automation. Enables Claude to interact with computer environments through screenshots, mouse control, keyboard input, and application automation in sandboxed environments.
Apply six transformational moves to refine concept designs, trading off between flexibility vs simplicity, generality vs specificity, and automation vs independent control. Use these moves to systemat
Create concept_summary.md as the invariant semantic anchor for an idea (writes to ideas/<IDEA_ID>/runs and updates ideas/<IDEA_ID>/latest)
Expert assistant for provisioning charm development and testing environments using concierge. Use when setting up development machines, bootstrapping Juju controllers, installing craft tools (charmcraft, snapcraft, rockcraft), or preparing test environments. Keywords include concierge, provision, development environment, Juju bootstrap, LXD, MicroK8s, K8s, craft tools, prepare, restore.
並行性の観測。データレース、デッドロック、タイミング依存バグを検出。Use when: async/await実装、スレッド/goroutine使用、共有状態操作、本番でだけ起きる問題、たまに落ちるテスト調査。
[REPLACE] Apply domain-specific logic based on detected context. Use when [REPLACE with specific triggers].
Plan, conduct, and synthesize high-signal user interviews and produce a User Interview Pack (recruiting plan, screener, discussion guide, notes template, synthesis report). Use for user interview, customer interview, discovery interview, JTBD switch interview, concept interview.