发现 Skills

Help users run effective post-mortems and retrospectives. Use when someone is reviewing a project that succeeded or failed, wants to establish learning practices, is dealing with failure aftermath, or needs to improve team learning loops.

Help users conduct effective usability testing. Use when someone is planning user tests, designing prototype validation, preparing usability studies, or trying to understand why users struggle with their product.

Expert in consent to assignment agreements where a tenant transfers their entire lease to a new party (assignee). Use when a tenant is selling their business and assigning the lease, a landlord is reviewing a consent request, analyzing whether the original tenant remains liable after assignment, drafting assignment consent agreements, negotiating release provisions, or handling assignment-plus-sublease combinations (e.g., professional corporations). Key terms include assignment vs. sublease, assignee, privity of estate, joint and several liability, no release, recapture rights, assignor remains liable, change of control, business sale.

How to use a Win32 build of BusyBox to run many of the standard UNIX command line tools on Windows.

Automate Google Search Console tasks via Rube MCP (Composio): query search analytics, list sites, inspect URLs, submit sitemaps, monitor search performance. Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas.

Automate Passslot tasks via the Rube MCP (Composio). Always search tools first for current schemas.

Intelligently organizes files and folders by understanding context, finding duplicates, and suggesting better organizational structures. Use when user wants to clean up directories, organize downlo...

Conducts multi-turn, iterative, deep research on specific topics within a codebase with zero tolerance for shallow analysis. Use when the user wants an in-depth investigation, needs to understand how specific components or flows operate, or requires evidence-backed conclusions.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Full-site migration from Beaver Builder to the WordPress block editor (Gutenberg). Audits every Beaver Builder page, maps modules to their Gutenberg block equivalents, builds a migration plan for a...

Full-site migration from Oxygen Builder to Breakdance. Audits every Oxygen-built page, maps components to their Breakdance equivalents, builds a migration plan for approval, and executes page-by-pa...

Full-site migration from Thrive Architect to the WordPress block editor (Gutenberg). Audits every Thrive-built page, maps elements to their Gutenberg block equivalents, builds a migration plan for ...

Adversarial review protocol for brainstorming, product planning, and technical architecture. Validate ideas against reality, enforce minimum 3 bugs, severity categorization, 3 resolution paths. USE WHEN: "adversarial review", "run adversarial protocol", "validate brainstorming", "stress test idea/plan/architecture", or reviewing any planning document. CORE PROTOCOL: 1. Reality vs Claims — web search min 3x diverse angle, status VALID/PARTIAL/INVALID 2. Acceptance Criteria — stress test specific executor capability 3. Mandatory Bug Quota — minimum 3 issues, force deeper dig if insufficient 4. Interactive Resolution — Critical/High/Medium/Low + options A(auto-fix)/B(action items)/C(deep dive) DIFFERENTIATOR: Mandatory bug quota prevents superficial reviews. Three resolution options make findings actionable. Executor stress test differentiates from generic reviews.

Creates DevRev CX agents from analyzed ticket data or manual configuration. Final step in CX agent building pipeline. Accepts config JSON from ticket-analyzer HTML report (recommended) or builds from scratch. Generates model-specific prompts with SOPs, guardrails, and skills. Always runs a dry-run first for validation.

Manage long-running background jobs and interactive workflows on Windows using PowerShell Jobs (Start-Job, Receive-Job) — the Windows equivalent of tmux sessions.

Debugs Kubernetes RBAC and permission issues including Forbidden errors, ServiceAccount permissions, Role/RoleBinding, and ClusterRole/ClusterRoleBinding problems. Use when seeing permission denied, forbidden errors, or ServiceAccount access issues.

Retrieves Kubernetes container logs with various patterns including multi-container pods, previous container logs, init containers, and label-based aggregation. Use when checking application logs, debugging crashes, or analyzing container output.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Design GCP architectures for startups and enterprises. Use when asked to design Google Cloud infrastructure, deploy to GKE or Cloud Run, configure BigQuery pipelines, optimize GCP costs, or migrate to GCP. Covers Cloud Run, GKE, Cloud Functions, Cloud SQL, BigQuery, and cost optimization.

Validate, test, and score the quality of skills within the claude-skills ecosystem. Comprehensive meta-skill: structure validation, Python script testing (syntax + imports + runtime + output format), multi-dimensional quality scoring with letter grades and tier classification (BASIC/STANDARD/POWERFUL). Use when authoring a new skill, auditing existing skills for tier promotion, setting up pre-commit hooks for skill quality, or integrating skill QA into CI.

Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.

Design the structural and emotional architecture for nonfiction books. Use when an author has a validated book concept and needs to create the blueprint before drafting. Triggers include requests to structure a book, create a chapter outline, design a table of contents, map the reader's journey, or plan book organization. Requires upstream documents from book-ideation (Book Concept Document) and optionally from idea-validator (Validation Report) and market-research (Market Research Report).

Tauri development guidelines for building cross-platform desktop applications with TypeScript, Rust, and modern web technologies

Bump the version of the zenoh-ros2-sdk package across all configuration files. Use when the user asks to update, bump, or change the package version, or when preparing a new release.