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 →[52] EXECUTE. Three-stage refactoring workflow: (1) iterative research of refactor/modularization options, (2) plan + risk/edge-case analysis + Scope150 validation, then implement with tests after user confirmation, and (3) apply Scout105 cleanup protocol. Use when asked to refactor, modularize, or restructure code safely.
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
Final step in building instruction context for codebase
Test features before users find bugs. Use when feature is built, before deploying, or when bugs reported. Covers manual testing, edge cases, cross-browser testing, and testing checklists for non-technical founders.
[60] VALIDATE. Ensure new (staged and unstaged) changes are covered by tests at >70% and the full test suite is green. Use when asked to validate coverage for recent changes, add tests for modified code, or verify nothing else broke.
You've spent this chapter building mental models: the LLMOps lifecycle, training taxonomy, economic analysis, use case specification. All valuable knowledge—but knowledge fades. Six months from now, y
Create your LLMOps data engineering skill in one prompt, then learn to improve it throughout the chapter
You've trained two specialized adapters: a TaskMaster persona adapter (Chapter 65) and an agentic tool-calling adapter (Chapter 66). Now you need to combine them. But before you learn the theory of mo
Fix bugs systematically instead of guessing. Use when features break, users report errors, or tests fail. Covers reproducing bugs, gathering diagnostic info, and working with AI tools to fix issues efficiently for non-technical founders.
Consolidate all Part 8 skills into a production-ready llmops-fine-tuner skill
Create documentation with gaming-specific examples, retro styling, and 8-bit terminology. Apply when documenting gaming blocks, RPG components, or retro-styled UI elements.
Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn. Use when users need icons, favicons, social sharing images, or Open Graph images from logos or text slogans. Handles image resizing, text-to-image generation, and provides proper HTML meta tags.
Generate AIAG-format Control Plans linked to PFMEAs with proper inspection methods, frequencies, and reaction plans. Supports Prototype/Pre-launch/Production phases. USE WHEN user says 'control plan', 'CP', 'inspection plan', 'process control', 'sampling frequency', 'reaction plan', or 'special characteristics'. Integrates with PFMEA, AutomotiveManufacturing, and MSA skills.
Agent evaluation framework based on Anthropic's best practices. USE WHEN eval, evaluate, test agent, benchmark, verify behavior, regression test, capability test. Includes three grader types (code-based, model-based, human), transcript capture, pass@k/pass^k metrics, and ALGORITHM integration.
Prompt injection testing. USE WHEN prompt injection, jailbreak, LLM security, AI security assessment, pentest AI application, test chatbot vulnerabilities.
Expert record keeping system with paperless-ngx integration, country-specific taxonomies, and intelligent document management. USE WHEN upload document, store file, organize records, find document, search papers, tag documents, delete records, retention check, archive documents, add entity, create trust, validate trust, workflow create, FTE check, connection test, system status, check status.
Safety Monitor
Web security assessment. USE WHEN web assessment, pentest, security testing, vulnerability scan. SkillSearch('webassessment') for docs.
You're an experimentation leader who has built testing cultures at high-velocity product
Comprehensive WCAG accessibility auditing with multi-tool testing (axe-core + pa11y + Lighthouse), TRUE PARALLEL execution with Promise.allSettled, graceful degradation, retry with backoff, context-aware remediation, learning integration, and video accessibility. Uses 3-tier browser cascade: Vibium → agent-browser → Playwright+Stealth.
Accessibility audit for CSS covering focus styles, color contrast, text sizing, screen reader support, and WCAG compliance. Provides actionable fixes. Use when auditing accessibility or fixing a11y issues.
Expert in web accessibility (WCAG 2.1/2.2 AA/AAA compliance), ARIA patterns, keyboard navigation, screen reader testing, color contrast, focus management, and automated accessibility testing
SDK installation and setup patterns for Agent-to-Agent Protocol across Python, TypeScript, Java, C#, and Go. Use when implementing A2A protocol, setting up SDKs, configuring authentication, or when user mentions SDK installation, language-specific setup, or A2A integration.
Implement state machines with AASM for workflow management. Covers state transitions, guards, callbacks, and testing.
Design and analyze A/B tests, calculate statistical significance, and determine sample sizes for conversion optimization and experiment validation
Calculate statistical significance for A/B tests. Sample size estimation, power analysis, and conversion rate comparisons with confidence intervals.
Эксперт A/B тестирования. Используй для статистических тестов, экспериментов и ML-оптимизации.
Expert in statistical analysis for blind A/B and ABX audio testing. Validates randomization, calculates statistical significance, and ensures proper experimental design. Use when implementing A/B test features or analyzing test results.
Use when designing experiments for subject lines, offers, cadences, or
Complete workflow for dynamic analysis. Use when user mentions impact, crash, drop test, transient, or time-varying response. Handles explicit and implicit dynamics.
Configure output requests - field outputs, history outputs. Use when user asks what results to save, output variables, reduce output file size, or history output.
Master skill for Abaqus FEA scripting. Use for any finite element analysis, topology optimization, or Abaqus Python scripting task. Routes to appropriate specialized skills.
Abductive analysis for qualitative interview data following Timmermans & Tavory. Guides you through theory-first analysis that recognizes anomalies and generates novel theoretical insights through systematic puzzle exploration.
Hypothesis-Test Loops via REPL for Exploratory Abductive Inference with Gay.jl colors
Эксперт ABM. Используй для account-based marketing, target account selection и personalized campaigns.
Read `.claude/aboutme-index.json` to find files by purpose instead of grep-searching.
Generate ABP Application.Contracts layer scaffolding (interfaces, DTOs, permissions) from technical design. Enables parallel development by abp-developer and qa-engineer. Use when: (1) backend-architect needs to generate contracts, (2) preparing for parallel implementation workflow, (3) creating API contracts before implementation.
Expert in groups, rings, fields, and algebraic structures with applications to cryptography and number theory
Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps. Invoke when user mentions abstraction levels, making concepts concrete, or explaining at different depths.
Law-driven abstraction protocol: evidence first, seam test, minimal algebra, executable law check.
Toolkit for creating an entertainingly stupid README that manages to give off Tim & Eric, Steve Brule vibes while maintaining a level of technical acumen that is expected of a modern open source project. This skill applies when users request a silly or absurd README.
Species abundance estimation using Bracken with Kraken2 output. Redistributes reads from higher taxonomic levels to species for more accurate estimates. Use when accurate species-level abundances are needed from Kraken2 classification output.
Turn vague Acceptance Criteria into measurable checks and test assertions
Master controller for complete autonomous operation. Use when starting full autonomous projects, managing end-to-end workflow, controlling autonomous lifecycle, or running complete implementations.
Parse and validate project specifications. Use when loading YAML/JSON specs, validating spec structure, extracting requirements, or converting between spec formats.
Run TDD cycle for feature implementation. Use when implementing features with RED-GREEN-REFACTOR, running test-driven development, automating TDD workflow, or ensuring test-first development.
When the user requests to create or customize an academic personal website from a GitHub template repository. This skill handles the complete workflow of forking academic template repositories (like academicpages.github.io), extracting structured personal information from memory or provided data, and systematically updating configuration files (_config.yml), navigation menus (_data/navigation.yml), content pages (_pages/about.md), and publication listings (_publications/). It specifically handles academic profiles including personal details, education background, research experience, publications, skills, and contact information. Triggers include requests to 'fork and customize academic homepage', 'build personal academic website', 'create research portfolio', or 'set up GitHub pages with academic template'.
Transform academic course assignment PDFs into structured, actionable markdown checklists with dates, unique IDs, and custom tags. Asks when the user will start, assigns tasks only to weekdays (Monday-Friday), respects weekends automatically, and calculates forum deadlines 3 days before due date. Use this skill when the user uploads academic PDFs or asks to create a task plan from course assignments.
Comprehensive toolkit for writing high-quality computer science research papers (conference, journal, thesis). Provides narrative construction guidance, sentence-level clarity principles (Gopen & Swan), academic phrasebank, CS-specific conventions, and section-by-section quality checklists. Use when assisting with academic paper writing, revision, or structure planning across all stages from drafting to submission.
Action-Domain-Responder pattern knowledge base. Provides patterns, antipatterns, and PHP-specific guidelines for ADR (web-specific MVC alternative) audits.