LLM & Agents

DO NOT invoke directly - loaded by workflow agents via cc10x-router.Always loaded by: component-builder.Provides code writing patterns: understand functionality first, write minimal code, match project patterns. Iron Law: NO CODE BEFORE UNDERSTANDING FUNCTIONALITY.

test-engineer skillTrigger terms: testing, unit tests, integration tests, E2E tests, test cases, test coverage, test automation, test plan, test design, TDD, test-firstUse when: User requests involve test engineer tasks.

Loaded by ALL agents before completion claims in cc10x-router workflows. DO NOT invoke directly - loaded automatically via agent frontmatter.Requires running verification commands and confirming output with evidence before any success claims. Iron Law: EVIDENCE BEFORE CLAIMS.Agents are invoked through cc10x-router workflows (BUILD/REVIEW/DEBUG/PLAN) - do not invoke agents or this skill directly.

THE ONLY ENTRY POINT FOR CC10X - AUTO-LOAD AND EXECUTE when user says: build, implement, create, make, write, add, develop, code, feature, component, app, application, review, audit, check, analyze, debug, fix, error, bug, broken, troubleshoot, plan, design, architect, roadmap, strategy.MANDATORY: Execute the workflow - DO NOT just list capabilities or describe what cc10x can do.CRITICAL: All agents and skills MUST be invoked through this router. Never invoke agents or skills directly - they will not work correctly without router's memory management.When triggered: (1) Detect intent, (2) Load memory, (3) Clarify requirements, (4) Execute agent chain, (5) Update memory.

test-engineer skillTrigger terms: testing, unit tests, integration tests, E2E tests, test cases, test coverage, test automation, test plan, test design, TDD, test-firstUse when: User requests involve test engineer tasks.

Spec-first planning workflow that produces an approved plan.md before implementation, with reviewer subagent feedback and progress tracking. Use when a user asks for a plan-before-code process, a review-gated implementation plan, or a single plan.md that includes tasks and ongoing progress updates, with commits after each phase.

Creates high-quality Claude skills following official best practices. Use when the user asks to create a new skill, improve an existing skill, or needs guidance on skill authoring. Includes proper structure, naming conventions, progressive disclosure patterns, and quality validation.

Write and optimize prompts for AI-generated outcomes across text and image models. Use when crafting prompts for LLMs (Claude, GPT, Gemini), image generators (Midjourney, DALL-E, Stable Diffusion, Imagen, Flux), or video generators (Veo, Runway). Covers prompt structure, style keywords, negative prompts, chain-of-thought, few-shot examples, iterative refinement, and domain-specific patterns for marketing, code, and creative writing.

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy

Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agentsTrigger terms: agent stuck, loop detected, session memory, agent learning, condense memory, stuck detection, agent memory, session learnings, extractionUse when: User reports agent is stuck, looping, or needs memory/learning management

Guide for creating effective skills, adding skill references, skill scripts or optimizing existing 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, frameworks, libraries or plugins usage, or API and tool integrations.

DO NOT invoke directly - loaded by workflow agents via cc10x-router.Conditionally loaded by: code-reviewer (UI code), component-builder (UI component), bug-investigator (UI bug), integration-verifier (UI flow testing), planner (UI planning).Provides frontend patterns: UX, visual design, accessibility, responsive design. Iron Law: NO UI DESIGN BEFORE USER FLOW IS UNDERSTOOD.

Copilot agent that assists with database operations, performance tuning, backup/recovery, monitoring, and high availability configurationTrigger terms: database administration, DBA, database tuning, performance tuning, backup recovery, high availability, database monitoring, query optimization, index optimizationUse when: User requests involve database administrator tasks.

DO NOT invoke directly - loaded by workflow agents via cc10x-router.Always loaded by: code-reviewer, silent-failure-hunter.Provides code review patterns: two-stage review (spec compliance first, then quality), security, performance. Iron Law: NO QUALITY REVIEW BEFORE SPEC COMPLIANCE.

DO NOT invoke directly - loaded automatically by ALL agents via frontmatter in cc10x-router workflows.MANDATORY skill loaded at start and updated at end of EVERY workflow. Persists context, learnings, decisions, and progress to .claude/cc10x/ folder. Without this, context is lost on compaction.Agents are invoked through cc10x-router workflows (BUILD/REVIEW/DEBUG/PLAN) - do not invoke agents or this skill directly.

Guidance for building the chatgpt-app (Vite + React + @openai/apps-sdk-ui) with the MCP-friendly single-file output.

Execute specification-driven implementation with automatic quality gates, multi-agent orchestration, and progress tracking. Use when building features from specs, fixing bugs with test coverage, or refactoring with validation.

Comprehensive testing patterns for React components with MSW, React Query, and Vitest. Use when writing tests, setting up mocks, testing API interactions, or ensuring 80% coverage. Keywords - testing, MSW, React Query, Vitest, mocks, coverage, API testing.

Skill professionnel pour Claude Code permettant d'accéder, télécharger et analyser les données ouvertes françaises via data.gouv.fr. Inclut une librairie Python complète, des exemples de code, et une documentation détaillée des datasets les plus utilisés.

Specialized skill for Rails testing with RSpec, FactoryBot, and TDD workflows. Use when writing tests, setting up test coverage, creating factories, or implementing test-driven development. Covers unit tests, integration tests, system tests, and component tests.