skill-name
{{SKILL_DESCRIPTION}}
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Menu
{{SKILL_DESCRIPTION}}
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Your project awareness buddy. Knows current state, reads docs, analyzes code, answers "where are we?" questions. Activate with "bro" or "project-bro".
Systematic debugging skill. 7-step workflow: Reproduce, Minimize, Hypothesize, Instrument, Fix, Prevent, Verify. Activate when troubleshooting errors.
Expert on Model Context Protocol (MCP) servers. Use this skill when designing, building, debugging, or integrating MCP servers with tools, resources, and prompts.
Analyzes codebase, designs modular refactoring specs, and delegates to domain executors. Runs static analysis, queries Context7 for best practices, and creates enforcement mechanisms.
Expert in Docker, CI/CD, and delivering Go/Nuxt apps.
Quality Assurance Lead. Tests E2E, API, and UI.
| name | {"[object Object]":null} |
| description | {"[object Object]":null} |
{{SKILL_PURPOSE_SUMMARY}}
[!IMPORTANT]
First Step: Read Project Config & MCP
Before making technical decisions, always check:
File Purpose project/CONFIG.yamlStack versions, modules, architecture mcp.yamlProject MCP server config mcp/Project-specific MCP tools/resources Use project MCP server (named after project, e.g.
mcp_xlinefitness-bot_*):
list_resources→ see available project data*_tools→ project-specific actions (db, cache, jobs, etc.)Use
mcp_context7for library docs:
- Check
mcp.yaml → context7.default_librariesfor pre-configured libs- Example:
libraryId: /nuxt/nuxt, query: "Nuxt 4 composables"
Before acting, determine the specific scenario:
scripts/script_a.pyreferences/guide_a.mdTip: Use
task_boundaryto track progress if this is a long task.
[!IMPORTANT] Phase 1: Draft in Brain
- Create drafts as UI Artifacts (in
brain/conversation directory)- Iterate with user via
notify_useruntil approved- Keep Q&A and sketches here — do NOT pollute
project/docs/Phase 2: Persist on Approval
- ONLY after "Looks good" → write final to
project/docs/path- Update file status:
Draft→Approvedin header- The
project/docs/folder is the ONLY memory that survives sessions
project/docs/<category>/<artifact>.md<previous skill artifacts>project/docs/ARTIFACT_REGISTRY.md (status + timestamp)[!CAUTION] NO CODE WITHOUT FAILING TEST.
- Red: Write test → Fail.
- Green: Write code → Pass.
- Refactor: Clean up. NEVER write implementation code without a failing test. NEVER fix a bug without a reproduction case.
[!CAUTION] BEFORE delegating to next skill:
- ✅ Final document exists in
project/docs/(not just brain artifact)- ✅ File header changed from
DrafttoApproved- ✅
project/docs/ARTIFACT_REGISTRY.mdupdated to ✅ Done- ✅ User approved via
notify_user- THEN delegate
scripts/:
example_script.py: {{SCRIPT_DESC}}references/:
reference.md: {{REF_DESC}}