leandrosilvaferreira

Condenses harness .md prompts (.claude/agents, commands, rules, skills) using caveman full + Opus, without losing information. Compresses verbose prose and tables, preserves code blocks/URLs/inline-code/headings via a deterministic gate. Overwrites in place (git is the review safety net). Use when asked to "condense/compress/shorten the agents/commands/rules/skills in .claude".

Audit .claude/agents/*.md frontmatter descriptions against the routing-description standard (condition-shaped, "Use proactively", 40-600 chars) and sync them with the project's CLAUDE.md `## Workflow & Agents` table or free-text mentions. Fixes descriptions in place, fixes stale/missing table rows, flags orphaned agents. Works on any existing project — not just one scaffolded by aia-harness. Use standalone, or after adding/editing agents by hand.

Generate or refresh rich intermediate CLAUDE.md files for strategic subdirectories of the target project. Reads .claude/rules/ (recursive), analyzes actual source files, maps rules to domains, and generates domain-specific CLAUDE.md with Key patterns, Applied rules, and Local conventions sections. Two-phase: map → approve → generate with diffs. Use after /aia-harness:init (step 5.6), or standalone to refresh existing files.

Seeds unit tests in a project that has none — installs the recommended framework for the stack, writes a real test in an existing module, wires the `test` script, and runs until green. Use when the project has no tests, when asked to "configure tests", "setup tests", "add tests", or "create test suite".

Use when setting up, scaffolding, bootstrapping, or improving a Claude Code "harness" for a project — hooks, skills, agents, rules, settings.json, .mcp.json, settings.local.json, worktree config, or per-domain CLAUDE.md. Triggers on "set up Claude Code", "harness engineering", "scaffold hooks/rules", "configure this project for Claude", "bootstrap .claude".

Review and upgrade the routing descriptions of candidate agents under templates/ (ECC, ag-kit, first-party) so each follows the best-practice standard — condition-shaped, with "Use proactively" and explicit trigger conditions. Writes the canonical description into the matching *_AGENT_WHEN_TO_USE map, propagates it into every agent file, and verifies the integrity gate. Use after editing any candidate agent, or standalone to sweep all of them.

Guards the Drizzle-kit generate → review → migrate flow for NestJS + Drizzle ORM projects. Use when changing the database schema or applying a migration.

Guides writing Jest unit tests for NestJS services and controllers using @nestjs/testing and mocked Drizzle DB. Use when adding or expanding unit tests.

Rank the functions/modules changed this session by test-worthiness and output TEST / integration-only / SKIP per symbol. Uses graphify blast-radius when graphify-out/ exists, a static rubric otherwise. Use when you changed several units and are unsure which deserve a unit test, or before writing tests for a batch of new code.

Use when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.

Use when publishing a new version of gitai to npm — cutting a release, bumping the version, shipping to the registry — or when a release was cut but the new version never reached npm, or a user reports the CLI still showing an old version.

Use when asked to generate, build, prepare, optimize or assemble a /goal command for autonomous or overnight execution — triggers: "montar goal", "gerar goal autônomo", "preparar task overnight", "goal para sessão autônoma", "otimizar goal", "goal builder".

Smoke test end-to-end do gitai CLI em repo temporário

Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, set issue fields (dates, priority, custom fields), set issue types, manage issue workflows, link issues, add dependencies, or track blocked-by/blocking relationships. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", "set the priority", "set the start date", "link issues", "add dependency", "blocked by", "blocking", or any GitHub issue management task.

This skill should be used when the user mentions tickets, issues, backlog, PR, pull request, worktree, sprint, or any development project management activity. Also activate when the user says "create issue", "work on #N", "close ticket", "open PR", "merge PR", "view backlog", "create branch for issue", or when code was modified without a linked issue.

Use when bootstrapping a repo (apply branch protection before first PR), PRs won't merge or BLOCKED, AI reviewer pushback, auto-merge fails for Dependabot/Renovate, branch protection or rulesets, CI fails, authoring reusable workflows, harden-runner, or CODEOWNERS/PR templates.