Browse skills

Debug pipeline: investigates a bug, diagnoses root cause, writes failing tests, implements fix via TDD, and reviews the result. Orchestrates bug-investigator -> bug-fixer -> code-reviewer.

The English summary is being prepared. Showing the original description.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or mentions "grill me". Run BEFORE /build when a feature idea is fuzzy and a PRD doesn't yet exist.

The English summary is being prepared. Showing the original description.

Lightweight refactor: audit → plan → approve → implement in a single Opus context, no sub-agent fan-out. Behavior preservation is the goal — verifies tests still pass, optionally commits, and offers a separate /code-review pass at the end. Use by default; reach for /refactor only when the cleanup needs parallel fan-out or exceeds one context.

The English summary is being prepared. Showing the original description.

Refactoring pipeline: analyzes a target file or directory for code quality issues, plans safe incremental improvements, optionally writes tests first as a safety net, implements the changes, and reviews the result. Orchestrates refactor-planner → (test-writer) → parallel-task-orchestrator → code-reviewer.

The English summary is being prepared. Showing the original description.

Lightweight build: explore → plan → approve → implement in a single Opus context, no sub-agent fan-out. Verifies build + tests, optionally commits, and offers a separate /code-review pass at the end. Use by default for everyday features; reach for /claude-setup:build only when the work needs parallel fan-out or exceeds one context.

The English summary is being prepared. Showing the original description.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when the user wants to stress-test a plan against the project's language and documented decisions. Run BEFORE /claude-setup:build on non-trivial features in repos that have (or should have) a CONTEXT.md.

The English summary is being prepared. Showing the original description.

Reads task files from tasks/<branch>/ and the diff against the detected base ref, then generates a polished PR description in markdown for the user to copy-paste.

The English summary is being prepared. Showing the original description.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when the user wants to stress-test a plan against the project's language and documented decisions. Run BEFORE /build on non-trivial features in repos that have (or should have) a CONTEXT.md.

The English summary is being prepared. Showing the original description.

Initialize project-level Claude setup (gitignore entries, settings.local.json) without copying agent/skill files. Use this in projects where agents were installed globally (default setup.sh behavior).

The English summary is being prepared. Showing the original description.

Lightweight build: explore → plan → approve → implement in a single Opus context, no sub-agent fan-out. Verifies build + tests, optionally commits, and offers a separate /code-review pass at the end. Use by default for everyday features; reach for /build only when the work needs parallel fan-out or exceeds one context.

The English summary is being prepared. Showing the original description.

QA pipeline: explores the running app like a real user using a browser, then produces a QA report and Playwright E2E tests for regression. Orchestrates app-scout → qa-agent.

The English summary is being prepared. Showing the original description.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or mentions "grill me". Run BEFORE /claude-setup:build when a feature idea is fuzzy and a PRD doesn't yet exist.

The English summary is being prepared. Showing the original description.

Lightweight refactor: audit → plan → approve → implement in a single Opus context, no sub-agent fan-out. Behavior preservation is the goal — verifies tests still pass, optionally commits, and offers a separate /code-review pass at the end. Use by default; reach for /claude-setup:refactor only when the cleanup needs parallel fan-out or exceeds one context.

The English summary is being prepared. Showing the original description.