claude-coding-commands

Capture what was done in the current conversation as a repeatable, well-structured skill (SKILL.md). Interviews the user to clarify intent, scope, and edge cases before writing.

Generate a high-level architecture design document from a requirements document. Covers technology choices, compute platforms, databases, data models, data flows, and security posture — no code snippets or code structure.

Generate a low-level design specification from requirements and high-level design documents. Covers class diagrams, package structure, class interactions, and testing strategy — the bridge between architecture and implementation.

Implement a specific task from the implementation plan using strict TDD. Writes failing tests first, then minimal code to pass, with human approval before committing. Tracks status in plan/{prefix}-plan.md.

Generate an implementation task plan from design documents. Breaks a low-level design into ordered, dependency-aware tasks with explicit parallelization analysis. Use when you have a completed low-level design and need to plan the implementation work.

Diagnose and fix test coverage gaps. Identifies uncovered code paths, adds targeted tests, refactors untestable code, and introduces mocking where needed. Never lowers thresholds.

Write a narrative design or proposal document iteratively, section by section, with human sign-off at each step. Use when the user wants to write a proposal, narrative, or design rationale — not a formal requirements doc or low-level design spec.

Quick research — get a sourced answer in under a minute. Use instead of /research when you need a fast answer, not a deep dive.

Generate a structured requirements document from unstructured plans or ideas. Use when the user describes a system they want to build and needs formal requirements.

Launch a deep research task. Investigates a topic and produces a structured report. Supports templates for different output types.

Template for structured options analysis with pros/cons and a recommendation. Loaded by the Researcher agent — not user-invocable.

Template for thorough open-ended research reports. Loaded by the Researcher agent — not user-invocable.

Template for three-phase learning syllabi (Apprentice, Journeyman, Master). Loaded by the Researcher agent — not user-invocable.

Review code changes for correctness, security, error handling, performance, testing, and more. Dynamically selects review perspectives based on what changed. Outputs a structured review document.

Review a high-level design document for gaps in architecture, security posture, data model soundness, technology choices, and deployment readiness. Use after producing a high-level design and before starting low-level design.

Review a low-level design document for gaps in code structure, class design, error handling, and testing strategy. Use after producing a low-level design and before starting implementation.

Execute an entire implementation plan end-to-end. Parallelizes tasks within batches, reviews each batch, fixes issues, commits, and opens a PR when done. Set-it-and-forget-it orchestration.

Bootstrap or fill gaps in a project's code quality tooling. Sets up pre-commit hooks, linting, formatting, test coverage enforcement, static analysis, dependency auditing, and documentation coverage. Writes an agent-friendly guide to AGENTS.md (or appends to CLAUDE.md if one already exists).