Deep-research analysis of a codebase, a topic, or both. Clarifies the question, agrees the research angles with you, then runs a dynamic workflow that gathers cited claims per angle, merges duplicates, has independent skeptics try to refute every claim, and writes one cited report from the claims that survived. Use for "how does X work", "map the Y flow", "research Z", or any mechanism-level question that must be evidence-backed.
中文简介正在准备中。当前显示原文说明。
Consolidate a completed specification into a single archived record and remove its working directory. Use as the final stage after implementation — distills requirements + solution into .start/archive/[NNN]-[name].md and deletes the .start/specs/[NNN]-[name]/ directory.
中文简介正在准备中。当前显示原文说明。
Required first step before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design before implementation.
中文简介正在准备中。当前显示原文说明。
Create or update a project constitution with governance rules. Uses discovery-based approach to generate project-specific rules.
中文简介正在准备中。当前显示原文说明。
Systematically diagnose and resolve bugs through conversational investigation and root cause analysis
中文简介正在准备中。当前显示原文说明。
Generate and maintain documentation for code, APIs, and project components
中文简介正在准备中。当前显示原文说明。
Implementation entry point. Use to execute a completed specification. Reads the spec's slice and scenario tasks from the tracker, then runs a dynamic workflow that drives each slice through a barriered code→eval retry loop until its holdout scenarios pass the threshold.
中文简介正在准备中。当前显示原文说明。
Find deepening opportunities in a codebase — refactors that turn shallow modules into deep ones for better testability and AI-navigability. Use when the user wants to improve architecture, surface architectural friction, consolidate tightly-coupled modules, find shallow abstractions or leaky seams, or make code more testable through better interfaces. Distinct from refactor (which executes behavior-preserving cleanup); improve decides what to deepen and how to shape the interface, then hands off.
中文简介正在准备中。当前显示原文说明。
Refactor, simplify, or clean up code for improved maintainability without changing business logic
中文简介正在准备中。当前显示原文说明。
Self-improvement from this project's Claude Code session logs. Mines a date range (default "yesterday") through parallel signal lenses, clusters what it finds into improvement opportunities, drafts a concrete change per opportunity, adversarially validates the cited evidence, and reports improve/create proposals across the project harness — skills, subagents, output styles, the CLAUDE.md/AGENTS.md instruction, and guardrails (permission rules, hooks). Advisory — it never edits an artifact; you decide what to apply.
中文简介正在准备中。当前显示原文说明。
Evidence-based code review. Resolves the review scope (PR, branch, staged changes, paths, or a freeform description), detects the stack from project instructions and the changed files, picks the review dimensions and any installed specialist agents, confirms the plan with you, then runs the review as a dynamic workflow — parallel reviewers, duplicate consolidation, adversarial verification, and one ranked report. Use when asked to review code, a PR, a branch, staged changes, or a directory.
中文简介正在准备中。当前显示原文说明。
Scaffold, status-check, and manage specification directories. Use when creating a new spec, reading spec status, transitioning between phases, or logging decisions on a spec in .start/specs/.
中文简介正在准备中。当前显示原文说明。
Author the implementation plan — a narrative plan.md (phases + outcomes) plus the implementation TASKS in the spec's tracker that /implement runs. Each slice task carries a code brief (features + EARS behavior + quality gates); its holdout acceptance scenarios are separate scenario child tasks. Use after requirements and solution.
中文简介正在准备中。当前显示原文说明。
Create and validate product requirements documents (PRD). Use when writing requirements, defining user stories, specifying acceptance criteria, analyzing user needs, or working on requirements.md files in .start/specs/.
中文简介正在准备中。当前显示原文说明。
Create and validate solution design documents (SDD). Use when designing architecture, defining interfaces, documenting technical decisions, analyzing system components, or working on solution.md files in .start/specs/.
中文简介正在准备中。当前显示原文说明。
Create a comprehensive specification from a brief description. Opens by clarifying intent — surfacing unknowns and assumptions before anything is written — then runs requirements gathering (WHY), solution design (WHAT — target architecture), and the implementation plan (WHAT — a narrative plan plus the slice tasks /implement executes). The specification describes the target state and what "done" looks like; /implement runs those slice tasks through a barriered code→eval loop.
中文简介正在准备中。当前显示原文说明。
Use when completing implementation, fixing bugs, refactoring code, or any time you need to verify the test suite passes. Also use when tests fail and you hear "pre-existing" or "not my changes" — enforces strict code ownership. Ensures MECE coverage (no overlap, no gaps) and that ALL test categories including E2E are executed.
中文简介正在准备中。当前显示原文说明。
Validate in any of six modes — spec quality, single-file review, spec-to-implementation drift, constitution rule enforcement, comparison between two artifacts, or sanity-checking your understanding. Use when checking a spec by ID, validating a file by path, detecting drift, enforcing constitution rules, comparing two sources ("$X against $Y"), or asking a freeform validation question.
中文简介正在准备中。当前显示原文说明。
RICE, MoSCoW, Kano, and value-effort prioritization frameworks with scoring methodologies and decision documentation. Use when prioritizing features, evaluating competing initiatives, creating roadmaps, or making build vs defer decisions.
中文简介正在准备中。当前显示原文说明。
Identify existing codebase patterns (naming conventions, architectural patterns, testing patterns) to maintain consistency. Use when generating code, reviewing changes, or understanding established practices.
中文简介正在准备中。当前显示原文说明。
Unified codebase discovery across structure navigation, tech-stack detection, and documentation extraction. Use when onboarding to a project, locating implementation paths, identifying frameworks/tooling, or validating docs against code reality.
中文简介正在准备中。当前显示原文说明。
Requirement gathering techniques, stakeholder analysis, user story patterns, and specification validation. Use when clarifying vague requirements, resolving conflicting needs, documenting specifications, or validating requirements with stakeholders.
中文简介正在准备中。当前显示原文说明。
User research and insight synthesis for interviews, usability testing, personas, journey mapping, and actionable product/design recommendations. Use when planning studies, collecting evidence, synthesizing patterns, or converting findings into prioritized decisions.
中文简介正在准备中。当前显示原文说明。
Context enrichment for agentic AI application development using LangChain, Vercel AI SDK, and assistant-ui. Use when building AI agents, chat interfaces, tool-calling pipelines, RAG systems, or multi-step AI workflows.
中文简介正在准备中。当前显示原文说明。