Maps an existing codebase before anyone changes it. Use whenever someone wants to understand or take stock of code that already exists — an overview of the stack (runtime, framework, libraries, versions, what is deprecated or end-of-life), an inventory of entry points, modules, dependencies and integrations, how a…
Answers which files to refactor first to reduce systemic risk, by crossing blast radius (how many modules stop working if this one breaks) against size. On first use it asks permission, installs its own tooling and writes a config by reading the project; on every run after that it executes a versioned script and reads…
Performs an exhaustive, item-by-item deep analysis of every module, service, component, or endpoint listed in the Architecture Analysis Report (REQUIRED as input). Maps every implementation detail, data flow, contract, and failure mode, and produces a structured Deep Analysis Report. Analysis/reporting only — never…
Externally evaluates an already-implemented feature against its contract.md (environment, quality gates, coverage manifest, observable criteria), producing screenshots, a report, and chat findings. Owns the evaluation loop — keeps the attempt counter in progress.json, decides the state (CLEAN/FAIL/PENDING/ABORTED)…
Dispatch-only corrector: it runs when the evaluator skill dispatches it on FAIL, or qa-preflight after a feature is done — never from a person's request. When someone asks to fix what an evaluation reported, use evaluator instead; it owns the correction loop and hands this skill the report. Reads the structured…
Builds the deterministic quality-gate infrastructure for a project (typecheck, lint with zero-warnings, dependency/architecture checks, tests, dead-code, and a single runGate entry point) from the Deep Analysis Report (+ Architecture Analysis Report). Auto-detects greenfield vs. brownfield, proposes a gate plan for…
Compacts the current conversation into a handoff document a fresh agent can pick up from, and asks where to save it before writing anything. Use when a session ends with work unfinished, when switching branch or machine, or when passing the work to another person. Records what is not already written down elsewhere and…
Implements a feature autonomously based on its spec, plan, AND contract.md, committing one commit per phase, satisfying the contract's quality gates and observable criteria, writing progress.json, and reporting results against the feature's acceptance criteria. Delegates test writing to the matching test-writer skill…
Use when an integration test file or folder of any project must be audited for conformance before it is trusted — dispatched by the evaluator or qa-preflight after an integration-test-writer correction or new test, or run directly by a user. Generic — reads the environment, the helpers, the data policy and the…
Use when an endpoint or module needs integration tests in any project — requests through the real stack against a real test environment — when implement-feature dispatches a phase's tests, when the evaluator or qa-preflight dispatch the correction of a failing integration test or a missing query-growth test, or when a…
Generate complete PRDs (Product Requirements Documents) through iterative clarification. Use when: (1) Starting a new project and need structured requirements, (2) Creating product specifications with 9-section PRD format, (3) Defining product scope from a description or context files. Keywords: "prd", "product…
The gate between a finished feature and the human QA. Investigates the delivered feature against its spec and the running screen, executes what is automatable, dispatches the existing correctors for defects that are objectively wrong, leaves a permanent guard so each defect cannot return unnoticed, and writes a QA…
Generates technical implementation spec, plan, AND an operational contract for one or more features based on PRD, codebase analysis, and iterative clarification. Produces contract.md (environment contract, quality gates, coverage manifest, observable criteria) consumed by implement-feature and evaluator. Supports…
Use when a unit test file or folder of any project must be audited for conformance before it is trusted — dispatched by the evaluator or qa-preflight after a unit-test-writer correction or new test, or run directly by a user. Generic — reads the suites, the runner and the project's own rules from the test profile in…
Use when a source file needs unit tests in any project — when implement-feature dispatches a phase's tests, when the evaluator or qa-preflight dispatch the correction of a failing unit test or coverage for a rule that has none, or when a user asks to plan or write unit tests. Generic — where the tests live, the…
Use when an end-to-end test file or folder (Playwright flows of any project whose GATES.md declares an e2e suite) must be audited for conformance before it is trusted — dispatched by the evaluator or qa-preflight after an e2e-test-writer correction, guard or new test, or run directly by a user. Generic — reads the…
Use when a feature needs end-to-end tests (Playwright flows against the running app) for any project whose GATES.md declares an e2e suite — when a user asks to plan or write e2e tests for a contract's UI surfaces, when implement-feature, evaluator or qa-preflight dispatch e2e coverage or a guard for a missing flow…
Use when a task creates, changes, reviews or audits user interface and needs to know which design rules bind it — implement-feature before a UI phase, gate-builder looking for the source of a design-system gate, qa-preflight needing the values to measure, or a person asking to write a project's design-system doc or to…
★not rated 3 16d agoA113 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: