spec-kit-plus

Advanced post-Review human acceptance workflow. Use after fresh approved Review closeout to restore a contextless human's understanding, guide one real product step at a time, and persist an explicit pass, fail, or blocked verdict.

Read-only cross-artifact consistency analysis for advanced coding models. Use when tasks exist and the specification, plan, and task boundaries need an independent gate before or during execution.

Existing-spec repair workflow for advanced coding models. Use when a specification package has planning-critical ambiguity, weak acceptance, contradictions, or new constraints that should be absorbed without recreating the feature.

Focused pre-plan feasibility research for advanced coding models. Use when a planning-ready specification still lacks a credible implementation chain, external evidence, or a disposable proof.

Lean design-system workflow for advanced coding models. Use for a new product UI, redesign, rebrand, shared visual language, or an audit/update of the root DESIGN.md contract.

Resumable product and technical discussion for advanced coding models. Use when a rough idea needs durable decisions and options before formal specification.

Read-only workflow-artifact explanation for advanced coding models. Use when the user wants a spec, plan, tasks, lane state, cognition state, or compatibility artifact explained from what is actually on disk.

Lean implementation workflow for advanced coding models. Use for ready tasks, adaptive direct or native-subagent execution, and evidence-backed feature completion.

Durable-team implementation workflow for advanced coding models. Use when work is ready for spx-implement but explicitly requires the installed integration's supported persistent team backend and durable joins.

Independent feature-lane integration and closeout for advanced coding models. Use when isolated lanes are implementation-complete and need readiness, overlap, sequencing, and recovery checks before mainline merge or PR follow-through.

Lean technical-planning workflow for advanced coding models. Use when a planning-ready specification needs repository-grounded architecture, interfaces, risks, verification, rollout, and rollback decisions.

Scan-to-PRD compilation workflow for advanced coding models. Use only after spx-prd-scan has produced a reconstruction-ready evidence package.

Reconstruction-grade repository scan for advanced coding models. Use when an existing product needs a read-only evidence package before a PRD suite can be compiled.

Lean tracked-change workflow for advanced coding models. Use when work is small but non-trivial and needs lightweight scope, resumability, implementation, and verification without a full feature specification.

Advanced system review and repair workflow. Use after implementation to prove the product starts from its real entrypoint, completes required user journeys, has no disconnected controls or registrations, and is ready for human acceptance.

Lean feature-specification workflow for advanced coding models. Use when a new capability or supplied feature PRD needs planning-ready requirements, acceptance, scope, and constraints.

Dependency-aware task-generation workflow for advanced coding models. Use when a validated plan exists and execution needs concrete outcomes, guardrails, write scopes, batches, and join points.

Codex teams runtime entrypoint for advanced coding models. Use when the operator needs to inspect, diagnose, resume, watch, or manage the supported durable team surface rather than execute a feature workflow.

Review an agent-only discussion requirement contract before it becomes ready or is consumed downstream.

Use when changing, reviewing, planning against, or debugging an existing Spec Kit Plus codebase. Consult the agent-planned project cognition query bundle as advisory navigation, then prove technical claims from live evidence.

Consume and produce reusable project Learning through the Specify CLI. Use at the start and closeout of every non-trivial SP workflow, and whenever user correction, repeated attempts, route changes, blockers, false leads, hidden dependencies, validation failures, tooling traps, or reusable project constraints appear.

Use when working inside a Spec Kit Plus repository and the user asks whether a structured sp-* workflow would help, or when a manually invoked sp-* workflow needs routing context.

Use this skill for test-first design in standalone changes or when the owning workflow selects TDD. Defers test execution to workflow-owned logical gates and attempts when sp-implement feature batching is active.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Requires current fingerprint-bound verification evidence; respects workflow-owned logical gates and attempts instead of duplicating commands.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Deterministic specify-runtime cognition build workflow for advanced coding models. Use when spx-map-scan has produced a validated scan package that must become the queryable SQLite cognition baseline.

Low-cost specify-runtime cognition scan workflow for advanced coding models. Use when a new or explicitly rebuilt baseline needs canonical repository evidence before deterministic graph construction.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Use when UI, UX, visual design, design-system, accessibility, component, platform interface, TUI, or CLI output quality matters in a Spec Kit Plus project.

State-aware workflow continuation for advanced coding models. Use when the user wants to resume or execute the safest next SPX step without naming the exact workflow.

Lean evidence-driven debugging workflow for advanced coding models. Use for a bug, regression, failed verification, or unexpected runtime behavior whose root cause is not yet proven.

Lean direct-change workflow for advanced coding models. Use for a truly trivial, local, low-risk change with a known solution and a small verification surface.

specify-runtime cognition rebuild orchestrator for advanced coding models. Use when a full rebuild is required and the independent scan then deterministic build skills should run in sequence.

Lean specify-runtime cognition maintenance workflow for advanced coding models. Use for explicit incremental map maintenance, external repository changes, interrupted updates, or a known existing-baseline gap that needs repair.

Lean, evidence-backed project Q&A for advanced coding models. Use when the user wants to understand repository facts, architecture, status, impact, or workflow choices without changing files.

Focused requirements-quality checklist workflow for advanced coding models. Use when a feature needs unit tests for the written requirements or planning package, not implementation testing.

Project-governance workflow for advanced coding models. Use when project principles or development rules must be created, revised, or realigned before downstream specification or planning.

Deprecated PRD compatibility entrypoint for advanced coding models. Use only when an older operator invokes spx-prd and must be routed to the canonical reconstruction scan and build skills.

Compatibility research entrypoint for advanced coding models. Use only when the operator invokes the older research name for the canonical pre-plan deep-research workflow.

Explicit task-to-GitHub-issue export for advanced coding models. Use when a validated task graph should be published to the repository tracker with dependency intent preserved.