菜单
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/.
Lightweight implementation orchestrator for low-complexity work — fixes, refactors, doc changes, or single-AC features that do not warrant a phase plan or factory decomposition.
Linear phase-loop orchestrator for single-feature implementation plans. Use for medium-complexity work where transparent human-in-the-loop phase review is preferred over factory automation.
Implementation entry point. Use to execute a completed specification. Auto-detects the decomposition tier (Direct, Incremental, or Factory) from spec artifacts and dispatches to the matching execution sub-skill.
Decompose a single-feature specification into a linear, phase-by-phase implementation plan. Use this for medium-complexity work — single feature, one or two components — where transparent human-in-the-loop phase review is preferred over factory automation.
Create a comprehensive specification from a brief description. Runs requirements gathering, solution design, and decomposition — routing decomposition to one of three tiers based on a complexity classifier: Direct (no plan), Incremental (linear phase plan), or Factory (parallel units with holdout scenarios).
Factory loop orchestrator for multi-feature or multi-component implementation manifests. Use for high-complexity work with parallel-eligible workstreams and holdout-scenario evaluation.
| name | specify-meta |
| description | 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/. |
Act as a specification workflow orchestrator that manages specification directories and tracks user decisions throughout the Requirements → Solution → Decomposition workflow. The Decomposition phase produces one of three artifact families based on the tier chosen by the specify classifier: Direct (no artifacts), Incremental (plan/ directory), or Factory (manifest.md + units/ + scenarios/).
SpecStatus { id: string // 3-digit zero-padded (001, 002, ...) name: string directory: string // .start/specs/[NNN]-[name]/ (legacy: docs/specs/) phase: Initialization | Requirements | Solution | Decomposition | Ready decomposition_tier: Direct | Incremental | Factory | None documents: { name: string status: pending | in_progress | completed | skipped notes?: string }[] }
State { specId = "" currentPhase: Initialization | Requirements | Solution | Decomposition | Ready decompositionTier: Direct | Incremental | Factory | None documents: [] }
Always:
Never:
Create a new spec with an auto-incrementing ID.
Bash("spec.py \"$featureName\"").Read existing spec metadata.
Bash("spec.py \"$specId\" --read").match (documents) { manifest exists => "Factory manifest found. Proceed to implementation?" plan exists => "Incremental plan found. Proceed to implementation?" solution exists, no decomposition => "Solution found. Continue to Decomposition (classifier will recommend Direct, Incremental, or Factory)?" requirements exists, no solution => "Requirements found. Continue to Solution?" no documents => "Start from Requirements?" }
Update the spec directory to reflect the new phase.
match (phase) { Requirements => specify-requirements skill Solution => specify-solution skill Decomposition => route by tier: Direct => no skill invocation (no artifacts written) Incremental => specify-incremental skill Factory => specify-factory skill }
Append a row to the README.md Decisions Log table. Update the Last Updated field.
match ($ARGUMENTS) { featureName (new) => execute step 1 (Scaffold) specId (existing) => execute steps 2, 3, and 4 in order }