Menü
Clarify WHAT a phase delivers with ambiguity scoring; produces a SPEC.md before discuss-phase.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Release or publish ahp-inspector to npm. Use when preparing an ahp-inspector npm release, running the publish.yml GitHub Action, checking a release action, or verifying the npm version and Git tag after shipping.
Generate tests for a completed phase based on UAT criteria and implementation
Generate an AI-SPEC.md design contract for phases that involve building AI systems.
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit
Audit milestone completion against original intent before archiving
Run all remaining phases autonomously — discuss→plan→execute per phase
| name | gsd-spec-phase |
| description | Clarify WHAT a phase delivers with ambiguity scoring; produces a SPEC.md before discuss-phase. |
| argument-hint | <phase> [--auto] [--text] |
| allowed-tools | Read, Write, Bash, Glob, Grep, AskUserQuestion |
Position in workflow: spec-phase → discuss-phase → plan-phase → execute-phase → verify
How it works:
Output: {phase_dir}/{padded_phase}-SPEC.md — falsifiable requirements that lock "what/why" before discuss-phase handles "how"
<execution_context> @.github/get-shit-done/workflows/spec-phase.md @.github/get-shit-done/templates/spec.md </execution_context>
<runtime_note>
Copilot (VS Code): Use vscode_askquestions wherever this workflow calls AskUserQuestion. They are equivalent.
</runtime_note>
Flags:
--auto — Skip interactive questions; the agent selects recommended defaults and writes SPEC.md--text — Use plain-text numbered lists instead of TUI menus (required for /rc remote sessions)Context files are resolved in-workflow using init phase-op.
MANDATORY: Read the workflow file BEFORE taking any action. The workflow contains the complete step-by-step process including the Socratic interview loop, ambiguity scoring gate, and SPEC.md generation. Do not improvise from the objective summary above.
<success_criteria>