Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
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.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
Quick spec generation with interactive or automatic mode
allowed-tools
Read, Skill, Bash, Write, Glob, Agent
argument-hint
<project-description> [--auto]
Quick Spec Generator
## CRITICAL: Automatic Mode Execution Rules
If --auto flag is present in $ARGUMENTS, you are in AUTOMATIC MODE.
In Automatic Mode:
Execute ALL 4 phases in a continuous loop without stopping
Display progress after each phase (e.g., "Phase 1/4 complete: spec initialized")
IGNORE any "Next Step" messages from Phase 2-4 (they are for standalone usage)
After Phase 4, run the final sanity review before exiting
Stop ONLY after the sanity review completes or if error occurs
Core Task
Execute 4 spec phases sequentially. In automatic mode, execute all phases without stopping. In interactive mode, prompt user for approval between phases.
Before claiming quick generation is complete, run one lightweight sanity review over the generated requirements, design, and tasks. If the host supports fresh subagents, use one. Otherwise run the sanity review inline.
Execution Steps
Step 1: Parse Arguments and Initialize
Parse $ARGUMENTS:
If contains --auto: Automatic Mode (execute all 4 phases)
Otherwise: Interactive Mode (prompt at each phase)
Extract description (remove --auto flag if present)
{{FEATURE_NAME}} → feature-name
{{TIMESTAMP}} → current ISO 8601 timestamp (use `date -u +"%Y-%m-%dT%H:%M:%SZ"`)
{{PROJECT_DESCRIPTION}} → description
en → language code (detect from user's input language, default to `en`)
After Phase 4, run a lightweight sanity review before claiming completion.
Review requirements.md, design.md, and tasks.md directly from disk. If brief.md exists, use it only as supporting context.
Prefer a fresh review subagent when the host supports it. Pass only file paths and the review objective; the reviewer should read the generated files itself.
Review focus:
Do requirements, design, and tasks tell a coherent story?
Are there obvious contradictions, missing prerequisites, or missing task coverage for required design work?
Are _Depends:_, _Boundary:_, and (P) markers plausible for implementation?
If the review finds only task-plan-local issues, repair or update the generated tasks.md once, then re-run the sanity review.
If the review finds a real requirements/design gap or contradiction, stop and report follow-up instead of claiming the quick spec is implementation-ready.
All 4 phases plus sanity review complete.
Output final completion summary (see Output Description section) and exit.
Important Constraints
Error Handling
Any phase failure stops the workflow
Display error and current state
Suggest manual recovery command
Output Description
Mode Banners
Interactive Mode:
Quick Spec Generation (Interactive Mode)
You will be prompted at each phase.
Note: Skips gap analysis and design validation.
Automatic Mode:
Quick Spec Generation (Automatic Mode)
All phases execute automatically without prompts.
Note: Skips optional validations (gap analysis, design review) and user approval prompts. Internal review gates still run.
Final sanity review still runs.
Intermediate Output
After each phase, show brief progress:
Spec initialized at .kiro/specs/{feature}/
Requirements generated → Continuing to design...
Design generated → Continuing to tasks...
Final Completion Summary
Provide output in the language specified in spec.json:
