Menu
Execute tasks from tasks.md. Implement code changes, update progress. Use after plan approval.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | sspec-implement |
| description | Execute tasks from tasks.md. Implement code changes, update progress. Use after plan approval. |
| metadata | {"author":"frostime","version":"3.0.0"} |
| Situation | Action |
|---|---|
| Task is ambiguous | @align for clarification |
| Implementation reveals design issue | See Design Changes During Implementation below |
| Blocker encountered | Record in memory.md, @align user |
| Multiple valid approaches | Pick the simpler one, note in memory |
| Design assumption was wrong | Re-enter Clarify posture: "Design says X but I found Y" → re-sync with user before revising |
Do not guess on blockers. One @align < one rework cycle.
Apply this test first:
Can the original spec/design still accurately predict the post-change code? YES → note in memory, continue | NO → revision required
If revision required:
@align user: explain the gap, get confirmationsspec change scaffold revision <change> --title "..." — create revision filetasks.md to reflect new workThis applies whether the issue was triggered by a user comment or self-discovered.
@align user before creating a new changeFor long sessions (>30 exchanges or multi-file work):
memory.md Knowledgememory.md MilestonesTest: "Would I struggle to continue if context was compressed right now?" → Write to memory.
When all tasks are complete:
User Check, include the user review recipe: action + expected observable result, mapped to BC-*@align user: "Implementation complete. Please review."This is a hard gate. → Transition to sspec-review phase.
→ Status transitions: sspec howto update-change-status
Pre-scan Markdown files before reading. Use `sspec tool mdtoc` to get file size + heading structure with line numbers (L<n> format) before reading long docs, SKILLs, or spec-docs. Eliminates blind reads.
Assess scale, create change, fill spec.md + design.md, align with user. Use after clarify when ready to define the solution.
Break design into concrete tasks. Fill tasks.md with file-level execution plan. Use after design alignment.
User acceptance and feedback loop. Handle argue-improve cycles until user is satisfied.
Build shared understanding through dialogue and investigation. Produces Problem Statement + direction sketch. Reusable posture, not rigid phase.
Structured, efficient agent-user synchronization at decision points. Formalized exchange over prose.