القائمة
Use when verification, review, or manual testing identifies concrete gaps in otherwise planned or completed work.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | gap-closure |
| description | Use when verification, review, or manual testing identifies concrete gaps in otherwise planned or completed work. |
Announce: "I'm using the gap-closure skill to create targeted fixes for the identified gaps."
Close only evidenced gaps; do not restart planning or turn repair into enhancement work.
Activate for goal-backward truth/artifact/wiring gaps, P1/P2 review findings, broken integration wiring, failing verification, or missing behavior exposed by manual testing.
Do not use when requirements or architecture are genuinely undecided; return to the appropriate planning/decision workflow instead.
Gaps only: every fix task must trace to a specific source finding and include files plus a proving check.
test-driven-development and focused edits.An enhancement is not gap closure. Finish the bounded closure before routing improvements separately.
| Thought | Required response |
|---|---|
| "While I'm here, improve..." | Record separately; fix only sourced gaps. |
| "Rewrite the component" | Target the root cause with the smallest repair. |
| "Start planning from scratch" | Preserve verified work and plan only gaps. |
| "The new test passes, so done" | Re-run the original verification and regressions. |
| "One more closure loop" beyond the cap | Stop and escalate remaining evidence. |
verification-before-completion, code-review, integration-checking, or manual evidence.executing-plans for fix tasks and test-driven-development for behavior.systematic-debugging when root cause is not yet established.verification-before-completion and state-management after repair.Use when following the Super Compound BRD -> PRD -> FSD -> GOAL -> IMPLEMENTATION -> VERIFICATION delivery path, artifact traceability, FSD authority, optional ADR handling, zero context bloat issue slicing, or OPEN-* stop conditions.
Use when an approved FSD goal or lightweight issue pointer is ready for implementation.
Use when multi-component work needs cross-component verification of API contracts, data flow, events, auth, config, UI, background jobs, or tests.
Use when /sc-plan needs FSD GOAL-* packets turned into lightweight issue pointers, local Markdown Kanban boards, blocker DAGs, or multi-agent task contracts.
Use when a plan or issue board has 2+ independent execution streams whose time saving exceeds coordination overhead. Dispatches agents in isolated git worktrees only after required delivery gates pass.
Use when an FSD and goal issue board need requirement coverage, goal quality, dependency DAG, sizing, and verification validated before execution.