القائمة
Use when a coding task must be completed against explicit acceptance criteria with minimal user re-intervention across implementation, review feedback, deployment, and runtime verification.
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
Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.
This skill should be used when the user asks to "attack Active Directory", "exploit AD", "Kerberoasting", "DCSync", "pass-the-hash", "BloodHound enumeration", "Golden Ticket", ...
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines,...
This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.
| name | closed-loop-delivery |
| description | Use when a coding task must be completed against explicit acceptance criteria with minimal user re-intervention across implementation, review feedback, deployment, and runtime verification. |
| risk | safe |
| source | community |
| date_added | 2026-03-12 |
Treat each task as incomplete until acceptance criteria are verified in evidence, not until code is merely changed.
Core rule: deliver against DoD (Definition of Done), not against code diff size.
Use this skill when:
Do not use this skill for:
Before execution, define these once:
dev by default)2)If acceptance criteria are missing, request them once. If user does not provide, propose a concrete default and proceed.
Before execution, prefer using create-issue-gate.
ready and execution gate is allowed, continue.draft, do not execute implementation/deploy/review loops.Define DoD
Implement minimal change
Verify locally
Review loop
Dev deploy + runtime verification
dev when runtime behavior matters.Completion decision
Avoid noisy short polling by default. Use batched windows:
3m, collect delta comments/reviews6m, collect delta again10m, collect all remaining visible comments/reviewsAt each round:
10m round, stop waiting and proceed with all comments visible at that pointIf CI is still running, align polling to check completion boundaries instead of fixed rapid polling.
Require explicit user confirmation for:
Stop and escalate with a concise blocker report when:
2 default)Escalation report must include:
When claiming completion, always include:
Do not claim success without evidence.