القائمة
Guidance for executing approved plans sequentially with branch checks, progress tracking, and verification.
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/kmshihab7878/claude-code-setup --skill executing-plansيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
Anti-over-engineering guardrail that activates when an AI coding agent expands scope, adds abstractions, or changes files the user did not request.
Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.
Complete n8n skill — workflow building, node configuration, JavaScript/Python code nodes, expression syntax, validation, MCP tools, credentials, administration, Docker deployment, backup/restore, internal API, and troubleshooting. Auto-triggers on any n8n task including workflow creation, node configuration, code nodes, expressions, validation errors, credential management, instance administration, n8n setup, n8n upgrade, n8n backup, and n8n API usage.
استنادا إلى تصنيف SOC المهني
عرض SKILL.md
| name | Executing Plans |
| description | Guidance for executing approved plans sequentially with branch checks, progress tracking, and verification. |
Never start on main. Execute sequentially. Verify each step. Track progress.
/plan produces a plan and user approves itBefore executing ANY plan, you MUST verify:
main or master branchfeature/<plan-topic> or fix/<plan-topic># Check current branch
git branch --show-current
# If on main/master, create and switch:
git checkout -b feature/<descriptive-name>
1. Read the plan document or recall the plan from conversation
2. Verify each task has:
- A clear deliverable (file path + behavior)
- A failing test that defines "done"
- An estimated time (2-5 minutes per task)
3. If tasks are missing tests or are too large, refine before starting
4. Confirm the plan with the user before executing
For each task in order:
1. Announce: "Starting task N/M: [description]"
2. Follow TDD: write failing test -> make it pass -> refactor
3. Run all tests (not just the new one) to check for regressions
4. Announce: "Task N/M complete. Tests: X pass, Y fail"
5. If a task fails or is blocked:
- Stop execution
- Report what failed and why
- Ask user how to proceed (skip, fix, re-plan)
1. Run the full test suite
2. Run linter/type checker if applicable
3. Show summary: tasks completed, tests passing, files changed
4. Trigger verification-before-completion skill
5. Ask user: ready to commit? ready for review? need changes?
/plan (RIPER Phase 3)test-driven-development skillverification-before-completion skillbranch-finishing skill for merge/PRIf any task in the plan takes more than 5 minutes: