executing-plans
Execute implementation plans with batch processing and review checkpoints. Use when given a plan document.
Best use case
executing-plans is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Execute implementation plans with batch processing and review checkpoints. Use when given a plan document.
Teams using executing-plans should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/executing-plans-dmjgilbert/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How executing-plans Compares
| Feature / Agent | executing-plans | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Execute implementation plans with batch processing and review checkpoints. Use when given a plan document.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Executing Plans Execute implementation plans systematically with quality gates between batches. ## When to Use - When given a plan document to implement - After writing-plans skill produces a plan - For batch execution with human checkpoints ## The Five-Step Process ### Step 1: Load and Review Plan 1. Read the plan document carefully 2. Identify potential issues or ambiguities 3. Raise concerns with user **before** beginning work 4. Create TodoWrite with all tasks if plan seems sound **If issues found:** Stop and clarify before proceeding ### Step 2: Execute Batch Default batch size: **3 tasks** For each task in batch: 1. Update status to `in_progress` 2. Execute each step as written 3. Run specified verifications 4. Mark as `completed` only when verified ### Step 3: Report After completing a batch: ```markdown ## Batch Complete **Tasks Completed:** [List] **Verifications:** - Task 1: [Pass/Fail] - [Details] - Task 2: [Pass/Fail] - [Details] - Task 3: [Pass/Fail] - [Details] **Issues Found:** [If any] Ready for feedback. ``` ### Step 4: Continue 1. Incorporate any requested changes 2. Execute next batch 3. Repeat cycle ### Step 5: Complete Development After all tasks finished and verified: 1. Run full test suite 2. Announce completion 3. Transition to finishing workflow (merge/PR decision) ## Critical Rules ### STOP Immediately When: - Blockers (missing dependencies, failed tests) - Plan gaps preventing progress - Unclear instructions - Repeated verification failures (2+ on same task) **When blocked:** Ask for clarification, don't force through. ### Return to Step 1 When: - User updates the plan - Approach needs fundamental revision - Architecture issues discovered ### Never: - Skip verifications - Force through blockers - Batch completions (mark done one at a time) - Proceed with unresolved critical issues ## Batch Size Guidelines | Scenario | Batch Size | | ----------------- | ------------ | | Simple tasks | 3-5 | | Complex tasks | 1-2 | | High-risk changes | 1 | | User preference | As specified | ## Integration with Other Skills - **test-driven-development:** Each task follows TDD - **systematic-debugging:** If tests fail, use debugging skill - **code-review:** Request review after significant batches
Related Skills
plans-management
Manages Plans.md tasks and marker operations. Use when user mentions タスクを追加, Plans.md更新, 完了マーク, タスク状態変更, add task, update plans, mark complete. Do NOT load for: 実装作業, レビュー, Plans.md以外のファイル操作.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
kitt-create-plans
Create hierarchical project plans optimized for solo agentic development. Use when planning projects, phases, or tasks that the AI agent will execute. Produces agent-executable plans with verification criteria, not enterprise documentation. Handles briefs, roadmaps, phase plans, and context handoffs.
airtight-plans
Write structured multi-step implementation plans in markdown format. Plans use numbered steps with clear titles and detailed instructions. Use when asked to create an implementation plan, development roadmap, or multi-step task breakdown.
treatment-plans
Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.
superteam-writing-plans
Create structured implementation plans with machine-parseable task blocks
libgraphql-plans
Track, organize, and maintain plans.md files and code TODOs for the libgraphql project. Use when the user asks to update plans, sync TODOs, mark tasks complete, add new tasks, identify high-impact work, or asks what's left to do in the libgraphql codebase. Triggers include phrases like "update plans", "sync TODOs", "what's left to do", "mark X as done", "track a new task", "highest-impact work", or references to plans.md files.
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
reviewing-documentation
Use when reviewing documentation quality, auditing README or CLAUDE.md files, or standardizing AI instruction files.
review-docs
Review documentation (README.md and CLAUDE.md) for quality, completeness, and consistency. Use when asked to review docs, check documentation, validate README files, or audit CLAUDE.md coverage.
review-changelog
Review and complete new changelog entries after automated PR creation. Use when there's a new changelog PR with entries that have placeholder URLs or empty fields that need review. Triggers on phrases like "review changelog", "complete changelog entries", "fix changelog PR", or when user mentions a PR with changelog updates.
research-documentation
Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages. Trigger on "노션 검색", "조사해줘", "리서치 정리". For meeting prep use meeting-intelligence; for saving knowledge use knowledge-capture; for spec breakdown use spec-to-implementation.