Agent skill
executing-plans
Execute implementation plans with batch processing and review checkpoints. Use when given a plan document.
Install this agent skill to your Project
npx add-skill https://github.com/aiskillstore/marketplace/tree/main/skills/dmjgilbert/executing-plans
SKILL.md
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
- Read the plan document carefully
- Identify potential issues or ambiguities
- Raise concerns with user before beginning work
- 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:
- Update status to
in_progress - Execute each step as written
- Run specified verifications
- Mark as
completedonly when verified
Step 3: Report
After completing a batch:
## 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
- Incorporate any requested changes
- Execute next batch
- Repeat cycle
Step 5: Complete Development
After all tasks finished and verified:
- Run full test suite
- Announce completion
- 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
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
perigon-backend
Perigon ASP.NET Core + EF Core + Aspire conventions
perigon-agent
Pointers for Copilot/agents to apply Perigon conventions
perigon-angular
Angular 21+ standalone/Material/signal conventions for Perigon WebApp
fastapi-mastery
Comprehensive FastAPI development skill covering REST API creation, routing, request/response handling, validation, authentication, database integration, middleware, and deployment. Use when working with FastAPI projects, building APIs, implementing CRUD operations, setting up authentication/authorization, integrating databases (SQL/NoSQL), adding middleware, handling WebSockets, or deploying FastAPI applications. Triggered by requests involving .py files with FastAPI code, API endpoint creation, Pydantic models, or FastAPI-specific features.
context7-efficient
Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.
browser-use
Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction.
Didn't find tool you were looking for?