agent planning skill risk: low
Implementation Plan Execution Workflow
Instructs the model to load a written implementation plan, review it critically for questions or concerns, execute its tasks sequentially while marking progress and running specifi…
SKILL 1 file
SKILL.md
--- name: executing-plans description: "Use when you have a written implementation plan to execute in a separate session with review checkpoints" --- # Executing Plans ## Overview Load plan, review critically, execute all tasks, report when complete. **Announce at start:** "I'm using the executing-plans skill to implement this plan." **Note:** Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use superpowers:subagent-driven-development instead of this skill. ## The Process ### Step 1: Load and Review Plan 1. Read plan file 2. Review critically - identify any questions or concerns about the plan 3. If concerns: Raise them with your human partner before starting 4. If no concerns: Create TodoWrite and proceed ### Step 2: Execute Tasks For each task: 1. Mark as in_progress 2. Follow each step exactly (plan has bite-sized steps) 3. Run verifications as specified 4. Mark as completed ### Step 3: Complete Development After all tasks complete and verified: - Announce: "I'm using the finishing-a-development-branch skill to complete this work." - **REQUIRED SUB-SKILL:** Use superpowers:finishing-a-development-branch - Follow that skill to verify tests, present options, execute choice ## When to Stop and Ask for Help **STOP executing immediately when:** - Hit a blocker (missing dependency, test fails, instruction unclear) - Plan has critical gaps preventing starting - You don't understand an instruction - Verification fails repeatedly **Ask for clarification rather than guessing.** ## When to Revisit Earlier Steps **Return to Review (Step 1) when:** - Partner updates the plan based on your feedback - Fundamental approach needs rethinking **Don't force through blockers** - stop and ask. ## Remember - Review plan critically first - Follow plan steps exactly - Don't skip verifications - Reference skills when plan says to - Stop when blocked, don't guess - Never start implementation on main/master branch without explicit user consent ## Integration **Required workflow skills:** - **superpowers:using-git-worktrees** - Ensures isolated workspace (creates one or verifies existing) - **superpowers:writing-plans** - Creates the plan this skill executes - **superpowers:finishing-a-development-branch** - Complete development after all tasks
REQUIRED CONTEXT
- plan file
ROLES & RULES
- Announce at start that you are using the executing-plans skill
- Tell your human partner that Superpowers works much better with access to subagents
- Read plan file
- Review critically and identify any questions or concerns about the plan
- If concerns, raise them with your human partner before starting
- If no concerns, create TodoWrite and proceed
- Mark each task as in_progress
- Follow each step exactly
- Run verifications as specified
- Mark each task as completed
- Announce use of finishing-a-development-branch skill after all tasks complete
- Use superpowers:finishing-a-development-branch sub-skill
- Stop executing immediately when you hit a blocker
- Ask for clarification rather than guessing
- Return to Review when partner updates the plan
- Review plan critically first
- Follow plan steps exactly
- Do not skip verifications
- Reference skills when plan says to
- Stop when blocked, do not guess
- Never start implementation on main/master branch without explicit user consent
EXPECTED OUTPUT
- Format
- plain_text
- Constraints
- announce skill usage at start
- create TodoWrite before executing
- mark tasks in_progress then completed
- announce finishing-a-development-branch sub-skill at end
- stop and ask when blocked
SUCCESS CRITERIA
- Load plan, review critically, execute all tasks, report when complete
- Follow each step exactly
- Run verifications as specified
- Verify tests, present options, execute choice
CAVEATS
- Dependencies
- plan file
- superpowers:using-git-worktrees
- superpowers:writing-plans
- superpowers:finishing-a-development-branch
QUALITY
- OVERALL
- 0.83
- CLARITY
- 0.90
- SPECIFICITY
- 0.85
- REUSABILITY
- 0.80
- COMPLETENESS
- 0.85
IMPROVEMENT SUGGESTIONS
- Add a placeholder or parameter for the plan file path to make invocation explicit.
- Define success criteria for 'verified' tasks more explicitly.
USAGE
Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.
MORE FOR AGENT
- Consciousness Council Multi-Perspective Deliberationagentplanning
- Multi-Agent Architecture Patterns Guideagentplanning
- TDD Implementation Plan Writeragentplanning
- A/B Test Design and Analysis Guideagentplanning
- Autonomous EDA Design Space Exploreragentplanning
- Autonomous Design Space Exploration Loopagentplanning
- Website Architecture Planning Expertagentplanning
- BDI RDF Mental State Modeleragentplanning
- Collaborative Software Design Brainstorming Processagentplanning
- WWA Product Backlog Item Creatoragentplanning
- Structured Development Plan Outlineragentplanning
- ML Ablation Study Planneragentplanning
- Ansoff Matrix Growth Strategy Analyzeragentplanning
- Team OKR Brainstorming Product Leaderagentplanning
- Context Engineering Fundamentalsagentplanning
- Product Monetization Strategy Developeragentplanning
- LLM Project Pipeline Development Methodologyagentplanning
- What-If Scenario Analysis Oracleagentplanning
- Business Model Canvas Generatoragentplanning
- Concise Coding Task Planneragentplanning
- Domain Model Plan Grilling Intervieweragentplanning
- Latent Briefing KV Cache Compactionagentplanning
- Product Roadmap Outcome Transformeragentplanning
- Puzzle Activity Planner with Generator Linksagentplanning
- Osterwalder Business Model Canvas Architectagentplanning