Help us improve
Share bugs, ideas, or general feedback.
From development-planning
Executes implementation plans step-by-step from plan files using file edits, git, and subagents. Supports single PR or Graphite stack modes. Activates on 'execute the plan' or similar.
npx claudepluginhub uniswap/ai-toolkit --plugin development-planningHow this skill is triggered — by the user, by Claude, or both
Slash command
/development-planning:execute-planopusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Execute implementation plans by reading the plan file and implementing each step directly with progress tracking. Supports both **single PR** (default) and **Graphite PR stack** execution modes.
Executes implementation plans by splitting into ≤5 steps: implement, test, code review per step via subagents. Ensures clean, extensible, high-quality code.
Executes approved implementation plans with checkpoint validation, progress tracking, and stakes-based enforcement. Locates plans, verifies approval, and runs verification criteria before proceeding.
Executes approved technical plans phase by phase using background sub-agents, verification checkpoints, and configurable autonomy modes. Useful for structured implementation with user oversight.
Share bugs, ideas, or general feedback.
Execute implementation plans by reading the plan file and implementing each step directly with progress tracking. Supports both single PR (default) and Graphite PR stack execution modes.
Activate stack execution mode when user says:
Implements all steps, commits at logical points, creates one PR at the end.
Creates a separate PR for each logical chunk during execution. Use when:
When executing in stack mode, follow this workflow:
stack_plan:
pr_count: N
prs:
- pr: 1
branch: '<username>/<feature>-types'
title: 'feat(<scope>): add types and interfaces'
steps: [1, 2]
- pr: 2
branch: '<username>/<feature>-impl'
title: 'feat(<scope>): implement core functionality'
steps: [3, 4]
depends_on: [1]
For each PR in the stack:
# 1. Create stack entry (timeout: 180000)
gt create -m "<type>(<scope>): <description>" --no-verify
# 2. Implement assigned steps
# ... make changes, stage files ...
# 3. Validate (use your project's linting/typecheck commands)
# 4. Finalize PR (timeout: 180000)
git add <specific-files>
CLAUDE_CODE=1 gt modify --no-verify
gt submit
# Submit entire stack when complete (timeout: 180000)
gt submit --stack
Good PR boundaries:
| PR | Content | Rationale |
|---|---|---|
| 1 | Types/Interfaces | Foundation with no dependencies |
| 2 | Core Implementation | Uses types, provides functionality |
| 3 | Integration/Glue | Connects to app |
| 4 | Tests | Validates implementation |
For comprehensive stack execution guidance, see graphite-stack-execution.md.
Always ask user before committing:
After execution, provide summary:
plan_executed: [path]
steps_completed: [N]
steps_failed: [N]
files_modified: [list]
files_created: [list]
commits_created: [list]
status: completed | partial | failed
next_steps: [remaining work]
After implementation, ask:
"Implementation complete. Would you like me to:
- Generate tests for the new code?
- Update documentation?
- Create a pull request?
- All of the above?"
After stack execution, provide summary:
"Stack execution complete. Created N PRs:
- PR #1:
feat(scope): description- [URL]- PR #2:
feat(scope): description- [URL] ...All PRs are linked in a Graphite stack. Reviewers can review bottom-up. Would you like me to generate tests or documentation for any of the PRs?"
This is Step 4 of the implementation workflow:
After execution completes, the pr-creator-agent handles step 5 (PR creation) within this same plugin.