executing-plans

Executes written implementation plans task-by-task with review checkpoints and per-task commits.

3|1|Updated May 29, 2026
One-click install
npx skills add https://github.com/mambo-wang/CodingHub --skill executing-plans-mambo-wang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/mambo-wang/CodingHub/tree/main/.qoder/skills/executing-plans
Command: npx skills add https://github.com/mambo-wang/CodingHub --skill executing-plans-mambo-wang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Written implementation plans often fail in execution because steps are skipped, verification is vague, or blockers are silently worked around. This Skill enforces a disciplined workflow that loads a plan, critically reviews it, executes each task with verification, and stops to ask when anything is unclear. ## Core Features & Use Cases - Critical Plan Review: Before executing, checks for missing dependencies between steps, vague verification criteria, and unstated environment assumptions, then raises concerns with the user. - Task-by-Task Execution: Marks each task in progress, implements it, runs the specified tests, commits with a message referencing the task number, and pauses every three tasks for a direction check. - Structured Exception Handling: Distinguishes implementation bugs from broken tests and flawed plans, and stops immediately on blockers instead of guessing. - Use Case: You have a five-task plan in docs/plan.md for adding user validation to an API. The Skill reviews the plan, flags an unclear verification step, executes each task with tests and individual commits, and produces a completion report before handing off to branch finishing. ## Quick Start Use the executing-plans skill to load docs/plan.md, review it critically, and execute every task with verification and per-task commits.

Frequently Asked Questions about executing-plans

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I execute an implementation plan with an AI coding assistant?▼

Provide a written plan file with ordered tasks and explicit verification criteria. The Skill reviews the plan for dependency gaps and vague checks, then executes each task with tests and a separate commit referencing the task number.

What makes a plan ready for automated execution?▼

A ready plan has correctly ordered tasks with no missing dependencies, concrete verification steps such as a specific test command, and stated environment assumptions like runtime versions or database connections. Vague criteria like 'confirm it works' must be clarified first.

What happens when a test fails during plan execution?▼

The Skill reads the error, determines whether the cause is an implementation bug, a broken test, or a flawed plan, then fixes code or tests accordingly. If the plan itself is wrong, it stops and reports the issue with a suggested correction.

When should I use subagent-driven development instead of executing plans?▼

On platforms that support subagents, such as Claude Code or Codex, the subagent-driven-development approach is recommended because it produces higher quality results. Use this Skill when subagent support is unavailable.

Does plan execution ever commit directly to the main branch?▼

No. The Skill explicitly forbids starting implementation on main or master without explicit user consent, and it integrates with a git worktree workflow to establish an isolated workspace before execution begins.