executing-plans

Executes written implementation plans with review checkpoints and verification steps.

10|1|Updated Jul 29, 2026
One-click install
npx skills add https://github.com/flowing-abyss/obsidian-local-fonts --skill executing-plans-flowing-abyss
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/flowing-abyss/obsidian-local-fonts/tree/main/.ai/skills/executing-plans
Command: npx skills add https://github.com/flowing-abyss/obsidian-local-fonts --skill executing-plans-flowing-abyss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Written implementation plans often fail in execution because steps get skipped, verifications are ignored, or blockers are worked around with guesses. This Skill enforces a disciplined process for carrying out a plan in a separate session with review checkpoints. ## Core Features & Use Cases - Critical Plan Review: Loads the plan file, reviews it critically, and raises concerns with the human partner before writing any code. - Step-by-Step Task Execution: Marks each task in progress, follows bite-sized steps exactly, runs specified verifications, and marks tasks completed. - Stop-and-Ask Discipline: Halts execution on blockers, unclear instructions, or repeated verification failures instead of guessing. - Use Case: You have a multi-task implementation plan written in a previous session. Hand it to this Skill in a fresh session and it executes every task in an isolated git worktree, then hands off to a branch-finishing workflow. ## Quick Start Use the executing-plans skill to implement the plan in docs/plans/feature-auth.md and stop if anything is unclear.

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 assistant?

Provide the plan file and invoke the executing-plans skill. It reviews the plan critically, creates todos for each task, executes steps exactly as written, runs the specified verifications, and stops to ask when blocked rather than guessing.

What should I do before running a plan execution workflow?

Ensure the plan is written with bite-sized steps and explicit verifications, and set up an isolated workspace such as a git worktree. The skill checks for an isolated workspace first and never starts implementation on main or master without explicit consent.

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

Use subagent-driven development when subagents are available through tools like Claude Code, Codex CLI, Copilot CLI, or Gemini CLI. The executing-plans skill is the fallback for sessions without subagent access.

What happens when plan execution hits a blocker?

Execution stops immediately on blockers such as missing dependencies, failing tests, unclear instructions, or repeated verification failures. The skill asks the human partner for clarification instead of guessing or forcing through the problem.

Does executing plans work on the main branch?

No. The skill requires an isolated workspace, typically a git worktree, and never starts implementation on main or master without explicit user consent. After all tasks complete, it hands off to a finishing-a-development-branch workflow.