agentleFS
slowernetslowernet/dietpowers/skills/execute-plan/SKILL.md

execute-plan

Skill0 starsChanged 39 days agoMITView on GitHub

Builds an approved plan task by task, test first, against the real repository. Use when you have an approved implementation plan to build.

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use create-plan, to-spec and 6 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JetBrainsSkill

    create-plan

    Research the codebase and create an implementation plan with architecture notes, design document, and track decomposition. Use when starting a new feature or large change.

    Also in 4 projects that use this

  • GoogleSkill

    to-spec

    Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

    Also in 3 projects that use this

  • MicrosoftSkill

    grill-with-docs

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

    Also in 4 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 6 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 4 projects that use this

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 3 projects that use this

  • +2 more from google

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When you find something worth doing later that this work does not include, add it as an item to .dietpowers/trackers/open-items.md, …

    line 13
  2. Distinctive:

    Read the plan and the spec it links, in full.

    line 18
  3. Distinctive:

    Use the plan's task checkboxes as your task list, mirrored in todos.

    line 19
  4. Very specific:

    If your partner changes a requirement, invoke the dietpowers:update-spec skill, then return to step 2.

    line 23
  5. Distinctive:

    When every task is ticked, report in a few lines: what was built, the calls you made under step 5, and anything left open.

    line 24

“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Execute Plan

You build the plan's tasks in order, test first, in this session. The plan names paths, interfaces, behaviors and tests; you write the code against the real repository.

Ask your partner one question at a time, in plain text; do not use the AskUserQuestion tool, because some clients show only the tool's question and drop the text around it. Put what your partner needs to answer in the same message: the problem and why it matters, then the options, recommended first, each with a short bold label in words (never numbers or letters) and a one-line reason. End with a line naming those labels in the same order, such as Reply with **new PR**, **straight to main**, or **drop it**., and make the question the last thing in the message, after any tool use. Your partner may answer with an option, their own alternative, a question or an aside. Keep messages short: lead with the decision, then only the detail needed to answer it. Before a stretch of work that takes more than a moment, such as dispatching a reviewer, writing a spec or plan, or fixing findings, say in one line what you are about to do; after your partner answers, say what comes next before starting it.

When you find something worth doing later that this work does not include, add it as an item to .dietpowers/trackers/open-items.md, following ## Open items in ${CLAUDE_PLUGIN_ROOT}/shared/trackers.md, and say so in one line.

Commit your work on the feature branch as you go: the spec and plan may be held back, code never is. If you are on main, master or the plan's Base: branch, first ask once: "I'll create branch <name> for this work. Reply with yes or no." If your partner declines, do no code work until a branch is agreed. Nothing is pushed or merged without asking.

  1. Work on the plan's branch.
  2. Read the plan and the spec it links, in full. If either conflicts with the repository in a way that changes what gets built, raise it now, before writing code.
  3. Use the plan's task checkboxes as your task list, mirrored in todos.
  4. For each task: build it with the dietpowers:tdd skill against its Behavior and Tests, tick its checkbox, and commit. When a test fails and the cause isn't obvious, use the dietpowers:find-root-cause skill.
  5. When the repository differs from what the plan assumes, make the routine call yourself and record it under the task in the plan as a Departure: line. Stop to ask only when the difference would change an interface, a spec requirement, or another task. When a change would alter behavior the spec describes, invoke the dietpowers:update-spec skill; if the change is declined and the task cannot be built without it, stop and ask your partner how to proceed.
  6. Move from task to task without stopping to report progress or to offer to continue; put any status note in the same message as your next tool call. Stop only when nothing can move without your partner: a blocker you cannot resolve, a missing dependency, or a decision that changes the design.
  7. If your partner changes a requirement, invoke the dietpowers:update-spec skill, then return to step 2.
  8. When every task is ticked, report in a few lines: what was built, the calls you made under step 5, and anything left open.

Terminal state: ask "Continue with code review? Reply with yes or no." On yes, invoke the dietpowers:adversarial-review skill on the code. Otherwise, report what is built and what is uncommitted, and stop.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.