agentleFS
Sign inStart free
zpower426zpower426/pmpowers/skills/writing-plans/SKILL.md

writing-plans

Skill0 starsChanged 7 months agoMITView on GitHub

Use when you have specs or requirements for a multi-step PM task, before starting execution. Used to develop detailed plans for research, experimentation, definition, and verification.

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Analyze Spec: Ensure full understanding of the logic in docs/pmpowers/specs/.

    line 18
  2. Distinctive:

    Save Plan: Write to the temporary plan directory and execute after approval.

    line 24
  3. Distinctive:

    Every task in the plan must be linked to the North Star Metric.

    line 28

“Common” is measured: kept by at least 6 in 10 of the 169 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

Writing Plans: PM Action Planning Guide

Transform approved designs into a series of verifiable, traceable tasks.

Core Mandates

  • Don't Skip Verification: Any plan that includes "implementation" must first include "verification."
  • Atomic Tasks: Each task should have a single output (e.g., an interview outline, a metric definition).
  • User Review: You must have the user confirm the plan before starting task execution.

Checklist

  1. Analyze Spec: Ensure full understanding of the logic in docs/pmpowers/specs/.
  2. Develop Phased Tasks:
    • Phase 1: Discovery/Validation: De-risking.
    • Phase 2: Definition: Detailed logic.
    • Phase 3: Final Guard: End-to-end verification.
  3. Set Checkpoints: Pause at critical decision points to get user feedback.
  4. Save Plan: Write to the temporary plan directory and execute after approval.

Verification & Traceability

Every task in the plan must be linked to the North Star Metric. If a task cannot explain how it improves the core metric, it is waste.

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.

Reviews can't be read right now.

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.

Check your setup, free