agentleFS
Sach1ngSach1ng/PM-operating-OS/skills/decision-logger/SKILL.md

decision-logger

Skill3 starsChanged 18 days agoMITView on GitHub

Capture durable product decision records — choice, evidence, rejected alternatives, boundary, owner, expiry. Use after PRD calls, scope changes, launch/kill, autonomy changes, or when asked to log a decision.

5 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use andreessen, business-investment-advisor and 10 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.
  • Hussain-ElfalahSkill

    andreessen

    Also in 4 projects that use this

  • Hussain-ElfalahSkill

    business-investment-advisor

    Also in 4 projects that use this

  • csiddhant796-blipSkill

    karpathy-coder

    Use when writing, reviewing, or committing code to enforce Karpathy's 4 coding principles — surface assumptions before coding, keep it simple, make surgical changes, define verifiable goals. Triggers on "review my diff", "check complexity", "am I overcomplicating this", "karpathy check", "before I commit", or any code quality concern where the LLM might be overcoding.

    Also in 4 projects that use this

  • csiddhant796-blipSkill

    self-eval

    Honestly evaluate AI work quality using a two-axis scoring system. Use after completing a task, code review, or work session to get an unbiased assessment. Detects score inflation, forces devil's advocate reasoning, and persists scores across sessions.

    Also in 4 projects that use this

  • +8 more from Hussain-Elfalah

The file

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 5 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. Distinctive:

    Write a record only when a future person or agent would make a worse call without it.

    line 8
  2. Distinctive:

    Do not log status, standup, or reversible trivia.

    line 19
  3. Very specific:

    If the decision is product-level, also add a one-line row to knowledge/products/<product>/brief.md Key Decisions.

    line 67

“Common” is measured: kept by at least 6 in 10 of the 5 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

Decision Logger

Write a record only when a future person or agent would make a worse call without it. This is judgment, not meeting minutes.

When to use

  • PRD approved or killed
  • Scope, ICP, or pricing call
  • Launch / iterate / kill
  • Autonomy change on an AI surface (alone / confirm / forbidden)
  • Eval bar that gates a ship
  • "Log this decision" / "why did we decide"

Do not log status, standup, or reversible trivia.

Six fields

  1. Decision — one sentence
  2. Evidence — the signal that carried the weight, and what was missing
  3. Rejected — one or two credible alternatives and why they lost (stops agents re-proposing them)
  4. Boundary — what the product, agent, or team must not decide alone
  5. Owner and next test — who watches; smallest evidence that would change the call
  6. Expiry — date, metric, or event that forces a revisit

Also capture date, type, and tags for retrieval.

Write to

memory/decisions/YYYY-MM-DD_short-slug.md

# [Decision title]

**Date:** YYYY-MM-DD
**Type:** [PRD | Scope | Launch/Kill | Autonomy | Prioritization | Other]
**Tags:** [product, pillar, metric]

## Decision
[1 sentence]

## Evidence
- [What carried the weight]
- **Missing:** [what we still don't know]

## Alternatives rejected
1. **[Option]** — [why it lost]
2. **[Option]** — [why it lost]

## Boundary
[What must not be decided autonomously]

## Owner and next test
- **Owner:**
- **Next test:**

## Expiry
[Date, metric threshold, or event]

Show the draft. Confirm before saving. Never overwrite an existing record — if the call changed, write a new one and point at the old.

If the decision is product-level, also add a one-line row to knowledge/products/<product>/brief.md Key Decisions.

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.