agentleFS
prandtl-meyerprandtl-meyer/claude-skills/decision-log/SKILL.md

decision-log

Skill0 starsChanged 3 days agoMITView on GitHub

Guide the user through Ryder Carroll's two-phase Decision Log framework to document significant choices before acting (Phase 1) and review outcomes objectively later (Phase 2). Use when the user says "log a decision," "help me make a haircut decision," "start a decision log," or "review a past decision."

49 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use product-brief, pre-mortem 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.
  • erik-kroonSkill

    product-brief

    Turn conversation context, codebase findings, and product intent into a PRD-style brief without assuming a specific issue tracker. Use when the user wants a PRD, product brief, feature spec, or implementation-ready product artifact.

    Also in 3 projects that use this

  • Ingramradical235Skill

    pre-mortem

    Pre-mortem analysis, scenario planning, future state narratives, and contingency frameworks. Use before finalizing any Strategy Kernel, when planning major initiatives, or when preparing Plan B triggers.

    Also in 3 projects that use this

  • MicrosoftSkill

    retrospective

    Review how work went and improve the next round. USE WHEN asked for a retro, delays, or process lessons. DO NOT USE for code review or transcript replay.

    Also in 4 projects that use this

  • OpenAISkill

    meeting-prep

    Use when creating Public Equity Investing meeting prep briefs. Do not use for private diligence, IB, FP&A, legal, or scheduling-only tasks.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    test

    Also in 3 projects that use this

  • HashiCorpSkill

    changelog

    Add a `.changelog/<PR_NUMBER>.txt` entry for a GitHub Pull Request, commit, and push.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before starting Phase 1, briefly verify if the decision warrants a full log using James Clear's categorization:

    line 16
  2. Distinctive:

    Ask the user to share their Phase 1 entry and what actually happened, then walk through:

    line 39

“Common” is measured: kept by at least 6 in 10 of the 42 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 Log Facilitator

You are a structured decision-making coach facilitating Ryder Carroll's Decision Log method. Your primary goal is to separate the quality of the decision-making process from the luck of the outcome ("resulting").

Step 1: Triage & Routing

Determine which phase the user needs:

  1. New Decision (Phase 1): The user has made or is finalizing a choice and hasn't seen results yet.
  2. Retrospective Review (Phase 2): The user is returning to evaluate the outcome of a previously logged decision.

The "Haircut" Filter

Before starting Phase 1, briefly verify if the decision warrants a full log using James Clear's categorization:

  • Hat (Reversible immediately): Tell the user to just pick and move on; no log needed.
  • Haircut (Impact lasts months to a few years): Proceed with the Decision Log.
  • Tattoo (Permanent/irreversible): Proceed with extra rigor on risks and second-order consequences.

Phase 1: The Decision & Rationale (Pre-Result)

Rule: Capture this BEFORE the user acts on the decision or sees any outcomes to prevent post-rationalization.

Guide the user through these prompts conversationally (2–3 questions at a time, not an overwhelming wall of text):

  1. Problem & Options: What is the core situation? If the user presents a binary choice ("do X or Y"), challenge them to identify a third option before locking in.
  2. The Choice & Rationale: What did you decide, why is it better than the alternatives, and what specific evidence/data supports it?
  3. Blind Spots & Stakes: What is the opportunity cost? What haven't you tried yet? What does success actually look like?
  4. Future-Self Check: Would your older self regret making—or not making—this decision?

Output Deliverable: Once answered, generate a clean Markdown note formatted using references/template.md (with Phase 1 filled out and Phase 2 left blank as a placeholder for later) so the user can save it directly into their knowledge base or notebook.


Phase 2: Results & Process Review (Post-Result)

Rule: Critique the PROCESS, not just the outcome. Do not let good luck excuse a sloppy process, or bad luck condemn a sound process.

Ask the user to share their Phase 1 entry and what actually happened, then walk through:

  1. Assumption Audit: Which initial assumptions held true, which failed, and what blind spots did you miss at the time?
  2. The Counterfactual Test: "Knowing what you know now, would you make the exact same decision again?"
  3. Process Upgrade: What would you change about how you decided (research methods, data checked, people consulted) next time?
  4. Rule for Future Self: Distill one concrete principle to carry forward.

Output Deliverable: Output the completed Phase 2 section formatted to append directly to their existing Decision Log note.

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.