agentleFS
Sign inStart free
JaimeGBAJaimeGBA/Ion/.claude/skills/decide/SKILL.md

decide

Skill9 starsChanged 7 months agoMITView on GitHub

Structured decision-making — lay out options, analyze tradeoffs, recommend, and document

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read relevant knowledge from the knowledge base for context

    line 13
  2. Distinctive:

    Time horizon: When does this pay off? What's the opportunity cost of waiting?

    line 23
  3. Distinctive:

    When your partner reaches a decision:

    line 33
  4. Very specific:

    Create a decision record at knowledge/decisions/YYYY-MM-DD-decision-title.md:

    line 35
  5. Distinctive:

    Update any knowledge files affected by the decision

    line 65
  6. Very specific:

    Add action items to ops/action-items.md

    line 66
  7. Very specific:

    Update ion/state.md if the decision is significant

    line 67

“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

Decide — Decision Framework

Help your partner make a structured decision and document it in the knowledge base.

Process

  1. Clarify the decision to be made — restate it as a clear question
  2. Read relevant knowledge from the knowledge base for context
  3. Identify the options (from the partner + suggest additional ones they may not have considered)
  4. Analyze each option

Analysis Framework

For each option, evaluate:

  • Alignment: How well does this serve the partner's stated mission, vision, or current priorities?
  • Feasibility: Can it be executed with current resources and constraints?
  • Reversibility: How hard is it to undo if wrong? Prefer reversible decisions, especially when uncertainty is high.
  • Time horizon: When does this pay off? What's the opportunity cost of waiting?
  • Risk: What could go wrong? What's the worst-case downside?
  • Opportunity cost: What is given up by choosing this over the alternatives?

Recommendation

Be opinionated. Your partner wants honest assessment, not a balanced spreadsheet. State which option you'd choose and why. If the decision is close, say so — but still pick one.

After Decision

When your partner reaches a decision:

  1. Create a decision record at knowledge/decisions/YYYY-MM-DD-decision-title.md:
    ---
title: "Decision: [clear title]"
description: "[one-line summary of what was decided and why]"
last_updated: YYYY-MM-DD
updated_by: [name]
status: active
---

# Decision: [Title]

## Context
[Why this decision needed to be made]

## Options Considered
[Each option with pros/cons]

## Decision
[What was decided]

## Reasoning
[Why this option was chosen]

## Action Items
[What needs to happen next]

## Participants
[Who was involved in making this decision]
  2. Update any knowledge files affected by the decision
  3. Add action items to ops/action-items.md
  4. Update ion/state.md if the decision is significant

Rules

  • Decision files are append-only. Once written, never edit. If a decision is reversed later, write a new decision record that supersedes the old one — don't rewrite history.

Download now (ZIP)

  • Other versions43 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 43

    1. superset-sh/superset★ 16ksame name
    2. ParadevAI/Paradev★ 16ksame name
    3. coreyhaines31/makerskills★ 873same name
    4. me2resh/apexyard★ 532same name
    5. menkesu/awesome-pm-skills★ 441same name
    6. BlockRunAI/blockrun-mcp★ 391same name
    7. kv0906/pm-kit★ 138same name
    8. Abilityai/cornelius★ 109same name
    9. me2resh/agent-decision-record★ 48same name
    10. seandavi/lifeos-template★ 41same name

    33 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use experiment, map and 7 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.
    • SethGammonSkill

      experiment

      Automated optimization loop with scalar fitness function. Proposes changes in isolated worktrees, measures with a metric command, keeps improvements, discards failures. Supports convergence detection and diminishing returns.

      Also in 3 projects that use this

    • AWSSkill

      map

      Map verified service capabilities against customer-provided control framework and threat model. Produces mapping-results.json, controls-catalog.md, and framework-mapping.md. Supports pluggable frameworks: CCMv4, NIST 800-53, CIS Benchmarks, ISO 27001, etc. Split into 4 focused sub-skills for better accuracy; this skill orchestrates them.

      Also in 3 projects that use this

    • ibahgatSkill

      loop

      Enforce repeated exec-verify-fix cycles until acceptance criteria pass or blockers are explicit.

      Also in 3 projects that use this

    • AnthropicSkill

      debug

      Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

      Also in 4 projects that use this

    • genomewalkerSkill

      learn

      Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

      Also in 4 projects that use this

    • AnthropicSkill

      status

      Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

      Also in 4 projects that use this

  • In this repository11 other files it gives its agents.

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