agentleFS
Sign inStart free
neurofooneurofoo/agent-skills/wrap/SKILL.md

wrap

Skill111 starsChanged 10 months agoMITView on GitHub

WRAP decision framework countering the four villains—narrow framing, confirmation bias, short-term emotion, and overconfidence. Use for major decisions or when stuck between options.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 35 edited versions we read keep these.

  • 3

    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:

    If someone you loved faced this decision, what would you tell them?

    line 78
  2. Distinctive:

    Don't skip phases—each counters a different bias

    line 116
  3. Distinctive:

    Look for the third option beyond the obvious two

    line 118

“Common” is measured: kept by at least 6 in 10 of the 35 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

WRAP Decision Framework

Apply the complete WRAP framework to make a better decision by countering the four villains of decision-making.

Instructions

Work through all four phases sequentially. Each phase targets a specific cognitive bias that undermines good decisions.

Output Format

Decision: [What are we deciding?] Context: [Key constraints and stakes]

W: WIDEN Your Options

Counter: Narrow Framing ("Should I do X?" → "What are all my options?")

Current Framing How is the decision currently framed? (Often as "whether or not")

Expanded Options

#OptionWhy It's Worth Considering
1[option][rationale]
2[option][rationale]
3[option][rationale]
4[option][rationale]

Option-Finding Techniques

  • Vanishing options test: "If you couldn't do X, what would you do?"
  • Opportunity cost: "What else could you do with this time/money?"
  • Find someone who solved it: "Who's had this problem?"

R: REALITY-TEST Your Assumptions

Counter: Confirmation Bias (seeking evidence that confirms what we want)

Key Assumptions

AssumptionHow Would We Know If Wrong?
[assumption 1][test]
[assumption 2][test]

Consider the Opposite For each option, what would it take to be convinced it's wrong?

Ooch Is there a small experiment we can run to test this before fully committing?

OptionSmall TestWhat We'd Learn
[option][test][insight]

A: ATTAIN Distance Before Deciding

Counter: Short-term Emotion (deciding when angry, excited, or desperate)

10/10/10

Time HorizonHow will you feel about this decision?
10 minutes[how you feel now]
10 months[how you'll likely feel]
10 years[long-term perspective]

What Would I Tell My Best Friend? If someone you loved faced this decision, what would you tell them?

P: PREPARE to Be Wrong

Counter: Overconfidence ("I'm sure this will work")

Premortem Imagine this decision failed completely. What went wrong?

Failure ModeHow to Prevent/Detect
[what could fail][safeguard]

Tripwires Set a future point to reconsider:

TripwireAction If Triggered
[date or condition][what we'll do]

Decision

Recommendation Based on the WRAP analysis:

[Your decision and reasoning]

Key Safeguards

  • [Safeguard 1]
  • [Safeguard 2]

Review Date: [When to reassess]

Guidelines

  • Don't skip phases—each counters a different bias
  • "Should I?" is almost always narrow framing
  • Look for the third option beyond the obvious two
  • Ooch when you can—small tests beat big analysis
  • Set tripwires before you need them

$ARGUMENTS

Download now (ZIP)

  • Other versions41 projects use a version of this.

    Word for word · 1

    1. vansvost-arch/claude-skills★ 0100% same

    Edited · 0

    None found.

    Wrote their own version · 40

    1. UniClipboard/UniClipboard★ 1.9ksame name
    2. team-attention/stanford-cs146s-kr★ 294same name
    3. egregore-labs/egregore★ 293same name
    4. mag123c/toktrack★ 196same name
    5. lsnackerman/raw-clauding-skills★ 45same name
    6. fjwood69/mori★ 30same name
    7. YahyaLendani/opus-tuner-claude-skill★ 13same name
    8. jackjin1997/ClawForge★ 12same name
    9. ucsandman/claude-skills★ 5same name
    10. hereinthehive/kickstart★ 4same name

    30 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 start, update and 2 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.
    • AnthropicSkill

      start

      Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.

      Also in 5 projects that use this

    • AnthropicSkill

      update

      Sync tasks and refresh memory from your current activity. Use when pulling new assignments from your project tracker into TASKS.md, triaging stale or overdue tasks, filling memory gaps for unknown people or projects, or running a comprehensive scan to catch todos buried in chat and email.

      Also in 3 projects that use this

    • SentrySkill

      commit

      Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.

      Also in 4 projects that use this

    • MicrosoftSkill

      handoff

      Compact the current conversation into a handoff document for another agent to pick up.

      Also in 4 projects that use this

  • In this repository22 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