decision-reversibility
Skill114 starsChanged 10 months agoMITView on GitHub
Classify decisions as Hat/Haircut/Tattoo by reversibility. Use to calibrate how much analysis a decision deserves.
In this repository48 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- assumption-mappingSkill
- assumption-prioritizationSkill
- atlassian-jira-syncSkill
- backend-designSkill
- brainstormingSkill
- challenging-stakeholder-questionsSkill
- competitor-analysisSkill
- crux-diagnosisSkill
- davciSkill
- decision-journalSkill
- difficult-conversationsSkill
- executive-update-reviewSkill
- experiment-designSkill
- frontend-designSkill
- google-calendar-schedule-checkSkill
- granola-meeting-syncSkill
- hidden-agendasSkill
- hypothesis-designSkill
- ideas-summarySkill
- influence-strategiesSkill
- interview-cleanupSkill
- jtbd-clusteringSkill
- jtbd-extractionSkill
- limit-based-strategySkill
- linear-issue-syncSkill
- llm-coding-guardrailsSkill
- mece-analysisSkill
- meeting-power-dynamicsSkill
- message-framing-commsSkill
- opportunity-solution-treeSkill
- ost-intakeSkill
- ost-target-selectionSkill
- power-mapSkill
- prd-writingSkill
- problem-structuringSkill
- root-cause-analysisSkill
- signal-identificationSkill
- slack-message-checkSkill
- spec-writingSkill
- stakeholder-risk-reviewSkill
- structured-product-strategySkill
- systematic-debuggingSkill
- tddSkill
- value-chain-mappingSkill
- verificationSkill
- writing-plansSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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
- Distinctive: line 12
Before making a decision, to determine how much deliberation is warranted.
- Distinctive: line 58
Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Decision Reversibility Classification
Classify decisions by reversibility to calibrate how much analysis they deserve.
When to Use
Before making a decision, to determine how much deliberation is warranted.
The Framework
Classify decisions into three categories:
| Type | Reversibility | Analysis Needed |
| Hat | Easily reversible, minimal consequences | Decide quickly |
| Haircut | Reversible with effort/time | Moderate analysis |
| Tattoo | Largely irreversible, lasting impact | Deep analysis |
Analysis Criteria
Consider these factors:
- Immediate consequences - What happens right away?
- Long-term effects - On you, team, users, company?
- Reversal effort - Time, money, resources to undo?
- Permanent changes - What can't be undone?
Classification Guide
Hat (decide fast):
- Can undo with minimal cost
- No lasting consequences
- Examples: Meeting time, doc format, tool choice
Haircut (moderate deliberation):
- Reversible but requires time/effort
- Temporary discomfort if wrong
- Examples: Feature scope, team process, pricing test
Tattoo (deliberate carefully):
- Largely permanent or very costly to reverse
- Long-lasting consequences
- Examples: Architecture choices, team structure, market positioning
Output
- Decision classification (Hat/Haircut/Tattoo)
- Key factors driving the classification
- Recommended level of analysis
When Not to Use
Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.
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
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.