deliberate
Skill0 starsChanged 14 days agoMITView on GitHub
Deliberate a consequential question with authorized peers through independent positions, challenge, and synthesis.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- taipt1504/claudehuttheir own version, first seen Nov 1, 2026
- JosefGisis/skillstheir own version, first seen Oct 20, 2026
- Nafjan/summontheir own version, first seen Sep 24, 2026
- warrenwhipple/decision-flowtheir own version, first seen Jul 17, 2026
- samuelfarkas/skillstheir own version, first seen Jul 13, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- Nafjan/summon★ 4same name
- samuelfarkas/skills★ 4same name
- taipt1504/claudehut★ 2same name
- JosefGisis/skills★ 1same name
- warrenwhipple/decision-flow★ 1same name
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.
The file
Files
Deliberate
Define the question, relevant evidence, established constraints, what is open, and the stopping condition. Use the participants and models the user authorized. Each participant is a reasoning peer; give useful context without assigning a predetermined conclusion or a permanent advocate role.
Obtain initial positions, then exchange the substantive arguments. Challenge assumptions and proposed tradeoffs with evidence. The principal contributes its own position and revises it when warranted; collecting separate reports alone is not deliberation.
Circulate the provisional synthesis for correction. State what converged, what changed, and what remains disputed or unknown. Silence is not agreement. Stop when the material question is resolved or the agreed round/effort limit is reached; do not fabricate consensus to satisfy an acceptance target.
Choose the execution mechanism using the orchestration skill: use native agent tools whenever they meet the assignment. A panel using several compatible models still uses native execution. Use Harness execution and message tools only for an eligible managed assignment. Keep context bounded to the question and relevant evidence, and preserve the shared execution limits. An explicitly requested expensive model remains that model; report unavailability instead of silently choosing another.
The output is a concise decision synthesis with reasons, relevant evidence, and unresolved tradeoffs. Persist useful conclusions through work or memory tools when appropriate; do not archive private reasoning traces. Deliberation does not itself authorize implementation or publication beyond the user's request.
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.

