campfire
Skill255 starsChanged 15 days agoMITView on GitHub
Run a Thread discussion with several members to compare perspectives, options or tradeoffs and produce shared notes. Applies to the host and invited contributors throughout that discussion; excludes solo work, unrelated messages and closed discussions.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- apideck-libraries/api-skillstheir own version, first seen Aug 13, 2026
- ReliOptic/campfiretheir own version, first seen Aug 4, 2026
- cukas/claudes-ai-buddiestheir own version, first seen Mar 22, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- cukas/claudes-ai-buddies★ 9same name
- apideck-libraries/api-skills★ 4same name
- ReliOptic/campfire★ 0same 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.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- analyze-agent-codebaseSkill
- cli-operationsSkill
- diagnosing-bugsSkill
- grill-duoSkill
- grill-duo-with-docsSkill
- member-studioSkill
- memory-stewardshipSkill
- review-duoSkill
- tddSkill
- worktreeSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
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
- Distinctive: line 20
Use trusted roles and request/reply relationships, not message titles.
“Common” is measured: kept by at least 6 in 10 of the 3 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.
Files
Campfire
The current Default Lead hosts independent views, at most one focused response round, then one final set of notes. Public messages make this an independent discussion, not a blind review. Use the user's language for prose and template headings.
Roles
| Current input | Action |
| User directly asks the current Default Lead to host | Follow Lead |
| Ordinary member receives a user broadcast or a call that also reaches the Lead | Follow Member; wait for a formal invitation |
| Member receives this discussion's independent-view or response request | Follow Member; return one complete result |
| Host receives an invited member's current-round reply | Follow Lead |
| Notes, late contributions or unrelated messages | Do not restart the discussion |
Use trusted roles and request/reply relationships, not message titles. One Lead may host only one unfinished Campfire per Thread. This workflow needs at least two contributors and is not for sustained two-person questioning or strict information isolation.
Discussion bounds
- Round 1: invite 2-3 members in one multi-recipient message.
- Round 2: optional, once, with 1-2 members addressing one disagreement that could change the conclusion.
- Each member returns one complete result per round. After round 2, publish the final Notes; no extra clarification round.
- User requests to stop, replace the topic, remove a member or summarize now take precedence. Late views do not reopen published notes.
Member reply contract
Include a core judgment, two main reasons, the most important risk/limit, what would change the judgment, and confidence. For Chinese, aim for 200-250 characters, at most 300; use comparable brevity in other languages.
Return the full result to the requester once. Omit repeated background, other members' views, acknowledgements and progress. Contributors do not recruit others, summarize the whole discussion or start another round.
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.