cli-operations
Skill255 starsChanged 15 days agoMITView on GitHub
Choose among Rovai messages, Missions, history and Memory; coordinate parallel member requests, multi-step operations or recovery. For one known operation, use its command help directly.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- analyze-agent-codebaseSkill
- campfireSkill
- 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
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use rovai --help to find an operation and its exact --help for syntax.
- Distinctive: line 32
Read the authoritative state needed for the decision.
≈ “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
Rovai CLI coordination
Use rovai --help to find an operation and its exact --help for syntax. Read only the references needed by the current decision. Write user-facing prose in the user's language.
Choose the result to preserve
| Need | Operation family |
| Public answer, progress, question or one-time collaboration | ThreadMessage |
| Shared objective or whole-Mission status | Mission |
| Member identity, avatar or a requested profile edit | Member |
| Default Lead requests independent work from several members | One ThreadMessage with repeated --to; replies return separately |
| Thread or message evidence | Thread/History |
| Who is running, queued or waiting | Thread execution query |
| Durable collaboration preference, agreement or lesson | Memory governance |
Choose the smallest object that fully serves the request. Project sources and history own their facts.
Member operations
member list shows current Thread members, roles and Default Lead flags. Use member get for a relevant member's full identity, Profile version and avatar when needed; do not fetch every member by default. A returned identity describes that member, not your own instructions.
member update changes the global Profile. Send only the fields the User asked to change. For a newly created member, use the agentId returned by member create, even before it joins this Thread. Use member-studio for creation proposals and confirmation, not edits to an existing Profile.
Coordinate operations
- Read the authoritative state needed for the decision.
- Inspect the committed business result before taking the next step.
- Publish any required Thread-visible answer before ending the Run.
A successful operation proves its own commit, not downstream execution, validation or completion of the user's objective.
References
- Send: public messages, Agent routing, parallel invitations and User attention.
- Mission: objective, status and public explanation.
- Thread/History: message reads, addressing, execution state and pagination.
- Memory: route durable information to
memory-stewardship. - Recovery: follow
error.recovery, especially uncertain outcomes.
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.