private-team-review
Skill9 starsChanged 39 days agoMITView on GitHub
Consult another teammate privately, resolve disagreements and deliver one consolidated answer to the user.
In this repository13 other files it gives its agents.
- site/llms-full.txtllms.txt
- site/llms.txtllms.txt
- checked-spreadsheet-analysisSkill
- document-to-action-itemsSkill
- gmail-browser-draftSkill
- google-calendar-browser-tasksSkill
- google-drive-browser-tasksSkill
- grounded-researchSkill
- meeting-action-itemsSkill
- systematic-debuggingSkill
- todoist-browser-tasksSkill
- weekly-review-planningSkill
- use-mac-appsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 9
Ask a bounded question with message_teammate, including the user's outcome, relevant context, scope and what evidence is needed.
- Very specific: line 10
After requesting a reply, wait for Sidemates' consultation continuation.
- Distinctive: line 13
If a consultation fails or reaches its limit, deliver the supported portion and describe the unresolved point.
- Distinctive: line 15
Use task_verify for saved deliverables.
≈ “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
One answer, informed by the team
- Decide whether another perspective will materially improve this task. Do not spend extra model calls on a simple answer.
- Ask a bounded question with message_teammate, including the user's outcome, relevant context, scope and what evidence is needed. Request a reply only when needed; do not share credentials or unrelated private material.
- After requesting a reply, wait for Sidemates' consultation continuation. Do not give a premature final answer or say a consultation completed before its result arrives.
- Evaluate the returned evidence, resolve disagreements and verify the deliverable. A teammate's assertion is not proof of an action or a saved file.
- Present one consolidated response from the lead teammate. Mention a useful difference of opinion only when relevant. Do not paste internal message IDs, tool payloads or parallel status chatter.
- If a consultation fails or reaches its limit, deliver the supported portion and describe the unresolved point. Do not create recursive handoffs or ping-pong conversations.
Use task_verify for saved deliverables. For coding, the separate host-enforced code_request_review workflow still applies; an informal chat is not a publishing approval.
Provenance
Original Sidemates method. Instructions are bundled with Sidemates and do not grant tool or account permissions. See LICENSE for reuse terms.
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.