clear-ask
Skill2 starsChanged 58 days agoMITView on GitHub
Turn vague workplace context into a crisp ask with clear ownership and timing.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- brief-meSkill
- decision-briefSkill
- follow-up-draftSkill
- meeting-to-actionsSkill
- reduce-to-factsSkill
- status-updateSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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 29
Do not send the message unless explicitly asked.
- Distinctive: line 32
Prefer the smallest useful ask.
- Distinctive: line 36
Use only the useful subset of source-backed facts, assumptions, source gaps, stakeholder sensitivities, potential misreads, and the …
- Distinctive: line 38
Use the smallest useful output.
- Distinctive: line 40
When consuming upstream state, do not promote an assumption, inference, open question, proposed action, or stakeholder position into a …
- Distinctive: line 43
Keep unresolved approvals, owners, timing, and blockers explicit in the ask and draft.
- Distinctive: line 44
Do not send, publish, update tickets, create events, or mutate systems unless explicitly asked.
≈ “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
clear-ask
Purpose
Convert a fuzzy request, thread, or note into a direct ask someone can understand and act on.
Use For
- Turning a rambling draft into a clear request
- Clarifying what decision is actually needed
- Making ownership and timing explicit before sending a message
Inputs
- Slack or email draft
- Meeting notes
- Project context
- Pasted workplace context
- A
reduce-to-factsledger or conversation-state record
Guardrails
- Read before write.
- Do not send the message unless explicitly asked.
- Separate known facts from assumptions.
- Flag missing owner, timing, or decision context.
- Prefer the smallest useful ask.
Portable Output Contract
- Use only the useful subset of source-backed facts, assumptions, source gaps, stakeholder sensitivities, potential misreads, and the suggested next action.
- Use the smallest useful output.
- Label assumptions and preserve source gaps, source anchors, and confidence labels.
- When consuming upstream state, do not promote an assumption, inference, open question, proposed action, or stakeholder position into a fact, decision, commitment, owner, or deadline without new source support.
- Keep unresolved approvals, owners, timing, and blockers explicit in the ask and draft.
- Do not send, publish, update tickets, create events, or mutate systems unless explicitly asked.
Output
- Clean ask
- Audience
- Owner
- Deadline / timing
- Decision needed
- Missing info
- Potential misread
- Why this ask is clearer
- Suggested message
Success Standard
The output should remove ambiguity and make the next action obvious within 5 minutes.
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.

