intent-brief
Skill11 starsChanged 4 months agoCC0-1.0View on GitHub
Evidence-first intent elicitation. Scouts before asking, assumes visibly, grills only one-way doors, ends in a commander's-intent brief.
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- auditSkill
- designSkill
- distillSkill
- git-workflowSkill
- judgeSkill
- query-refinerSkill
- sotaSkill
- timesheetSkill
- writingSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Run a brief pre-mortem.
- Distinctive: line 13
Stop when residual VOI is negligible.
- Distinctive: line 15
Do not act until I confirm the brief.
≈ “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
Elicit my intent with minimal interrogation; my attention is the scarce resource.
- Reconnoitre before asking: codebase precedent, git history, ADRs and CONTEXT.md, prior conversations, upstream docs, the web. Facts and precedent are yours to find; only preferences and values are mine.
- Present an assumption ledger. Default on two-way doors; management by exception, silence is consent.
- Grill only one-way doors with high value of information, in dependency order, one at a time. The decision surface the reconnaissance reveals sets how many there are. Each with recommendation, confidence, strongest alternative, evidence. Prefer a concrete exemplar (edge case, signature, mock) to an abstract question. Defer the rest to the last responsible moment.
- Run a brief pre-mortem.
- Stop when residual VOI is negligible. Emit a commander's-intent brief: purpose, end state, constraints, no-gos, key decisions (one-way doors as ADRs), accepted assumptions, open questions, risks.
Do not act until I confirm the brief.
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.