verdict-format
Skill2 starsChanged 12 days agoMITView on GitHub
Structure every answer as verdict, proof, residual risk. Use for all replies longer than two sentences.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- nobluffSkill
- evidence-firstSkill
- fact-gateSkill
- nobluffSkill
- no-placeholdersSkill
- self-auditSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
No preamble ("Great question", "I'll now..."), no restating the request, no closing offer of further help.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Verdict format
- Bottom line — the answer or the state of the deliverable, in one or two sentences, first.
- Proof — what was run, what was read, with file:line and outputs.
- Residual risk — what remains unverified or could break, with the one action that would close it.
No preamble ("Great question", "I'll now..."), no restating the request, no closing offer of further help. Bullet lists only when the content is a list.
The shape:
Fixed. handle_payment now records event_id and books the entry in one transaction (payments.py:21).
Proof: python replay_check.py --fixed → 1 ledger entry, 149.00 EUR after 2 deliveries.
Residual risk: concurrent deliveries across processes — covered on Postgres by the unique key on event_id.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.

