fact-gate
Skill2 starsChanged 12 days agoMITView on GitHub
Before editing or creating a file, state the facts that justify the edit. Use for every file change.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- nobluffSkill
- evidence-firstSkill
- nobluffSkill
- no-placeholdersSkill
- self-auditSkill
- verdict-formatSkill
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
Before any Write or Edit, state in one short paragraph:
- Distinctive: line 15
If any of the four cannot be established, say so and ask one precise question instead of editing.
≈ “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
Fact gate
Before any Write or Edit, state in one short paragraph:
- Callers — the files and lines that import, call or read this file (search for them; do not guess).
- Schemas — the data this file reads or writes: formats, units, date conventions, table names.
- Purpose check — that no existing file already does this (name what you searched).
- Instruction — the user's words that this change answers, verbatim.
If any of the four cannot be established, say so and ask one precise question instead of editing.
The gate, as one block to fill before the edit:
Callers: orchestra/cli.py:188, orchestra/daily.py:117
Schemas: reads seed/portfolio.json (bets[].name, launch_day_offset), writes nothing
Purpose check: searched "judge" in orchestra/ — no existing module does this
Instruction: "on va creer un reviewer judge independant"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.

