facto
Skill1 starsChanged 5 days agoNo licenceView on GitHub
Record findings as facts in a Datalog (CozoDB) store where each one cites either a verbatim quote or a command that can be re-run, so a claim is re-checkable rather than merely sourced. Detects contradictions between agents, records who asserted what and when they stopped believing it, flags facts nobody has re-verified lately, and assembles prompt context from verified facts instead of vector-similarity chunks. Use this skill whenever work spans multiple sessions, sources or agents — literature reviews, competitive analysis, due diligence, investigations, infrastructure state, long-running notes — or whenever they mention fact extraction, provenance, citations, knowledge graphs, contradiction detection, stale notes, or "things I've learned so far." Reach for it especially when the claims are counts, versions or states of a running system: indexes, replicas, commits, rows, transitions. Also use it when the user complains that their notes have drifted, that they cannot remember where a claim came from, that two agents disagree, or that an AI assistant keeps losing or inventing details across a long project. Prefer this over freeform markdown notes or a RAG index any time the accuracy of individual claims matters more than the fluency of the summary.
In this repositoryOne other file it gives its agents.
- agent-mailSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 7 are distinctive, and 6 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.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.