cognitive-friction-extractor
Skill0 starsChanged 5 months agoNo licenceView on GitHub
Scans any build session for resolved friction points and extracts them as named, categorized skills in CATEGORY / SKILL / CONSTRAINT / TRIGGER / ASCENT format. Runs both arms of the recursive-learning flywheel in a single gesture — the compression arm captures and thickens what resolved, and the ascent arm emits the sharper successor question each resolution now makes askable. Each extraction is matched against the existing skill ecosystem before any new skill is proposed — the default move is to thicken an installed skill, not to proliferate a new one. Invoke with "extract skills" at any point in a session — mid-session to capture live resolution, or end-of-session for a full retrospective sweep. Also triggers on "extract skills from what I just described" for cross-session recall. Each extracted skill is automatically categorized, matched against existing skills, given its successor question, and offered for routing — upgrade, memory, new file, or discard.
In this repository17 other files it gives its agents.
- carousel-engineSkill
- core-extractorSkill
- crystalliseSkill
- distillSkill
- fuse-deltaSkill
- handoffSkill
- intakeSkill
- intuition-forgeSkill
- moultSkill
- occams-razorSkill
- ossifySkill
- placement-protocolSkill
- Prompt Engine Interface ContractSkill
- ruptureSkill
- spinal-columnSkill
- typographySkill
- ui-contractSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
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.