kg-assess
Skill0 starsChanged 5 months agoNo licenceView on GitHub
Assess and judge an AIDLC node on three axes — its frontmatter ratings (re-rating maturity, confidence, volatility, business_impact, risk_level against current evidence), its narrative coherence (does it tell a clear, self-contained story; are the concepts it leans on actually defined and reachable; do its cross-references deliver what they promise; is terminology consistent), and its emergence/structure status (should a concept graduate to a phase, a signal become a node, a node split, merge, promote, or demote). Use this whenever the user wants to assess, judge, critique, re-rate, sanity-check, or challenge a node — its ratings, its story/storytelling, its coherence, or its status — or asks "is this rating still right", "does this node hold together", "the story doesn't make sense", "this references something we never defined", "is this well written", "should X be its own node", or "reassess this". Proposes changes with evidence and waits for approval before editing.
In this repository11 other files it gives its agents.
- kg-add-nodeSkill
- kg-auditSkill
- kg-digestSkill
- kg-enrichSkill
- kg-linkSkill
- kg-refreshSkill
- kg-scanSkill
- report-briefSkill
- report-deckSkill
- report-qaSkill
- report-story-arcSkill
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.
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.