model
Skill12 starsChanged 49 days agoMITView on GitHub
Create or maintain a source-grounded kpopper knowledge model as a versioned plugin. Use when a reusable domain model should ship independently of any one project.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- timpulver/openai-image-gentheir own version, first seen Nov 1, 2026
- marcuskrogh/skillstheir own version, first seen Oct 13, 2026
- hass-energy/haeotheir own version, first seen Oct 8, 2026
- yuchi423/MCM-ICM_Agent_Skillstheir own version, first seen Aug 23, 2026
- TheLatentSpaceLab/Qubitotheir own version, first seen Apr 1, 2026
- alectimison-maker/MCM-ICM_Agent_Skillstheir own version, first seen Jan 29, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- hass-energy/haeo★ 77same name
- alectimison-maker/MCM-ICM_Agent_Skills★ 3same name
- marcuskrogh/skills★ 1same name
- TheLatentSpaceLab/Qubito★ 1same name
- yuchi423/MCM-ICM_Agent_Skills★ 1same name
- timpulver/openai-image-gen★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- annotated-docSkill
- consolidateSkill
- documentSkill
- groundSkill
- hubSkill
- kpopperSkill
- mapSkill
- pageSkill
- recordSkill
- watchSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
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 8
Use this skill for a reusable, source-backed model that people should install and query across projects.
- Distinctive: line 12
Read the authoring guide. The complete example is a separate packaging walkthrough.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Create a model plugin
Use this skill for a reusable, source-backed model that people should install and query across projects. An ordinary project record, a one-off answer, or a case adapter alone is a different task.
The generated plugin and packaging workflow are currently qualified for local Codex on macOS ARM64. This skill's presence in another host does not establish support there. The companion is an unreleased source candidate; use a maintainer-supplied qualified prebuilt toolchain.
Read the authoring guide. The complete example is a separate packaging walkthrough; do not copy its record or history over a model you have authored. Define the scope, source closure, unknowns, independently expected questions and plugin descriptor before packaging.
Author records with the native kpop commands. Do not hand-edit generated GROUNDING.yaml or history. Preserve a person's case in a disposable workspace, never in the reusable model. Use the release-qualified prebuilt kpop-model build tool and bundled engine when they are available; model authors should not compile Rust or install another language runtime. If either artifact is missing, save the authored model and report the missing packaging prerequisite.
Before native authoring, set XDG_CACHE_HOME to a private writable directory outside the model, within the task's existing allowed paths. The engine needs its runtime cache even with --no-cache; do not rely on a writable home directory or broaden host permissions. Keep this transient cache out of the committed model and package.
A read model needs only the standard native reader. Recorded rules run through the native engine too. A domain application that adds case-specific input binding or output projection must supply a separately tested native adapter and maintainer-owned build. Keep that obligation separate from model authoring.
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.