skills
CLAUDE.md0 starsChanged 3 months agoMITView on GitHub
A public monorepo of generic, brand-neutral Claude Code skills (github.com/atleronningen/skills). Each top-level folder is one independently installable skill. system-map is the first; more will be added as siblings over time. Primary language for this project (code, docs, comments, README) is English, even though chat in this working directory may happen in Norwegian — that's separate from the project's own output. Skills that render user-facing text (like system-map's widget) should default to English but allow the end user to swap in…
In this repositoryOne other file it gives its agents.
- system-mapSkill
The file
We split this CLAUDE.md 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
- Distinctive: line 16
No build step. Each skill is plain Markdown + whatever scripts it needs (currently Python and browser-console JS for system-map).
- Very specific: line 51
When adding a new skill: create a new top-level folder named after the skill (matching its SKILL.md name: field), keep it self-contained …
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
skills — for Claude
A public monorepo of generic, brand-neutral Claude Code skills
(github.com/atleronningen/skills). Each top-level folder is one
independently installable skill. system-map is the first; more will be
added as siblings over time.
Primary language for this project (code, docs, comments, README) is English, even though chat in this working directory may happen in Norwegian — that's separate from the project's own output. Skills that render user-facing text (like system-map's widget) should default to English but allow the end user to swap in their own language, not hardcode Norwegian/English.
Stack
No build step. Each skill is plain Markdown + whatever scripts it needs (currently Python and browser-console JS for system-map).
Commands
<!-- Fill in per-skill dev/verification commands as skills are added. -->Structure
Repo root holds the public-facing, repo-wide files (README, LICENSE, this
file). Every other top-level folder is a self-contained, installable skill —
the exact folder a user copies into their .claude/skills/.
skills/
├── README.md # overview of all skills + install instructions
├── LICENSE # MIT, repo-wide
├── CLAUDE.md # this file
├── .gitignore
└── system-map/ # first skill — installable payload
├── README.md
├── SKILL.md
├── references/
│ ├── palette.md
│ └── examples/
│ ├── agent-workflow.html
│ ├── business-integration.html
│ ├── data-pipeline.html
│ └── hr-platform.html
├── screenshots/ # doc-only PNG previews used by system-map/README.md
└── scripts/
├── layout.py
└── selfcheck.jsWhen adding a new skill: create a new top-level folder named after the
skill (matching its SKILL.md name: field), keep it self-contained (own
references/, scripts/ as needed), and add it to the table in
README.md.
Privacy
This repo is public. Never use the user's personal name in anything tied to it — not in committed content (README, SKILL.md, code, commit messages) and not in working artifacts either (plan files, chat framing). Refer to "the user" or omit the reference entirely. This is scoped to this project only; it does not apply elsewhere in the wider Playground workspace.
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.

