agentleFS
ManceRayder42ManceRayder42/jarvis-os/skills/wiki-article/SKILL.md

wiki-article

Skill5 starsChanged 43 days agoMITView on GitHub

Write a wiki article capturing structure you learned about an active project in the user's hub. Use when you grepped or spawned Explore agents to understand a project and must record that knowledge before /done, or when the user asks to "write a wiki article", "document this in the wiki", or "add this to the wiki".

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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
  1. Very specific:

    Add it to that project's <hub>/wiki/<project>/index.md (create the index if this is the first article for the project).

    line 52

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Wiki article

When this is required

If you grep, or spawn Explore-style agents, to learn the structure of an active project — and that project lives inside the hub (<hub>/<project>/) — write a wiki article before running /done. The reasoning: that discovery cost real tokens and real time; without a durable record, the next session repeats the same search from scratch, and that cost compounds every time. A short article converts one-time discovery into standing knowledge.

Skip this for shallow lookups (a single grep, one file read) — see "Length" below for the anti-fabrication guard that covers that case.

Template

---
topic: <topic>/<subtopic>
last-updated: YYYY-MM-DD
sources:
  - <file paths you actually read>
---

# <Component / Concept>

## What it is
2–3 sentences, concrete.

## When to read this article
- Bullet list of agent questions it answers

## How it works
Concrete mechanism with file:line references.

## Inputs / Outputs
- Inputs: ...
- Outputs: ...

## Failure modes
1. <mode> — detected by <symptom>, root cause <X>

## Code references
- `path/to/file:line` — what's there

## Related
- [[../other-article]]

Save + register

  1. Save to <hub>/wiki/<project>/<topic>/<article>.md.
  2. Add it to that project's <hub>/wiki/<project>/index.md (create the index if this is the first article for the project).
  3. Mention it in the session note's "Work done" section.
  4. Then /done — its commit step picks up anything dirty under <hub>/wiki/ automatically.

Length

200–400 words. If discovery was shallow (1–2 files read, not enough to write 200 words honestly), do NOT fabricate — append a 5-line "what's missing for a wiki article" stub to the topic's index.md instead, so the next agent knows where to start.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.