write-doc
Skill0 starsChanged 3 months agoMITView on GitHub
Write an illustrated explainer doc for a feature, folder, or recent change, saved as docs/show-me-how/<topic>/<topic>.md.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- swm8023/skillstheir own version, first seen Nov 1, 2026
- bbvch-ai/aihub-coretheir own version, first seen Oct 25, 2026
- LeoHChen/claude-skillstheir own version, first seen Jul 18, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- bbvch-ai/aihub-core★ 16same name
- swm8023/skills★ 2same name
- LeoHChen/claude-skills★ 1same 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 repository4 other files it gives its agents.
- explainSkill
- illustrateSkill
- initSkill
- pr-reviewSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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 9
Never run git commit, git add, or any other write-doc step that commits.
- Distinctive: line 22
Write BRIEF (<=200 words): what changed or what this is, why, how it works, what a teammate must do or know, the gotcha.
≈ “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.
Files
/show-me-how:write-doc $ARGUMENTS
Never run git commit, git add, or any other write-doc step that commits. This command only writes files under the docs folder.
1. Resolve input, in order
$ARGUMENTSis an existing file -> read it. TOPIC = its H1, or the filename if it has none.$ARGUMENTSis an existing folder -> read its README/index if present, and list its files. TOPIC = the folder name.$ARGUMENTSis free text -> treat it as a topic and grep the repo like/show-me-how:explainstep 1, at most 8 files.$ARGUMENTSis empty -> rungit log -20 --stat. Pick the most recent coherent set of commits (same feature words in the subjects); read the files those commits changed. TOPIC = the feature words from those subjects. Tell the user which commits you picked, by hash and subject, before continuing.
Record every file read (and, for case 4, every commit picked) as SOURCES.
2. Brief
Write BRIEF (<=200 words): what changed or what this is, why, how it works, what a teammate must do or know, the gotcha.
3. Illustrate
MAX_IMAGES = 8. The beat sheet decides the real count: a single short file usually needs 2-3 panels, a multi-file feature 5-6.
Invoke the illustrate skill (skills/illustrate/SKILL.md) from its step 0, with this brief block:
MODE: doc
TOPIC: <TOPIC>
SOURCES: <the paths/commits from step 1>
BRIEF: <the text from step 2>
MAX_IMAGES: 84. Report
After illustrate finishes, print the doc path (DIR/<slug>.md) and a 3-line summary of what it covers. Illustrate already suggests the .show-me-how/ gitignore line; do not repeat it, and never edit .gitignore. Do not commit anything, and do not tell the user to commit it for them — leave that to them.
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.

