farm
Skill1 starsChanged 13 days agoMITView on GitHub
Rebuild the Skill Farm page from local skills and transcripts, then open it in the browser. Optional argument demo, fetch or reshuffle.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- master-g/skillstheir own version, first seen Oct 10, 2026
- bradautomates/second-braintheir own version, first seen Oct 9, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- bradautomates/second-brain★ 217same name
- master-g/skills★ 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.
The file
Files
Rebuild the Skill Farm page and open it.
Pick the flags from the argument "$ARGUMENTS":
- empty:
--plugin --open demo:--plugin --demo --open, a page built from made-up datafetch:--plugin --fetch --open, also runsgit fetchon skill repos and plugin marketplaces so update hints are currentreshuffle:--plugin --reshuffle --open, gives every skill a new plant- anything else: tell the user the accepted arguments and stop
First give new skills a Chinese display name. Run:
python3 "${CLAUDE_PLUGIN_ROOT}/build.py" --plugin --unnamedIt prints names_file and a list unnamed. If the list is empty, skip this step. Otherwise read names_file if it exists (a JSON object), add one entry per unnamed skill with its invoke as the key and a short natural Chinese name of 2 to 8 characters as the value, based on its description, keep every existing entry unchanged, and write the file back. It also prints blurbs_file and a list no_blurb. For each skill in no_blurb, add an entry to blurbs_file (a JSON object, read it first if it exists) with the invoke as the key and the value {"zh": "...", "en": "..."}: one plain sentence in each language saying what the skill does, at most about 16 Chinese characters or 8 English words, no brackets. Keep existing entries unchanged.
It also prints tags_file, tag_vocab (tags already in use, with counts), tag_en and a list untagged. For each untagged skill, add an entry to tags_file (a JSON object, read it first if it exists) with its invoke as the key and a list of one or two tags as the value. Reuse tags from tag_vocab whenever one fits; only create a new tag when none does, keep it short, write it in the same language as the existing tags, and add its English name to the _英文 object in the same file. Never change or remove tags that are already there. Don't mention these steps in your reply unless one fails.
Then run exactly this command with the chosen flags:
python3 "${CLAUDE_PLUGIN_ROOT}/build.py" <flags>Then reply in one or two short sentences: the summary line the script printed and where the page is. Your page, farm.json and tags.json live in ~/.claude/skill-farm/ unless SKILL_FARM_HOME points somewhere else. If the command fails, show the error and suggest checking that python3 is version 3.9 or newer.
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.

