zhijian-skills
AGENTS.md787 starsChanged 4 months agoMITView on GitHub
This repository is the only editable source for the public Zhijian Skills portfolio. Before committing a Skill change: The Registry is the single machine-readable source for Skill paths, versions, validation, capabilities, Harness support, and documentation. Mirror metadata is forbidden.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 33,315 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository20 other files it gives its agents.
- codex-cli-model-bridgeSkill
- codex-doctorSkill
- codex-external-handoffSkill
- codex-handoffSkill
- codex-image-genSkill
- codex-model-routing-teamSkill
- codex-skill-adminSkill
- codex-theme-studioSkill
- enterprise-clone-builderSkill
- gpt56-sol-pro-consultSkill
- html-expressSkill
- leadbookSkill
- light-plan-and-workSkill
- scholar-stickersSkill
- skill-open-sourcerSkill
- web-clipperSkill
- wechat-article-searchSkill
- wechat-stylerSkill
- workbuddy-cli-model-bridgeSkill
- wxmp-article-harvesterSkill
The file
We split this AGENTS.md into the rules it gives an agent
10 rules. About 1 is common, 7 are distinctive, and 2 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 7
Treat main as a protected integration branch.
- Very specific: line 8
Before publishing, record and re-check the live remote SHA.
- Distinctive: line 12
Do not create or update standalone Skill repositories.
- Common: line 16
Never publish credentials, personal absolute paths, customer data, caches, generated previews, reports, browser profiles, or dependency …
- Distinctive: line 20
Never force-push or rewrite published Portfolio history or Tags.
- Distinctive: line 24
Before committing a Skill change:
- Distinctive: line 26
Run the repository-owned Skill validator.
- Distinctive: line 27
Run that Skill's declared deterministic tests.
- Distinctive: line 28
Run its isolated install check.
- Distinctive: line 29
Run Portfolio contract tests when Registry or governance code changes.
≈ “Common” is an estimate: at least 1 in 5 of the 42,283 AGENTS.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
Zhijian Skills Repository Instructions
Repository role
This repository is the only editable source for the public Zhijian Skills portfolio.
- Treat
mainas a protected integration branch. Start each task from the liveorigin/mainSHA on a short-lived branch, push only that branch, and merge through a PR. - Before publishing, record and re-check the live remote SHA. A
.git/zhijian-needs-sync.jsonmarker blocks commits, pulls, and pushes until the checkout is clean and exactly synchronized toorigin/main. skills/<name>/is the install payload and must remain self-contained.- Human documentation lives in
docs/skills/<name>/. - Per-Skill release notes live in
docs/changelogs/<name>.md. - Do not create or update standalone Skill repositories. Every public Skill is released only from this Portfolio.
Safety
- Never publish credentials, personal absolute paths, customer data, caches, generated previews, reports, browser profiles, or dependency directories.
- Candidate Skill code runs without release credentials.
- Release and repository-admin credentials stay separate.
- Unknown source drift blocks the affected Skill.
- Never force-push or rewrite published Portfolio history or Tags.
Verification
Before committing a Skill change:
- Run the repository-owned Skill validator.
- Run that Skill's declared deterministic tests.
- Run its isolated install check.
- Run Portfolio contract tests when Registry or governance code changes.
The Registry is the single machine-readable source for Skill paths, versions, validation, capabilities, Harness support, and documentation. Mirror metadata is forbidden.
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.

