ZooData-Skills
AGENTS.md77 starsChanged 8 months agoMITView on GitHub
Before modifying or reviewing any skill, read and follow CONTRIBUTING.md, especially Skill Specification Ownership, then read the affected skill's SKILL.md and review its modules against the responsibility map declared there. Run the relevant consistency tests before completing the change. Skills are published to ClawHub manually via clawhub sync (the ClawHub key stays local — never in CI). A release is a repo-level milestone cut as a GitHub Release whose tag ends in -release (e.g. v1.2.3-release). This repo is public, so…
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 31,774 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 repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- amazon-analysisSkill
- amazon-competitor-intelligence-monitorSkill
- amazon-daily-market-radarSkill
- amazon-keyword-traffic-analysisSkill
- amazon-listing-audit-proSkill
- amazon-market-analysisSkill
- amazon-pricing-command-centerSkill
- amazon-review-intelligence-extractorSkill
- web-extractSkill
- zoodataSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
Before modifying or reviewing any skill, read and follow CONTRIBUTING.md, especially Skill Specification Ownership, then read the affected …
- Very specific: line 17
Keep this file as an instruction bridge.
- Very specific: line 19
Follow docs/pr-description.md when writing or revising a PR description.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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
Repository Agent Instructions
Before modifying or reviewing any skill, read and follow
CONTRIBUTING.md, especially Skill Specification Ownership, then read the
affected skill's SKILL.md and review its modules against the responsibility
map declared there. Run the relevant consistency tests before completing the
change.
Releasing / publishing
Skills are published to ClawHub manually via clawhub sync (the ClawHub key stays
local — never in CI). A release is a repo-level milestone cut as a GitHub Release whose
tag ends in -release (e.g. v1.2.3-release). This repo is public, so the Lark
launch-tracking notification is run from hermes-workspace on this repo's behalf (no
notification secrets live here). See docs/release-notify.md.
Keep this file as an instruction bridge. Do not copy skill-specific contracts,
module policies, or runtime rules into it.
Follow docs/pr-description.md when writing or revising a PR description.
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.

