toolkit
Skill84 starsChanged 13 days agoMITView on GitHub
Use to build or rebuild the documentation site of the project from the repo, the architecture, the data lineage, the call graph, the data model, the data quality, the runs and the data catalog.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- notque/vexjoy-agenttheir own version, first seen Nov 7, 2026
- notque/claude-code-toolkittheir own version, first seen Oct 8, 2026
- roethlar/AgentGovernanceBootstraptheir own version, first seen Sep 10, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- notque/claude-code-toolkit★ 448same name
- notque/vexjoy-agent★ 448same name
- roethlar/AgentGovernanceBootstrap★ 2same 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 repository16 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- big-reviewSkill
- contractSkill
- cost-reviewSkill
- data-productSkill
- docsSkill
- impactSkill
- incidentSkill
- knowledge-refreshSkill
- metadataSkill
- migrationSkill
- profileSkill
- pr-reviewSkill
- qualitySkill
- reconcileSkill
- test-dataSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
5
Distinctive
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 14
Write a site builder: one script that reads the repo and writes the pages, so the site can be built again after every release.
- Distinctive: line 18
Call graph: who calls what in the code, clickable.
- Distinctive: line 23
When the project is big, ask how many agents may run, give one agent per page, and let every agent check its page against the repo.
- Distinctive: line 40
Never edits a page by hand: fix the input or the builder, and build again.
- Distinctive: line 41
Never adds a library or a fetch from the network to a page.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Toolkit
The job: the engineering toolkit of the project as a website, built from the repo, one page per tool. Rebuilt after every release.
Input: none, it reads the whole repo.
Steps
- Write a site builder: one script that reads the repo and writes the pages, so the site can be built again after every release.
- Overview: the sources, the layers and the latest runs.
- Architecture: drawn from what runs, not by hand. The high-level picture first, the detail below it.
- Data lineage: every table, clickable, upstream and downstream.
- Call graph: who calls what in the code, clickable.
- Data model: the entities and their relationships, then the star schema with the keys.
- Data quality: the checks and their results, day by day.
- Runs: what ran, how long it took, and the result.
- Data catalog: every table and column, with a sample and a description. Personal data is masked in the samples.
- When the project is big, ask how many agents may run, give one agent per page, and let every agent check its page against the repo.
- Build the site and say where to open it.
Output
One folder of HTML files, like references/: index.html as the hub and one page per tool, nothing fetched from the network. Read them for the layout before you write the builder.
Reads
- the metadata, the pipeline code, the run records, the check results, the knowledge
Writes
- the site builder, and the pages it writes
Never
- Never edits a page by hand: fix the input or the builder, and build again.
- Never adds a library or a fetch from the network to a page.
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.