doc-drafting
Skill1 starsChanged 3 months agoNo licenceView on GitHub
Two-stage drafting workflow for any AI-generated document a person will review or that will leave the team: reports, proposals, policies, memos, slide decks, long-form copy, markdown docs in a repo. Use this whenever you are asked to draft, write, generate, regenerate, revise, "take another pass at", or "fold feedback into" a document that someone other than the requester will read, even if they don't say "draft" or mention a review. Also use it when handed an AI-generated document to review, and when the user says "freeze it", "move to refining", "new version", "new tab", or asks what state a draft is in. It keeps the draft as a frontmatter markdown file, renders each generation into a new tab with a status-and-provenance grid, never writes over people's edits, stops regenerating once a version is frozen, and refuses to review AI documents that carry no grid. Not for email, chat replies, or code.
In this repository11 other files it gives its agents.
- agent-dev-workflowSkill
- axi-skillsSkill
- ci-quality-gatesSkill
- jarvus-dbtSkill
- jarvus-extjsSkill
- jarvus-fastifySkill
- jarvus-flutterSkill
- jarvus-reactSkill
- plain-languageSkill
- release-flowSkill
- repo-setupSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 7 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.