stream-carve
Skill1 starsChanged 5 months agoNo licenceView on GitHub
Carve a matured line — a business, product, or life-area that grew up inside another stream — OUT into its own peer stream, cleaning the source (a MOVE: content relocates, the source releases its copy, nothing is discarded). Use when the operator says 'carve out', 'spin X into its own stream/OS', 'clean X out of this stream', or 'X has outgrown this stream'. Runs a read-only discovery sweep + density read, a density-adaptive interview (build the core where the source is thin, disentangle the seam where it's thick), proposes a carve manifest (move / split-slice / distill-rehome / seed / register / consumer-handoff), routes the carved-out line either to its own new stream OR to a retrievable PARK in pending/ (never a true discard), and — once approved, inside an enforced checkpoint bracket — carves it out, de-entangles the source, verifies nothing was dropped, and offers to pack a Claude.ai BOS. Gated, never silent. For a NEW peer with the source UNTOUCHED, see stream-seed; for separating one stream into two co-equal peers, see stream-split (staged).
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
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 364,980 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.

