ship-milestone
Skill0 starsChanged 37 days agoMITView on GitHub
Land any multi-day feature or new repo as a sequence of verified, deployable milestones (M1 skeleton+CI, M2 core work, M3 production dressing) so progress is always shippable. Use when starting a new project or a large feature.
In this repository4 other files it gives its agents.
- templates/AGENTS.mdAGENTS.md
- agent-wavesSkill
- pr-stackSkill
- verify-before-pushSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Never build "the whole thing" — build M1, ship it, then M2, ship it.
- Distinctive: line 28
No branch lives long enough to need a rebase strategy.
≈ “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.
Files
Ship in milestones
Never build "the whole thing" — build M1, ship it, then M2, ship it.
M1 — skeleton + CI first
- Repo, build tooling, and a CI workflow (build + test + lint) before any real feature code.
- One thin end-to-end slice to prove the stack compiles and tests run.
- Nothing else happens until CI is green on
main.
M2 — core work
- The smallest set of features that makes the thing useful to its first real user.
- Each push keeps the full suite green — milestones are deployable checkpoints, not branches that live long.
M3 — production dressing
- Docs with actual design notes (the decisions, not the obvious).
- Container image / release automation.
- Tag
vX.Y.Z, then verify the artifact exists and runs — a release you haven't downloaded is a release you haven't made.
Rules
- No branch lives long enough to need a rebase strategy.
- "Done" always means CI green + artifact verified, never "code written".
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.