ship-context
Skill1 starsChanged 3 months agoMITView on GitHub
When starting to make a repo shippable, or before any other ship-skill. Triggers: 'ship this', 'make it production ready', 'prepare to release', 'ship-context'. Detects the repo's stack and records it in .agents/ship.md so every other ship-skill reuses it.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- add-testsSkill
- cut-a-releaseSkill
- env-and-configSkill
- license-and-legalSkill
- lint-and-formatSkill
- one-command-runSkill
- package-for-npmSkill
- package-for-pypiSkill
- readme-that-convertsSkill
- repo-hygiene-passSkill
- security-basicsSkill
- set-up-ciSkill
- ship-checklistSkill
- write-a-changelogSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 17
Test runner and lint/format tools already present.
≈ “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 Context
The foundation skill. You detect what this repo is and how it ships, and write it to .agents/ship.md so every other ship-skill reads it once instead of re-detecting.
What to detect
Inspect the repo, do not guess:
- Language and runtime (package.json, pyproject.toml, go.mod, Cargo.toml).
- Package manager and lockfile (npm/pnpm/yarn, pip/uv/poetry).
- Test runner and lint/format tools already present.
- Publish target: npm, PyPI, a container image, a hosted app, or GitHub only.
- CI provider (.github/workflows, .gitlab-ci.yml) or none.
- The one-command way a stranger runs it (npx, pipx, docker), if any.
Write .agents/ship.md
Record the above plus: project name, one-line what-it-does, license (or "unlicensed, pick one"), and the intended audience. Keep it short and factual; other skills read it verbatim.
Done when
.agents/ship.md exists and accurately describes stack, package manager, test tooling, and publish target. If anything is unknown, write "unknown, decide in <skill>" rather than guessing.
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.