ask-minimalship
Skill0 starsChanged 25 days agoMITView on GitHub
Choose the smallest MinimalShip flow for a product-development task.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- minimalshipSkill
- codebase-designSkill
- code-reviewSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- grill-with-docsSkill
- implementSkill
- implement-specSkill
- improve-codebase-architectureSkill
- prototypeSkill
- prSkill
- researchSkill
- retroSkill
- setup-minimalshipSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wayfinderSkill
- wizardSkill
- grillingSkill
- grill-meSkill
- handoffSkill
- teachSkill
- to-questionnaireSkill
- wait-whatSkill
- writing-for-agentsSkill
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 9
Use this router when a request could follow more than one product-development path.
- Distinctive: line 24
Do not route by fashion. Route by the next unresolved decision and the smallest artifact that can settle it.
≈ “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
Ask MinimalShip
Use this router when a request could follow more than one product-development path.
Route by need
- Unclear outcome or competing options: use
grill-meorgrill-with-docs. - A settled conversation needs a concise contract: use
to-spec. - A large contract needs dependency-aware slices: use
to-tickets. - A runnable increment needs building: use
implementorimplement-spec. - A failure is reported: use
diagnosing-bugs. - The right module boundary is uncertain: use
codebase-design. - Tests need a behavior-first loop: use
tdd. - A branch needs independent review: use
code-review, thenpr. - A decision needs several sessions: use
wayfinder. - The work is complete and the environment should improve: use
retro.
Do not route by fashion. Route by the next unresolved decision and the smallest artifact that can settle it. Never invoke two competing orchestration flows for the same task.
When the request is a new project or an existing repository to investigate, route through understanding and planning first: inspect the project, update FEATURES.md and RUN.md, present the execution proposal, and wait for approval unless the user's original instruction already authorizes implementation. Do not dispatch workers as a side effect of routing.
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.

