ship-plan
Skill1 starsChanged 7 months agoMITView on GitHub
Create atomic execution plans for a specific phase. Includes file decomposition, task sizing (2-5 min), model routing, TDD test-first blocks, and wave grouping. Argument is the phase number.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- richardochristjia/skillstheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- richardochristjia/skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository43 other files it gives its agents.
- accessibilitySkill
- agent-evalSkill
- agentic-engineeringSkill
- ai-regression-testingSkill
- api-designSkill
- atomic-planningSkill
- backend-patternsSkill
- coding-standards-eccSkill
- context-engineeringSkill
- frontend-patternsSkill
- git-worktreesSkill
- langchain-dependenciesSkill
- langchain-fundamentalsSkill
- langchain-middlewareSkill
- langchain-ragSkill
- langgraph-fundamentalsSkill
- langgraph-persistenceSkill
- minimalist-skillSkill
- output-skillSkill
- redesign-skillSkill
- security-scanSkill
- ship-architectSkill
- ship-autoSkill
- ship-bugfixSkill
- ship-deploySkill
- ship-discoverSkill
- ship-executeSkill
- ship-finish-branchSkill
- ship-newSkill
- ship-researchSkill
- ship-resumeSkill
- ship-reviewSkill
- ship-settingsSkill
- ship-specSkill
- ship-statusSkill
- ship-testSkill
- ship-worktreeSkill
- soft-skillSkill
- systematic-debuggingSkill
- taste-skillSkill
- test-driven-developmentSkill
- two-stage-reviewSkill
- verification-before-completionSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Read PRD + ARCHITECTURE + ROADMAP.
- Distinctive: line 22
File decomposition first: Before defining tasks, map out ALL files to be created or modified.
- Distinctive: line 53
Wait for "go" or adjustments.
- Very specific: line 59
Every task MUST include a <test-first> block (TDD by default).
- Very specific: line 60
Every task MUST include a <verify> block with concrete checks.
- Very specific: line 61
Every task references which skill the implementer should read via <skill>.
≈ “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
Plan — Atomic task planning
Usage
/bayes-ship:ship-plan <phase_number>
Example: /bayes-ship:ship-plan 1
Pre-condition
.claude/state/PRD.md, .claude/state/ARCHITECTURE.md, and .claude/state/ROADMAP.md must exist.
Process
- Read PRD + ARCHITECTURE + ROADMAP. Identify which user stories belong to the specified phase.
- File decomposition first: Before defining tasks, map out ALL files to be created or modified. For each file, state its single responsibility. Lock in decomposition decisions here. Design units with clear boundaries and well-defined interfaces.
- Break the phase into atomic tasks. Each task must be completable in 2-5 minutes of AI work. If a task cannot be described in 2-3 sentences, split it further.
- Structure each task as XML:
<task type="auto" model="sonnet">
<n>Task title</n>
<files>src/path/to/file.ts, src/path/to/other.ts</files>
<skill>relevant-skill-name</skill>
<test-first>
Write test: [describe the test]. Watch it fail (RED).
</test-first>
<action>
[Implementation instructions]. Watch tests pass (GREEN).
</action>
<verify>Run test suite. All tests pass. Typecheck passes.</verify>
<done>Completion criteria.</done>
</task>- Model routing per task:
model="haiku"— mechanical 1-2 file tasks (rename, config, simple CRUD)model="sonnet"— standard multi-file integration (default)model="opus"— architecture decisions, complex refactors, review
- Wave grouping: Group independent tasks into parallel waves. Dependent tasks go into later waves.
- Save plan to
.claude/state/plans/phase-<n>/plan.md. - Present the plan to the user: file decomposition summary, task list with waves, estimated time.
- Wait for "go" or adjustments.
- Update progress.json.
- Output: "Run
/bayes-ship:ship-executeto start building."
Rules
- Every task MUST include a
<test-first>block (TDD by default). Iftdd_modeisrelaxed, the test-first block becomes optional. - Every task MUST include a
<verify>block with concrete checks. - Every task references which skill the implementer should read via
<skill>.
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.