ship-it
Skill0 starsChanged 3 months agoMITView on GitHub
Complete a named software change through its requested source or authorized live outcome when the user asks to ship, merge, deploy, make it live, or finish established delivery. Do not execute for audits, status, planning, or quoted examples.
46 other projects use a version of this.
Adopted by
Most recently taken up by
- alexandrosandre/agentic-engineeringtheir own version, first seen Nov 8, 2026
- alexandrosandre/alice-issue-agenttheir own version, first seen Nov 8, 2026
- spencerldixon/skillstheir own version, first seen Nov 8, 2026
- unional/skillstheir own version, first seen Nov 6, 2026
- frappe/skillstheir own version, first seen Nov 1, 2026
- schalk-conradie/skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use modern-go, loop-it and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
jidechaoSkillmodern-go
Modernize Go code by applying version-appropriate idioms and APIs (gofix-style transformations). Scans go.mod for the Go version, then transforms Go source files to use modern patterns—from Go 1.0 through 1.26+. Use when the user says "现代化","现代Go语言", "地道的", "idiomatic", "modernize", "modern-go", "update Go code", "gofix", or wants to upgrade Go idioms.
Also in 3 projects that use this
jidechaoSkillloop-it
Automated issue loop with checkpoint/resume: fetch open GitHub issues → dependency-aware topological sort → implement each issue end-to-end → review with /review-it → document with /note-it → ship with /ship-it → repeat. Persists state to .loop-state.json for crash recovery. Triggers on: loop-it, loop issues, auto implement, 批量实现, 循环实现, 实现所有issue, 恢复循环, resume loop.
Also in 3 projects that use this
SentrySkillcreate-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
Also in 5 projects that use this
GitHubSkillrefactor
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
Also in 4 projects that use this
GoogleSkillto-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
Also in 3 projects that use this
Hugging FaceSkillsimplify
Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.
Also in 3 projects that use this
- +2 more from jidechao
Other versions46 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 46
- vectorize-io/hindsight★ 60ksame name
- learntocloud/learn-to-cloud-app★ 1.1ksame name
- leonvanzyl/agentic-coding-starter-kit★ 447same name
- smallnest/goal-workflow★ 283same name
- frappe/skills★ 162same name
- DECRUX9812/hermes-plugin-gameforge★ 44same name
- awslabs/llm-evaluation-system★ 26same name
- LunkiBR/ship-it★ 18same name
- paultyng/skill-issue★ 8same name
- davidmeirlevy/obvious-skills★ 6same name
36 more not listed
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 repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- domains/AGENTS.mdAGENTS.md
- index/AGENTS.mdAGENTS.md
- records/AGENTS.mdAGENTS.md
- research/AGENTS.mdAGENTS.md
- reviews/AGENTS.mdAGENTS.md
- skills/AGENTS.mdAGENTS.md
- ai-writing-reviewSkill
- general-writingSkill
- live-data-rewriteSkill
- live-ui-auditSkill
- parallel-build-sprintSkill
- r2cSkill
- research-stackSkill
- skill-indexSkill
- streamdeck-authoringSkill
- video-creative-rulesSkill
- wikipedia-researchSkill
- wikipedia-reviewSkill
- wikipedia-workflowSkill
- wikipedia-writingSkill
- writing-cleanupSkill
- writing-reviewSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 42 edited versions we read keep these.
7
Distinctive
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 8
Use the owning repository's delivery contract when present.
- Distinctive: line 38
Do not deploy a dirty checkout or silently substitute another artifact.
- Distinctive: line 55
Do not infer those effects from a generic instruction to finish.
- Distinctive: line 57
Ask only for missing coverage, a material choice, or unavoidable human action.
- Distinctive: line 64
After the requested endpoint is verified and task users, workers, and terminals have released the target, invoke the owning cleanup …
- Distinctive: line 69
Remove ordinary leftovers only through its verified preservation procedure.
- Distinctive: line 70
Treat accepted or queued cleanup as pending until removal is independently verified.
“Common” is measured: kept by at least 6 in 10 of the 42 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Ship it
Use the owning repository's delivery contract when present. Otherwise use this completion contract with its existing validation, release, deployment, recovery, and cleanup procedures. Do not introduce another command implementation.
Resolve the requested outcome
| Request and context | Endpoint |
| Named implementation, fix, build, or change | Validated source delivery through commit, push, PR, exact-head merge, default-branch verification, and safe task cleanup. |
| A request clearly requiring a live result on an established service, including "ship it" or "make it live"; or "merge it" when a live endpoint was already established | Source delivery plus necessary release, deployment, activation, live verification, and safe task cleanup. |
| "Finish", "continue", or "work until complete" | Retain the established endpoint and limits through retries, waits, and route changes. |
| Source-only, merge-only, draft-only, preview-only, staging-only, do-not-deploy, or preservation limits | Honor the narrower endpoint, target, and effects. |
| Audit, review, status, recommendation, planning, or a quoted example | Read-only; do not start delivery. |
Infer the repository, task, exact revision, environment, and intended effects from the user's request and current task evidence. A prototype or a repository with no runtime need not acquire a production target. When live delivery is requested but the target or owning deployment path remains ambiguous, complete independent work and ask only for that missing choice. Credentials and client defaults do not choose the target. An explicit user-defined meaning overrides the vocabulary above. Do not reapprove an outcome already authorized in this task.
Deliver with evidence
- Preserve unrelated work. Reuse existing results and checkpoint coherent work; isolate Git changes where needed. Use one final validation owner and the repository's exact-revision merge procedure. Required gates remain binding.
- For an authorized live outcome, use the owning release and deployment path. Bind the artifact to the merged revision, confirm the target and documented recovery path, then install, configure, activate, or restart only as necessary. Do not deploy a dirty checkout or silently substitute another artifact.
- For live endpoints only, read back the running revision and exercise the changed user behavior with a bounded probe inside the authorized effects. Health alone does not prove the outcome. Keep an unperformed or failed user-path check unverified.
- Diagnose recoverable failures before retrying. Re-bind the target, effect, and revision after a route change; stop a repeated unchanged failure pending new evidence. Reconcile ambiguous external results and never repeat a completed merge because runtime evidence is missing.
Ask only at a material boundary
Retain authorization while the target, effects, access, cost limits, and risk remain in scope. New infrastructure, spending commitments, permissions, destructive data changes, public disclosure, and external communications need explicit coverage in the user's authorization. Installation or activation of an automation that introduces such effects is subject to the same boundary. Do not infer those effects from a generic instruction to finish.
Ask only for missing coverage, a material choice, or unavoidable human action. State the exact missing decision or binding guard, prepare the authorized work, and continue independent work. Never bypass a failed required gate or a tool guard, disclose credentials, or treat available access as action authority.
Close out
After the requested endpoint is verified and task users, workers, and terminals have released the target, invoke the owning cleanup procedure from a safe checkout with the exact task and merge evidence, plus runtime evidence for a live endpoint. Let that owner coordinate worktree and branch retirement. Preserve active, dirty, ignored, ambiguous, unmerged, or recovery-needed work. Remove ordinary leftovers only through its verified preservation procedure. Treat accepted or queued cleanup as pending until removal is independently verified; reconcile uncertain results before retrying. A cleanup hold does not undo a successful merge or justify force deletion.
Report the source revision and merge; release, deployment, installation, and activation separately; the running artifact and observed behavior; acceptance when in scope; and cleanup or preserved work. Mark unrequested stages as not applicable and unresolved stages as held. Never equate these states.
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.

