ship-task
Skill0 starsChanged 36 days agoMITView on GitHub
Run the full michaelshimeles workflow on one task, start to PR - isolate in a worktree, build, prove with evidence, open a PR with before/after proof, then loop Greptile to 5/5. Invoke with /ship-task <task description>.
- Commits and pushes
1 other project uses a version of this.
Adopted by
Most recently taken up by
- aiatelie/ai-atelietheir own version, first seen May 9, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- aiatelie/ai-atelie★ 9same 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.
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 3 are distinctive, and 5 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.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
If the task is empty or too vague to test, ask one short question before starting.
- Very specific: line 18
Must be inside a git repo with a GitHub origin and an authenticated gh (gh auth status).
- Very specific: line 27
Start the task in its own worktree branched from latest origin/main (or the repo's default branch), including the scope check against open …
- Distinctive: line 36
Run the repo's checks from preflight.
- Very specific: line 41
Commit with a clear message, rebase onto latest origin/<default branch>, rerun checks, push (git push -u origin <branch>.
- Very specific: line 42
Write the PR body: what changed, how it was tested (every claim backed by evidence), risks and follow-ups.
- Very specific: line 44
Run /greploop until Greptile gives 5/5 with zero unresolved comments (use /greploop-apps if Greptile says too many files changed).
- Distinctive: line 49
Keep the worktree until the PR is merged or closed.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Task
Task: $ARGUMENTS
If the task is empty or too vague to test, ask one short question before starting.
Run the four beats below in order, invoking each named skill with the Skill tool. Do not skip a beat silently: if a beat cannot run (missing tool, no GUI, no Greptile), say so in one line, use the fallback, and keep going. Keep a short checklist of beats and tick each one off as you go.
0. Preflight
- Must be inside a git repo with a GitHub
originand an authenticatedgh(gh auth status). If not, stop and tell the user what is missing. - The skills this workflow calls must be installed:
new-feature,code-structure,evidence-driven-testing,unslop,greploop,greploop-apps,before-and-after. If any is missing from your skill list, stop and tell the user to run the installer from https://github.com/Koushik890/ship-task. Do not improvise a replacement for a missing skill. Thebefore-and-afterskill must be the vercel-labs version: its directory containsscripts/format.mjs. If it hasscripts/capture.shinstead, it is the older copy vendored in michaelshimeles/skills, which this workflow does not support; tell the user to rerun the installer. - Find the default branch with
gh repo view --json defaultBranchRef -q .defaultBranchRef.name(fall back tomain). Wherever this skill saysorigin/main, useorigin/<default branch>. - Check optional tools once and remember which are missing:
jq,node,ffmpeg,agent-browser, and Python. On Windowspython3is often absent or a Microsoft Store stub; trypython3, thenpython, thenpy -3, and use whichever prints a 3.x version for every Python command the other skills give you. - Shell: write commands for the shell tool you are actually running (bash/Git Bash vs PowerShell). Use forward slashes and quote paths that can contain spaces.
- Find the repo's checks:
CLAUDE.md/AGENTS.mdfirst, thenpackage.jsonscripts (test, lint, typecheck, build),Makefile,pyproject.toml, etc. Note the exact commands; you will run them in beat 3 and before pushing.
1. Isolate - /new-feature
Start the task in its own worktree branched from latest origin/main (or the repo's default branch), including the scope check against open PRs. On overlap with another open PR, stop and ask.
2. Build - /code-structure
Implement the smallest change that does the task. Follow code-structure: actions own the why/when, a service layer owns reusable how. Do not refactor beyond what the task needs.
3. Prove - /evidence-driven-testing
- Capture the before state first, while reproducing the issue or showing the missing feature, before the fix lands where possible.
- Run the repo's checks from preflight; all must pass.
- Gather runtime evidence of the after state. UI change: screen recording if a GUI is drivable, else the skill's headless path (Playwright screenshots). Non-UI change: measured numbers or before/after output pairs.
4. Ship - /before-and-after, /unslop, /greploop
- Commit with a clear message, rebase onto latest
origin/<default branch>, rerun checks, push (git push -u origin <branch>;--force-with-leaseonly on your own branch, never plain--force). - Write the PR body: what changed, how it was tested (every claim backed by evidence), risks and follow-ups. Run
/unslopover the PR title, body and commit messages, then open the PR withgh pr create. - Visible change: capture before/after screenshots or recordings with
agent-browser(runagent-browser skills get core --fullfor usage) into acaptures/folder, then run/before-and-afterto insert the comparison block into the PR. Its formatter isscripts/format.mjsinside the before-and-after skill's own directory (the skill's base directory is shown when it loads; do not assume~/.claude/skills), run withnode; it uploads throughgh --attach(GitHub-hosted, needs gh 2.100+). Never commitcaptures/: addcaptures/to.git/info/excludebefore capturing. - Run
/greploopuntil Greptile gives 5/5 with zero unresolved comments (use/greploop-appsif Greptile says too many files changed). If Greptile is not installed on the repo or never responds, say so and skip this step.
Finish
- Do not merge the PR unless the user explicitly says to.
- Keep the worktree until the PR is merged or closed.
- End with: PR URL, one line per beat (done / skipped and why), and the Greptile score.
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.

