agentleFS
Sign inStart free
cloverinkcloverink/shipwright/skills/push/SKILL.md

push

Skill0 starsChanged 49 days agoMITView on GitHub

Smart commit + push + auto-create PR. Blocks push to main. When called from /ship (bundled mode), verifies the ship gates and only opens the PR.

  • Commits and pushes

49 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use get-pr-reviews, push-everything and 9 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.
  • saffron-healthSkill

    get-pr-reviews

    Get nicely formatted output of the last review comments on a PR. Used internally by other skills.

    Also in 3 projects that use this

  • saffron-healthSkill

    push-everything

    Stage ALL changes in the repository (not just session changes), commit, and push. Use when you need to commit all pending changes.

    Also in 3 projects that use this

  • NVIDIASkill

    generate-spec

    Produce a feature specification covering API changes, backward compatibility, cross-language impact, performance, and a file-level change plan. Use when designing a new feature, planning a significant change, or the user asks to spec something out.

    Also in 3 projects that use this

  • ddehartSkill

    knowledge-graph

    Search, capture, and query the claude-code-plugins knowledge graph. Use when asked to "capture this", "add this to the graph", "what do we know about X", "update the graph", "check the graph for X", or when a decision, pattern, or non-obvious fact surfaces mid-session that's worth recording. Also: "log an observation", "what patterns do we have about skill triggering", "any decisions on the knowledge-commons plugin", "what do we know about the commit-creator agent".

    Also in 3 projects that use this

  • anombyte93Skill

    discover

    Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.

    Also in 4 projects that use this

  • MicrosoftSkill

    merge

    Merge changes from the topic branch to the merge base branch. Use when the user wants to merge their session's work back to the base branch.

    Also in 3 projects that use this

  • +2 more from saffron-health

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    PR: if no open PR exists, create one with template

    line 18
  2. Very specific:

    if a PR already exists for the branch, updates its body instead (gh pr edit --body-file)

    line 36
  3. Very specific:

    Before opening the PR, /push verifies:

    line 40
  4. Distinctive:

    Never pushes to main: always feature branches

    line 61
  5. Distinctive:

    Never force pushes: always regular push

    line 62
  6. Distinctive:

    Never skips hooks: if pre-push hook fails, fix the issue

    line 63

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/push

Safe push with guard rails. Commits, pushes, and opens a PR if one doesn't exist.

Workflow

  1. Safety check: refuse if on main branch
  2. Stage changes: git add relevant files (never -A blindly)
  3. Commit: conventional commit format, auto-detect type from diff
  4. Rebase: git pull --rebase origin main to stay current
  5. Push: git push -u origin <branch>
  6. PR: if no open PR exists, create one with template

Conventional Commits

<type>(<scope>): <subject>

Types: feat, fix, docs, style, refactor, perf, test, chore
<!-- CONFIGURE: Adjust scopes to match your project (e.g., www, api, docs) -->

Bundling behavior (called from /ship)

/ship Phase S has already committed, rebased and pushed. In bundled mode /push:

  • skips steps 2-5 (no stage, commit, rebase or push)
  • verifies the gates below, then only runs step 6 with the PR body /ship hands over
  • if a PR already exists for the branch, updates its body instead (gh pr edit --body-file)

Pre-flight Gates (bundled mode)

Before opening the PR, /push verifies:

GateRequirement
Code reviewScore ≥ 9.5 (Opus code-reviewer)
UX reviewScore = 10/10 (if frontend changed)
Working treeClean (no uncommitted changes)
<!-- CONFIGURE: Adjust gate thresholds or remove gates you don't need -->

PR Template

Auto-generated PR body includes:

  • Summary (1-3 bullet points from commits)
  • Test plan checklist
  • Round table from /ship: per round, which reviewer ran (continued or fresh), the score, and what was fixed
  • Leftover Suggestions the gates allowed through, for the human reviewer
  • Phases that came back clean (instead of empty commits)

Safety Rules

  • Never pushes to main: always feature branches
  • Never force pushes: always regular push
  • Never skips hooks: if pre-push hook fails, fix the issue

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free