forge-ship
End-to-end implementation and self-review in a single invocation: implements from an Issue, plan file, or free-text description, then runs a lean fresh-context review. Asks the user to approve the plan and triage findings unless --unattended or --guard. With --guard it also waits for CI and peer review, addresses feedback until the PR is review-ready, and ends with a risk verdict (merge-ready or review-ready, or merged when the project opts in). Use when the user or an orchestrating agent asks for forge-ship or to ship an Issue as a reviewed PR, not for a quick edit in the current session.
How do I install this agent skill?
npx skills add https://github.com/mgratzer/forge --skill forge-shipIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill automates the full development lifecycle from implementation to landing pull requests. It involves executing local shell scripts, running project-specific setup commands, and processing external data from GitHub, which presents a surface for indirect prompt injection and involves standard development-related data movement.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 1 issue
What does this agent skill do?
Ship a Change
Implement a change, review it in fresh context, and push it. With --guard, carry the PR on to a terminal state.
Input
Same as forge-implement ($ARGUMENTS): Issue number/URL, plan file path, or free-text. Optional: -- <additional context>.
Unattended mode: --unattended skips plan approval and triages findings without asking. A run no person can answer is unattended too, as in forge-implement.
Guard mode: --guard continues after the PR is open with forge-guard, then forge-land (Step 4). Implies --unattended.
Process
Step 1: Implement
Execute the full forge-implement process with one modification: do not produce implement's summary. Step 5 reports everything once.
Step 2: Review (delegate)
Simplification pass: if the runtime provides a simplification skill (Claude Code: /simplify), invoke it on the branch diff and commit its edits before the review, so the review checks them. Otherwise skip it: the review's default checklist covers the same items.
Fresh-context review: run it however clean the change looks, following review-delegation. This session wrote the diff, so even a tiny one goes to a fresh-context reviewer.
Inputs provided to sub-agent: what review-delegation's Inputs Required lists. Expected output: Deduplicated findings grouped by file with severity tags (P0/P1/P2).
Step 3: Triage Findings
Attended (default): present each finding to the user with a recommendation, biased hard toward fix now: defer only what materially expands the PR's scope or is truly out of scope.
Unattended: triage per Unattended Triage.
Commit the fixes and push once, together with any Step 2 simplification commit, even when nothing needed fixing. Deferred items become Issues, per issue-operations.
Step 4: Guard and Land (only with --guard)
Without --guard, report pushed via status-reporting: the PR is open and self-reviewed, and the human takes it from there.
With --guard, run the full forge-guard process on the PR from Step 1. When it ends at needs-human, that is this skill's terminal state. When it reaches review-ready, don't report that state: run the full forge-land process on the same PR, and its terminal state (merged only with the project's auto-merge opt-in, merge-ready, review-ready or needs-human) is this skill's.
Step 5: Summarize
Report implementation, review, guard, and land results together.
Output Format
## Ship Summary
**PR:** #<number>: <title>
**Branch:** <branch-name>
**Result:** pushed | merged | merge-ready | review-ready | needs-human (<reason>)
### Implementation
- <N> commits, <M> files changed
- Tests: <added/modified/none>
- Docs: <updated/none>
- Exercised: <intended | wrong: <observed vs expected> | not exercised: <why>> (plus "not run: <parts>" when parts were skipped)
- Try it: <the `Try it` line from `## Exercised`> (omit when the section has none)
### Review Findings
- Simplify: applied <n> edits | nothing to simplify | covered by review (no simplification skill)
- Fixed in PR: <list or "none">
- Deferred: #<issue> (<title>), or "none"
### Guard (guard mode only: the Passes, Rounds, and Open sections from forge-guard; Result above is authoritative)
### Land (guard mode only, when guard reached review-ready: Judged, Checks, Review requested, and Label from forge-land)
### Quality Gates
- Lint: ✓/✗
- Format: ✓/✗
- Types: ✓/✗
- Tests: ✓/✗
- Coverage: ✓/✗/not configured
Related Skills
Components: Composes forge-implement, the fresh-context review flow shared with forge-reflect (_shared/review-delegation.md), and forge-guard followed by forge-land when --guard is set.
After peer review: Use forge-address-pr-feedback to address reviewer comments (guard mode does this for you).
Example Usage
/forge-ship 42
/forge-ship 42 -- keep the diff minimal
/forge-ship docs/roadmap.md
/forge-ship --unattended 42
/forge-ship --guard 42
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/mgratzer/forge/forge-ship">View forge-ship on skillZs</a>