Ship
Plan launch readiness, staged rollouts, production monitoring, rollback, communications, and post-launch validation. Use when the user asks for `/ship`, pre-launch checklists, release readiness, staged rollout plans, feature flags, deployment monitoring, or rollback planning.
Install
$ agentstack add skill-eigent-ai-agent-skills-ship ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-eigent-ai-agent-skills-ship) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Ship
Overview
Use this skill to prepare a feature or change for production. The goal is to make launch decisions explicit: what ships, how it rolls out, what is monitored, when to stop, and how to recover.
Workflow
- Identify the release scope, owner, timeline, users affected, dependencies, and risk level.
- Build a pre-launch checklist:
- Tests, migrations, feature flags, documentation, support readiness, analytics, alerts, and runbooks.
- Define rollout strategy:
- Internal, beta, percentage rollout, region/account cohorts, or all-at-once when low risk.
- Specify success metrics and guardrails:
- Product metrics, reliability metrics, error rates, latency, revenue, support volume, and user feedback.
- Create rollback and mitigation steps:
- Flag disablement, revert path, data repair, comms, and owner escalation.
- Plan launch communications for affected teams and users.
- After launch, compare live metrics against expected ranges and decide whether to continue, pause, expand, or roll back.
Output Pattern
- Release summary.
- Pre-launch checklist.
- Rollout stages and entry/exit criteria.
- Monitoring plan.
- Rollback plan.
- Communications plan.
- Post-launch validation steps.
Example Prompts
/ship - We're deploying the new payments flow tomorrow. Walk me through the pre-launch checklist, what to monitor in the first hour, and our rollback plan if error rates spike./ship - Plan a staged rollout for our new recommendation engine. Start at 5% traffic, define success metrics, and set the criteria for each expansion step to 100%./ship - We shipped 3 hours ago. Here are the current metrics [paste]. Is anything outside normal range? Should we roll back or keep going?
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: eigent-ai
- Source: eigent-ai/agent-skills
- License: Apache-2.0
- Homepage: https://www.eigent.ai/skills
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.