Install
$ agentstack add skill-etr-groundwork-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.
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
Orchestrator for the ship phase — the last leg of the lifecycle, after the change is built, validated, and reviewed. It sequences the ship disciplines and stops at a human go/no-go before anything reaches users.
Step 1: Confirm Validation and Review Passed
Shipping presupposes a clean change. Confirm both gates already cleared:
- Validation passed — see [[validate]].
- Review passed — see [[review-pr]].
Check for evidence (a green validation run, an approved PR). If you cannot confirm either, stop and ask the user to run [[validate]] / [[review-pr]] first. Do not re-run them here; this skill assumes they are done.
Step 2: Sequence the Ship Disciplines
Dispatch the two disciplines in order via the Skill tool. Each is dual-tier, so this leaf may call them. Do not parallelize — the rollout depends on the instrumentation.
(Architecture decisions are recorded earlier, during design-architecture — there is no decision-capture step here.)
Skill(skill="groundwork:instrument-observability")— make the change observable (structured logs, RED metrics, trace spans, symptom alerts). Run before rollout: the rollout's monitoring window watches these signals.Skill(skill="groundwork:staged-rollout")— produce the pre-launch checklist, feature-flag gating, the staged/canary ramp, and the written rollback plan.
Carry each skill's verification result forward. If any reports its Verification incomplete, surface that to the user at Step 3 rather than silently proceeding.
Step 3: Final Go / No-Go Gate
Before any outward-facing deploy step (flipping the canary flag on, promoting a stage, releasing), stop and ask the user with AskUserQuestion:
{
"questions": [{
"question": "Validation and review passed. Observability instrumented, staged rollout plan and rollback ready. Proceed to begin the rollout?",
"header": "Go / No-Go",
"options": [
{ "label": "Go", "description": "Begin the staged rollout starting at the canary stage" },
{ "label": "No-Go", "description": "Stop — something needs attention first" }
],
"multiSelect": false
}]
}
- No-Go → stop. Report what's outstanding; do not deploy.
- Go → proceed to begin the staged rollout (the canary stage) per the plan from Step 2. Never skip this gate, even if every prior step is green — a human owns the decision to expose the change to users.
Verification
- [ ] Validation and review were confirmed passed before any ship step ran
- [ ]
instrument-observabilitythenstaged-rolloutwere dispatched in that order - [ ] Each dispatched skill's Verification result was carried forward and any gaps surfaced
- [ ] The go/no-go
AskUserQuestiongate ran before any outward-facing deploy step - [ ] On No-Go, nothing was deployed; on Go, the rollout began at the canary stage
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: etr
- Source: etr/groundwork
- License: MIT
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.