arch-design
System-design thinking before any doc or code: goals/non-goals, back-of-envelope numbers, components and contracts, failure modes, operability, security,…
Run Ship's full production workflow from raw requirement to PR: design, dev, E2E, review, QA, refactor, and handoff. Use only for explicit /ship:auto, auto pipeline requests, or end-to-end delivery.
$ npx -y skills add heliohq/ship --skill auto --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/autoContext preview
The summary Claude sees to decide when to auto-load this skill.
Run Ship's full production workflow from raw requirement to PR: design, dev, E2E, review, QA, refactor, and handoff. Use only for explicit /ship:auto, auto pipeline requests, or end-to-end delivery.
name: auto version: 0.1.0 description: > Run Ship's full production workflow from raw requirement to PR: design, dev, E2E, review, QA, refactor, and handoff. Use only for explicit /ship:auto, auto pipeline requests, or end-to-end delivery. allowed-tools: - Bash - Read - Agent
Full staged workflow for explicit end-to-end production delivery.
Your cwd is the user's repo, not the plugin — a bare relative path will not find the orchestrator. Set `SKILL_DIR` to this skill's base directory (announced as "Base directory for this skill" when the skill loaded), then run the shared stage-aware orchestrator:
SKILL_DIR="<base directory from the skill invocation>" SHIP_ORCH="$SKILL_DIR/../../scripts/auto-orchestrate.sh" if [ -f .ship/ship-auto.local.md ]; then bash "$SHIP_ORCH" resume else bash "$SHIP_ORCH" init '<user requirement goes here>' fi
Then follow the `/ship:auto` dispatch loop: read `PROMPT_FILE`, dispatch the agent, classify the report card, and call `complete <PHASE>`.
`/ship:auto` is only for full end-to-end runs. For a single phase (design, dev, E2E, review, QA, refactor, handoff), invoke that `/ship:*` skill directly instead of routing through auto.
An agentic development harness for Claude Code & Codex: agent-routed workflows from raw requirement to green PR.
System-design thinking before any doc or code: goals/non-goals, back-of-envelope numbers, components and contracts, failure modes, operability, security,…
Plan implementation before coding: investigate the repo, write spec and plan, and validate with a peer. Use for "plan", "design approach", "scope", or any…
Implement from a spec or plan: extract stories, build in safe waves, test, commit, and get peer review per story. Use for "implement", "build/code this plan",…
Add durable end-to-end tests for user/API-visible behavior. Detect or scaffold the E2E framework, write tests, run the app, and store evidence. Use for E2E,…
Ship completed work: verify locally, commit related changes, push, create or update the PR, watch CI/reviews, and fix until merge-ready or escalated. Use for…