Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Package and finalize completed work for delivery — use when a feature is done and ready to ship
.claude/skills/hashgraph-online-skill-ship/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | 186% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 252% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 404% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 120% | 0% |
> Host: Codex CLI — This skill was designed for Claude Code and adapted for Codex. > Cross-reference commands use installed skill names in Codex rather than /octo:* slash commands. > Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it. > For host tool equivalents, see skills/blocks/codex-host-adapter.md.
Finalize and deliver completed work with Multi-AI security audit, lessons capture, and archival.
Core principle: Verify ready -> Multi-AI audit -> Capture lessons -> Archive -> Ship.
Use this skill when user asks:
Do NOT use for:
bashif [[ ! -d ".octo" ]]; then echo "No project initialized" exit 1 fi
If .octo/ does not exist:
markdown## Cannot Ship **Status:** No project initialized No Claude Octopus project found in this directory. Run `/octo:embrace [description]` to start a new project.
STOP. Do not proceed.
bash# Check if STATE.md exists and read status if [[ -f ".octo/STATE.md" ]]; then # Read current status STATUS=$(grep -E "^status:" .octo/STATE.md | cut -d':' -f2 | xargs || echo "unknown") CURRENT_PHASE=$(grep -E "^current_phase:" .octo/STATE.md | cut -d':' -f2 | xargs || echo "unknown") else STATUS="unknown" CURRENT_PHASE="unknown" fi echo "Status: $STATUS" echo "Current Phase: $CURRENT_PHASE"
Ship is allowed when:
status = "complete" ORcurrent_phase = "4" (Deliver phase) ORIf not ready:
markdown## Project Not Ready to Ship **Current Status:** {status} **Current Phase:** {current_phase} ### To prepare for shipping: 1. Complete remaining phases: - [ ] Phase 1: Discover - Use `/octo:discover` - [ ] Phase 2: Define - Use `/octo:define` - [ ] Phase 3: Develop - Use `/octo:develop` - [ ] Phase 4: Deliver - Use `/octo:deliver` 2. Or override with: "ship anyway" (not recommended)
STOP unless user says "ship anyway".
bash# Check provider availability command -v codex &> /dev/null && codex_status="Available" || codex_status="Not installed" command -v agy &> /dev/null && agy_status="Available" || agy_status="Not installed"
Output:
markdown## Multi-AI Security Audit **Providers:** - Codex CLI: ${codex_status} - Code security analysis - Antigravity CLI: ${agy_status} - Additional external-model challenge - Claude: Available - Synthesis and final validation **Estimated Time:** 3-5 minutes **Estimated Cost:** $0.02-0.08
You MUST execute this via native shell command tool:
bash# Run Multi-AI security audit for delivery "${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh" ink "Security audit for delivery - comprehensive review of all code changes for production readiness"
CRITICAL: You are PROHIBITED from:
bash# Find the latest validation file VALIDATION_FILE=$(find ~/.claude-octopus/results -name "ink-validation-*.md" -mmin -10 2>/dev/null | head -n1) if [[ -z "$VALIDATION_FILE" ]]; then echo "AUDIT FAILED: No validation file found" exit 1 fi echo "AUDIT COMPLETE: $VALIDATION_FILE"
Read validation file and present:
If FAILED with critical issues:
markdown## Audit Failed - Cannot Ship Critical issues must be resolved before shipping: 1. [Issue 1 from validation] 2. [Issue 2 from validation] Resolve issues and run `/octo:ship` again.
STOP if critical issues found.
markdown## Lessons Learned Before finalizing, let's capture what we learned from this project. **Please answer the following:** 1. **What went well?** (What worked better than expected?) 2. **What could improve?** (What would you do differently?) 3. **Key learnings?** (What insights will you carry forward?) *Reply with your answers, or type "skip" to proceed without capturing lessons.*
Wait for user response.
If user provides lessons (not "skip"):
bash# Generate timestamp TIMESTAMP=$(date '+%Y-%m-%d') # Ensure LESSONS.md exists touch .octo/LESSONS.md # Append lessons cat >> .octo/LESSONS.md << EOF ## ${TIMESTAMP} - Project Delivery ### What Went Well - ${USER_WHAT_WENT_WELL} ### What Could Improve - ${USER_WHAT_COULD_IMPROVE} ### Key Learnings - ${USER_KEY_LEARNINGS} EOF
Count total lessons:
bashLESSON_COUNT=$(grep -c "^## " .octo/LESSONS.md 2>/dev/null || echo "0") echo "Total lessons captured: $LESSON_COUNT"
bash# Generate timestamp for archive ARCHIVE_TIMESTAMP=$(date +%Y%m%d-%H%M%S) ARCHIVE_DIR=".octo/archive/${ARCHIVE_TIMESTAMP}" # Create archive directory mkdir -p "$ARCHIVE_DIR"
bash# Archive STATE.md if exists if [[ -f ".octo/STATE.md" ]]; then cp .octo/STATE.md "$ARCHIVE_DIR/" fi # Archive PROJECT.md if exists if [[ -f ".octo/PROJECT.md" ]]; then cp .octo/PROJECT.md "$ARCHIVE_DIR/" fi # Archive ROADMAP.md if exists if [[ -f ".octo/ROADMAP.md" ]]; then cp .octo/ROADMAP.md "$ARCHIVE_DIR/" fi # Archive ISSUES.md if exists if [[ -f ".octo/ISSUES.md" ]]; then cp .octo/ISSUES.md "$ARCHIVE_DIR/" fi echo "Archived to: $ARCHIVE_DIR"
IMPORTANT: NEVER archive LESSONS.md - lessons are preserved across projects.
bash# List archived files ls -la "$ARCHIVE_DIR"
bash# Update status to shipped sed -i '' 's/^status:.*/status: shipped/' .octo/STATE.md 2>/dev/null || \ sed -i 's/^status:.*/status: shipped/' .octo/STATE.md # Append history entry cat >> .octo/STATE.md << EOF ## History - $(date '+%Y-%m-%d %H:%M') - **Event:** Project shipped - **Archive:** .octo/archive/${ARCHIVE_TIMESTAMP}/ - **Validation:** ${VALIDATION_FILE} EOF
bash# Create git checkpoint tag CHECKPOINT_TAG="octo-checkpoint-shipped-${ARCHIVE_TIMESTAMP}" git tag -a "$CHECKPOINT_TAG" -m "Project shipped - $(date '+%Y-%m-%d %H:%M:%S')" echo "Checkpoint created: $CHECKPOINT_TAG"
bash# Count resolved issues ISSUES_RESOLVED=$(grep -c "^\- \[x\]" .octo/ISSUES.md 2>/dev/null || echo "0") # Count total lessons LESSONS_COUNT=$(grep -c "^## " .octo/LESSONS.md 2>/dev/null || echo "0") echo "Issues resolved: $ISSUES_RESOLVED" echo "Lessons captured: $LESSONS_COUNT"
Present final summary:
markdown## Project Shipped! **Delivered:** {timestamp} **Phases Completed:** 4/4 **Issues Resolved:** {ISSUES_RESOLVED} **Lessons Captured:** {LESSONS_COUNT} ### Multi-AI Audit Summary - **Security Score:** {score}/100 - **Quality Score:** {score}/100 - **Providers Used:** Claude plus available external providers ### Archive Location: `.octo/archive/{ARCHIVE_TIMESTAMP}/` Contents: - STATE.md - PROJECT.md - ROADMAP.md - ISSUES.md ### Checkpoint Tag: `{CHECKPOINT_TAG}` Restore with: `/octo:rollback {CHECKPOINT_TAG}` **To start a new project:** `/octo:embrace` *Multi-AI validation powered by Claude Octopus* *Providers: Codex | Antigravity | Claude*
| Error | Resolution | |-------|------------| | No .octo/ directory | Suggest /octo:embrace | | Project not ready | Show remaining phases | | orchestrate.sh fails | Show error logs, suggest retry | | Critical audit issues | Block ship, show issues | | Git tag fails | Warn but continue (non-blocking) |
| Measure | Implementation | |---------|----------------| | Pre-ship audit | orchestrate.sh Multi-AI validation required | | Lessons preservation | LESSONS.md never archived, always preserved | | Archive before ship | State files copied to archive directory | | Git checkpoint | Tag created for rollback capability | | No file deletion | Archive copies, doesn't delete source files |
User runs /octo:deliver to validate
→ Deliver phase complete
→ User runs /octo:ship to finalizeUser ships project
→ Checkpoint created
→ Later: /octo:rollback octo-checkpoint-shipped-*After ship: status shows "shipped"
→ Suggests /octo:embrace for new project| Action | Why It's Wrong | |--------|----------------| | Skip Multi-AI audit | Security vulnerabilities missed | | Archive LESSONS.md | Loses accumulated project knowledge | | Delete source files | Should copy, not move | | Ship without ready check | Incomplete work shipped | | Skip checkpoint creation | No rollback recovery path |
| Step | Command | Purpose | |------|---------|---------| | 1 | Check .octo/STATE.md | Verify ready to ship | | 2 | orchestrate.sh ink | Multi-AI security audit | | 3 | Ask user | Capture lessons learned | | 4 | mkdir + cp | Archive state files | | 5 | Update STATE.md | Mark as shipped | | 6 | git tag | Create shipped checkpoint |
Ship → Ready + Audit passed + Lessons captured + Archived + Checkpoint created
Otherwise → Not shippedVerify ready. Run Multi-AI audit. Capture lessons. Archive state. Create checkpoint. Ship.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 17,556 | 16,417 | -6% | 1 | 1 | 0% | 358 | 3,451 | +864% | 0 | 0 | — |
case-02 | fail→fail | 18,483 | 14,978 | -19% | 1 | 1 | 0% | 2,322 | 3,255 | +40% | 0 | 0 | — |
case-03 | fail→fail | 19,402 | 11,645 | -40% | 1 | 1 | 0% | 3,446 | 3,334 | -3% | 0 | 0 | — |
case-04 | pass→fail | 5,379 | 10,803 | +101% | 1 | 1 | 0% | 960 | 3,417 | +256% | 0 | 0 | — |
case-05 | pass→fail | 16,981 | 6,131 | -64% | 1 | 1 | 0% | 2,824 | 3,318 | +17% | 0 | 0 | — |
case-06 | pass→pass | 22,781 | 37,114 | +63% | 1 | 1 | 0% | 3,430 | 8,739 | +155% | 0 | 0 | — |
case-07 | fail→fail | 4,461 | 8,065 | +81% | 1 | 1 | 0% | 270 | 3,364 | +1146% | 0 | 0 | — |
case-08 | fail→fail | 21,365 | 10,823 | -49% | 1 | 1 | 0% | 2,740 | 3,313 | +21% | 0 | 0 | — |
case-09 | fail→fail | 16,544 | 11,875 | -28% | 1 | 1 | 0% | 1,838 | 3,399 | +85% | 0 | 0 | — |
case-10 | fail→fail | 7,290 | 14,272 | +96% | 1 | 1 | 0% | 799 | 4,269 | +434% | 0 | 0 | — |
case-11 | fail→fail | 9,233 | 6,388 | -31% | 1 | 1 | 0% | 1,422 | 3,327 | +134% | 0 | 0 | — |
case-12 | fail→fail | 14,491 | 33,707 | +133% | 1 | 1 | 0% | 1,503 | 3,930 | +161% | 0 | 0 | — |
case-13 | fail→pass | 12,601 | 2,761 | -78% | 1 | 1 | 0% | 1,230 | 3,519 | +186% | 0 | 0 | — |
case-14 | pass→pass | 13,580 | 3,537 | -74% | 1 | 1 | 0% | 1,550 | 3,658 | +136% | 0 | 0 | — |
case-15 | pass→pass | 12,182 | 9,638 | -21% | 1 | 1 | 0% | 2,020 | 3,876 | +92% | 0 | 0 | — |
case-16 | fail→pass | 11,933 | 4,501 | -62% | 1 | 1 | 0% | 1,123 | 3,953 | +252% | 0 | 0 | — |
case-17 | fail→pass | 4,020 | 2,943 | -27% | 1 | 1 | 0% | 718 | 3,622 | +404% | 0 | 0 | — |
case-18 | fail→pass | 15,474 | 9,351 | -40% | 1 | 1 | 0% | 2,657 | 3,933 | +48% | 0 | 0 | — |
case-19 | fail→fail | 13,250 | 12,653 | -5% | 1 | 1 | 0% | 2,284 | 4,126 | +81% | 0 | 0 | — |
case-20 | fail→fail | 5,081 | 5,661 | +11% | 1 | 1 | 0% | 806 | 3,360 | +317% | 0 | 0 | — |
case-21 | fail→pass | 8,600 | 2,835 | -67% | 1 | 1 | 0% | 1,581 | 3,472 | +120% | 0 | 0 | — |
case-22 | fail→fail | 12,146 | 7,122 | -41% | 1 | 1 | 0% | 1,345 | 3,346 | +149% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 12 counted toward the lift figure. The other 10 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +14 percentage points is the difference between those two pass rates over the 12 comparable cases. 5 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.