[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MKCMX60MDQ36FH2WN23K50":3,"skill-same:01M6MKCMX60MDQ36FH2WN23K50":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":50,"updatedAt":51,"install":52,"resources":64},"01M6MKCMX60MDQ36FH2WN23K50","skill-ship",null,"Package and finalize completed work for delivery — use when a feature is done and ready to ship","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-ship\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35],"ship","skill ship","ready","done","work","delivery","feature","for","true","package","use","when","2026-11-10 10:12:30",false,"---\nname: skill-ship\ndescription: \"Package and finalize completed work for delivery — use when a feature is done and ready to ship\"\ndisable-model-invocation: true\n---\n\n> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.\n> Cross-reference commands use installed skill names in Codex rather than `\u002Focto:*` slash commands.\n> 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.\n> For host tool equivalents, see `skills\u002Fblocks\u002Fcodex-host-adapter.md`.\n\n\n# Ship Project - Multi-AI Delivery Validation\n\nFinalize and deliver completed work with Multi-AI security audit, lessons capture, and archival.\n\n**Core principle:** Verify ready -> Multi-AI audit -> Capture lessons -> Archive -> Ship.\n\n\n## When to Use\n\n**Use this skill when user asks:**\n- \"Ship the project\" or \"We're done\"\n- \"Finalize this\" or \"Let's deliver\"\n- \"Complete the project\" or \"Ready to ship\"\n- \"Mark as shipped\" or \"Time to deliver\"\n\n**Do NOT use for:**\n- Code review (use \u002Focto:review or flow-deliver)\n- Implementation (use \u002Focto:develop)\n- Research (use \u002Focto:research)\n\n\n## The Process\n\n### Phase 1: Verify Project Ready to Ship\n\n#### Step 1: Check .octo\u002F Exists\n\n```bash\nif [[ ! -d \".octo\" ]]; then\n    echo \"No project initialized\"\n    exit 1\nfi\n```\n\n**If .octo\u002F does not exist:**\n\n```markdown\n## Cannot Ship\n\n**Status:** No project initialized\n\nNo Claude Octopus project found in this directory.\n\nRun `\u002Focto:embrace [description]` to start a new project.\n```\n\n**STOP. Do not proceed.**\n\n#### Step 2: Read STATE.md Status\n\n```bash\n# Check if STATE.md exists and read status\nif [[ -f \".octo\u002FSTATE.md\" ]]; then\n    # Read current status\n    STATUS=$(grep -E \"^status:\" .octo\u002FSTATE.md | cut -d':' -f2 | xargs || echo \"unknown\")\n    CURRENT_PHASE=$(grep -E \"^current_phase:\" .octo\u002FSTATE.md | cut -d':' -f2 | xargs || echo \"unknown\")\nelse\n    STATUS=\"unknown\"\n    CURRENT_PHASE=\"unknown\"\nfi\n\necho \"Status: $STATUS\"\necho \"Current Phase: $CURRENT_PHASE\"\n```\n\n#### Step 3: Validate Ready State\n\n**Ship is allowed when:**\n- `status` = \"complete\" OR\n- `current_phase` = \"4\" (Deliver phase) OR\n- All four phases have entries in STATE.md history\n\n**If not ready:**\n\n```markdown\n## Project Not Ready to Ship\n\n**Current Status:** {status}\n**Current Phase:** {current_phase}\n\n### To prepare for shipping:\n\n1. Complete remaining phases:\n   - [ ] Phase 1: Discover - Use `\u002Focto:discover`\n   - [ ] Phase 2: Define - Use `\u002Focto:define`\n   - [ ] Phase 3: Develop - Use `\u002Focto:develop`\n   - [ ] Phase 4: Deliver - Use `\u002Focto:deliver`\n\n2. Or override with: \"ship anyway\" (not recommended)\n```\n\n**STOP unless user says \"ship anyway\".**\n\n\n### Phase 2: Multi-AI Security Audit\n\n#### Step 1: Display Visual Indicators\n\n```bash\n# Check provider availability\ncommand -v codex &> \u002Fdev\u002Fnull && codex_status=\"Available\" || codex_status=\"Not installed\"\ncommand -v agy &> \u002Fdev\u002Fnull && agy_status=\"Available\" || agy_status=\"Not installed\"\n```\n\n**Output:**\n\n```markdown\n## Multi-AI Security Audit\n\n**Providers:**\n- Codex CLI: ${codex_status} - Code security analysis\n- Antigravity CLI: ${agy_status} - Additional external-model challenge\n- Claude: Available - Synthesis and final validation\n\n**Estimated Time:** 3-5 minutes\n**Estimated Cost:** 0.02-0.08 USD\n```\n\n#### Step 2: Execute orchestrate.sh Security Audit\n\n**You MUST execute this via native shell command tool:**\n\nUse the installation that loaded this skill for both execution and validation.\nIf `CLAUDE_PLUGIN_ROOT` is absent, replace the `OCTO_ROOT` fallback below with\nthe absolute plugin root derived from this loaded skill's path. Do not infer it\nfrom the project directory or an existing stable link. The root helper refreshes\ninstalled copies while preserving another session's working root when called\nfrom an inferred development checkout.\n\n```bash\n# Run Multi-AI security audit for delivery\nOCTO_ROOT=\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\"\nbash \"$OCTO_ROOT\u002Fscripts\u002Fhelpers\u002Fensure-plugin-root.sh\" || exit 1\nRUN_MARKER=$(mktemp) || exit 1\nRUN_STATUS=0\nOCTOPUS_WORKFLOW_INVOCATION_ID=\"${RUN_MARKER##*\u002F}\" \"$OCTO_ROOT\u002Fscripts\u002Forchestrate.sh\" ink \"Security audit for delivery - comprehensive review of all code changes for production readiness\" || RUN_STATUS=$?\nREPORT_STATUS=0\nVALIDATION_FILE=$(\"$OCTO_ROOT\u002Fscripts\u002Fhelpers\u002Fworkflow-result.sh\" ink \"$RUN_MARKER\" \"$RUN_STATUS\") || REPORT_STATUS=$?\nrm -f \"$RUN_MARKER\"\n[[ \"$REPORT_STATUS\" == 0 ]] || exit \"$REPORT_STATUS\"\necho \"AUDIT COMPLETE: $VALIDATION_FILE\"\n```\n\n## MANDATORY COMPLIANCE\n\n**CRITICAL: You are PROHIBITED from:**\n- Skipping Multi-AI validation\n- Doing single-provider analysis instead\n- Claiming you're \"simulating\" the audit\n- Proceeding without running orchestrate.sh\n\n#### Step 3: Verify Audit Completed\n\nStep 2 must exit successfully and validate a fresh `delivery-*.md` report\nwhose launcher status is `COMPLETE`. A report from a previous deliver run,\na partial report, or a failed command cannot pass this audit.\nUse the exact validated path printed by Step 2 for the summary.\n\n#### Step 4: Display Audit Summary\n\nRead validation file and present:\n- Overall status (PASSED \u002F PASSED WITH WARNINGS \u002F FAILED)\n- Quality score\n- Critical issues (must fix before ship)\n- Warnings (should fix)\n\n**If FAILED with critical issues:**\n```markdown\n## Audit Failed - Cannot Ship\n\nCritical issues must be resolved before shipping:\n\n1. [Issue 1 from validation]\n2. [Issue 2 from validation]\n\nResolve issues and run `\u002Focto:ship` again.\n```\n\n**STOP if critical issues found.**\n\n\n### Phase 3: Capture Lessons Learned\n\n#### Step 1: Ask User for Lessons\n\n```markdown\n## Lessons Learned\n\nBefore finalizing, let's capture what we learned from this project.\n\n**Please answer the following:**\n\n1. **What went well?** (What worked better than expected?)\n\n2. **What could improve?** (What would you do differently?)\n\n3. **Key learnings?** (What insights will you carry forward?)\n\n*Reply with your answers, or type \"skip\" to proceed without capturing lessons.*\n```\n\n**Wait for user response.**\n\n#### Step 2: Append to LESSONS.md\n\nIf user provides lessons (not \"skip\"):\n\n```bash\n# Generate timestamp\nTIMESTAMP=$(date '+%Y-%m-%d')\n\n# Ensure LESSONS.md exists\ntouch .octo\u002FLESSONS.md\n\n# Append lessons\ncat >> .octo\u002FLESSONS.md \u003C\u003C EOF\n\n## ${TIMESTAMP} - Project Delivery\n\n### What Went Well\n- ${USER_WHAT_WENT_WELL}\n\n### What Could Improve\n- ${USER_WHAT_COULD_IMPROVE}\n\n### Key Learnings\n- ${USER_KEY_LEARNINGS}\n\nEOF\n```\n\n**Count total lessons:**\n```bash\nLESSON_COUNT=$(grep -c \"^## \" .octo\u002FLESSONS.md 2>\u002Fdev\u002Fnull || echo \"0\")\necho \"Total lessons captured: $LESSON_COUNT\"\n```\n\n\n### Phase 4: Archive Project State\n\n#### Step 1: Create Archive Directory\n\n```bash\n# Generate timestamp for archive\nARCHIVE_TIMESTAMP=$(date +%Y%m%d-%H%M%S)\nARCHIVE_DIR=\".octo\u002Farchive\u002F${ARCHIVE_TIMESTAMP}\"\n\n# Create archive directory\nmkdir -p \"$ARCHIVE_DIR\"\n```\n\n#### Step 2: Copy State Files to Archive\n\n```bash\n# Archive STATE.md if exists\nif [[ -f \".octo\u002FSTATE.md\" ]]; then\n    cp .octo\u002FSTATE.md \"$ARCHIVE_DIR\u002F\"\nfi\n\n# Archive PROJECT.md if exists\nif [[ -f \".octo\u002FPROJECT.md\" ]]; then\n    cp .octo\u002FPROJECT.md \"$ARCHIVE_DIR\u002F\"\nfi\n\n# Archive ROADMAP.md if exists\nif [[ -f \".octo\u002FROADMAP.md\" ]]; then\n    cp .octo\u002FROADMAP.md \"$ARCHIVE_DIR\u002F\"\nfi\n\n# Archive ISSUES.md if exists\nif [[ -f \".octo\u002FISSUES.md\" ]]; then\n    cp .octo\u002FISSUES.md \"$ARCHIVE_DIR\u002F\"\nfi\n\necho \"Archived to: $ARCHIVE_DIR\"\n```\n\n**IMPORTANT: NEVER archive LESSONS.md** - lessons are preserved across projects.\n\n#### Step 3: Verify Archive\n\n```bash\n# List archived files\nls -la \"$ARCHIVE_DIR\"\n```\n\n\n### Phase 5: Create Delivery Summary\n\n#### Step 1: Update STATE.md\n\n```bash\n# Update status to shipped\nsed -i '' 's\u002F^status:.*\u002Fstatus: shipped\u002F' .octo\u002FSTATE.md 2>\u002Fdev\u002Fnull || \\\n    sed -i 's\u002F^status:.*\u002Fstatus: shipped\u002F' .octo\u002FSTATE.md\n\n# Append history entry\ncat >> .octo\u002FSTATE.md \u003C\u003C EOF\n\n## History - $(date '+%Y-%m-%d %H:%M')\n\n- **Event:** Project shipped\n- **Archive:** .octo\u002Farchive\u002F${ARCHIVE_TIMESTAMP}\u002F\n- **Validation:** ${VALIDATION_FILE}\n\nEOF\n```\n\n#### Step 2: Create Shipped Checkpoint\n\n```bash\n# Create git checkpoint tag\nCHECKPOINT_TAG=\"octo-checkpoint-shipped-${ARCHIVE_TIMESTAMP}\"\n\ngit tag -a \"$CHECKPOINT_TAG\" -m \"Project shipped - $(date '+%Y-%m-%d %H:%M:%S')\"\n\necho \"Checkpoint created: $CHECKPOINT_TAG\"\n```\n\n#### Step 3: Count Metrics\n\n```bash\n# Count resolved issues\nISSUES_RESOLVED=$(grep -c \"^\\- \\[x\\]\" .octo\u002FISSUES.md 2>\u002Fdev\u002Fnull || echo \"0\")\n\n# Count total lessons\nLESSONS_COUNT=$(grep -c \"^## \" .octo\u002FLESSONS.md 2>\u002Fdev\u002Fnull || echo \"0\")\n\necho \"Issues resolved: $ISSUES_RESOLVED\"\necho \"Lessons captured: $LESSONS_COUNT\"\n```\n\n\n### Phase 6: Display Completion\n\nPresent final summary:\n\n```markdown\n## Project Shipped!\n\n**Delivered:** {timestamp}\n**Phases Completed:** 4\u002F4\n**Issues Resolved:** {ISSUES_RESOLVED}\n**Lessons Captured:** {LESSONS_COUNT}\n\n### Multi-AI Audit Summary\n\n- **Security Score:** {score}\u002F100\n- **Quality Score:** {score}\u002F100\n- **Providers Used:** Claude plus available external providers\n\n### Archive\n\nLocation: `.octo\u002Farchive\u002F{ARCHIVE_TIMESTAMP}\u002F`\n\nContents:\n- STATE.md\n- PROJECT.md\n- ROADMAP.md\n- ISSUES.md\n\n### Checkpoint\n\nTag: `{CHECKPOINT_TAG}`\n\nRestore with: `\u002Focto:rollback {CHECKPOINT_TAG}`\n\n\n**To start a new project:** `\u002Focto:embrace`\n\n*Multi-AI validation powered by Claude Octopus*\n*Providers: Codex | Antigravity | Claude*\n```\n\n\n## Error Handling\n\n| Error | Resolution |\n|-------|------------|\n| No .octo\u002F directory | Suggest `\u002Focto:embrace` |\n| Project not ready | Show remaining phases |\n| orchestrate.sh fails | Show error logs, suggest retry |\n| Critical audit issues | Block ship, show issues |\n| Git tag fails | Warn but continue (non-blocking) |\n\n\n## Safety Measures\n\n| Measure | Implementation |\n|---------|----------------|\n| **Pre-ship audit** | orchestrate.sh Multi-AI validation required |\n| **Lessons preservation** | LESSONS.md never archived, always preserved |\n| **Archive before ship** | State files copied to archive directory |\n| **Git checkpoint** | Tag created for rollback capability |\n| **No file deletion** | Archive copies, doesn't delete source files |\n\n\n## Integration with Other Skills\n\n### With \u002Focto:deliver\n\n```\nUser runs \u002Focto:deliver to validate\n→ Deliver phase complete\n→ User runs \u002Focto:ship to finalize\n```\n\n### With \u002Focto:rollback\n\n```\nUser ships project\n→ Checkpoint created\n→ Later: \u002Focto:rollback octo-checkpoint-shipped-*\n```\n\n### With \u002Focto:status\n\n```\nAfter ship: status shows \"shipped\"\n→ Suggests \u002Focto:embrace for new project\n```\n\n\n## Red Flags - Never Do\n\n| Action | Why It's Wrong |\n|--------|----------------|\n| Skip Multi-AI audit | Security vulnerabilities missed |\n| Archive LESSONS.md | Loses accumulated project knowledge |\n| Delete source files | Should copy, not move |\n| Ship without ready check | Incomplete work shipped |\n| Skip checkpoint creation | No rollback recovery path |\n\n\n## Quick Reference\n\n| Step | Command | Purpose |\n|------|---------|---------|\n| 1 | Check .octo\u002FSTATE.md | Verify ready to ship |\n| 2 | orchestrate.sh ink | Multi-AI security audit |\n| 3 | Ask user | Capture lessons learned |\n| 4 | mkdir + cp | Archive state files |\n| 5 | Update STATE.md | Mark as shipped |\n| 6 | git tag | Create shipped checkpoint |\n\n\n## The Bottom Line\n\n```\nShip → Ready + Audit passed + Lessons captured + Archived + Checkpoint created\nOtherwise → Not shipped\n```\n\n**Verify ready. Run Multi-AI audit. Capture lessons. Archive state. Create checkpoint. Ship.**\n","> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.\n> Cross-reference commands use installed skill names in Codex rather than `\u002Focto:*` slash commands.\n> 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.\n> For host tool equivalents, see `skills\u002Fblocks\u002Fcodex-host-adapter.md`.\n\n\n# Ship Project - Multi-AI Delivery Validation\n\nFinalize and deliver completed work with Multi-AI security audit, lessons capture, and archival.\n\n**Core principle:** Verify ready -> Multi-AI audit -> Capture lessons -> Archive -> Ship.\n\n\n## When to Use\n\n**Use this skill when user asks:**\n- \"Ship the project\" or \"We're done\"\n- \"Finalize this\" or \"Let's deliver\"\n- \"Complete the project\" or \"Ready to ship\"\n- \"Mark as shipped\" or \"Time to deliver\"\n\n**Do NOT use for:**\n- Code review (use \u002Focto:review or flow-deliver)\n- Implementation (use \u002Focto:develop)\n- Research (use \u002Focto:research)\n\n\n## The Process\n\n### Phase 1: Verify Project Ready to Ship\n\n#### Step 1: Check .octo\u002F Exists\n\n```bash\nif [[ ! -d \".octo\" ]]; then\n    echo \"No project initialized\"\n    exit 1\nfi\n```\n\n**If .octo\u002F does not exist:**\n\n```markdown\n## Cannot Ship\n\n**Status:** No project initialized\n\nNo Claude Octopus project found in this directory.\n\nRun `\u002Focto:embrace [description]` to start a new project.\n```\n\n**STOP. Do not proceed.**\n\n#### Step 2: Read STATE.md Status\n\n```bash\n# Check if STATE.md exists and read status\nif [[ -f \".octo\u002FSTATE.md\" ]]; then\n    # Read current status\n    STATUS=$(grep -E \"^status:\" .octo\u002FSTATE.md | cut -d':' -f2 | xargs || echo \"unknown\")\n    CURRENT_PHASE=$(grep -E \"^current_phase:\" .octo\u002FSTATE.md | cut -d':' -f2 | xargs || echo \"unknown\")\nelse\n    STATUS=\"unknown\"\n    CURRENT_PHASE=\"unknown\"\nfi\n\necho \"Status: $STATUS\"\necho \"Current Phase: $CURRENT_PHASE\"\n```\n\n#### Step 3: Validate Ready State\n\n**Ship is allowed when:**\n- `status` = \"complete\" OR\n- `current_phase` = \"4\" (Deliver phase) OR\n- All four phases have entries in STATE.md history\n\n**If not ready:**\n\n```markdown\n## Project Not Ready to Ship\n\n**Current Status:** {status}\n**Current Phase:** {current_phase}\n\n### To prepare for shipping:\n\n1. Complete remaining phases:\n   - [ ] Phase 1: Discover - Use `\u002Focto:discover`\n   - [ ] Phase 2: Define - Use `\u002Focto:define`\n   - [ ] Phase 3: Develop - Use `\u002Focto:develop`\n   - [ ] Phase 4: Deliver - Use `\u002Focto:deliver`\n\n2. Or override with: \"ship anyway\" (not recommended)\n```\n\n**STOP unless user says \"ship anyway\".**\n\n\n### Phase 2: Multi-AI Security Audit\n\n#### Step 1: Display Visual Indicators\n\n```bash\n# Check provider availability\ncommand -v codex &> \u002Fdev\u002Fnull && codex_status=\"Available\" || codex_status=\"Not installed\"\ncommand -v agy &> \u002Fdev\u002Fnull && agy_status=\"Available\" || agy_status=\"Not installed\"\n```\n\n**Output:**\n\n```markdown\n## Multi-AI Security Audit\n\n**Providers:**\n- Codex CLI: ${codex_status} - Code security analysis\n- Antigravity CLI: ${agy_status} - Additional external-model challenge\n- Claude: Available - Synthesis and final validation\n\n**Estimated Time:** 3-5 minutes\n**Estimated Cost:** 0.02-0.08 USD\n```\n\n#### Step 2: Execute orchestrate.sh Security Audit\n\n**You MUST execute this via native shell command tool:**\n\nUse the installation that loaded this skill for both execution and validation.\nIf `CLAUDE_PLUGIN_ROOT` is absent, replace the `OCTO_ROOT` fallback below with\nthe absolute plugin root derived from this loaded skill's path. Do not infer it\nfrom the project directory or an existing stable link. The root helper refreshes\ninstalled copies while preserving another session's working root when called\nfrom an inferred development checkout.\n\n```bash\n# Run Multi-AI security audit for delivery\nOCTO_ROOT=\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\"\nbash \"$OCTO_ROOT\u002Fscripts\u002Fhelpers\u002Fensure-plugin-root.sh\" || exit 1\nRUN_MARKER=$(mktemp) || exit 1\nRUN_STATUS=0\nOCTOPUS_WORKFLOW_INVOCATION_ID=\"${RUN_MARKER##*\u002F}\" \"$OCTO_ROOT\u002Fscripts\u002Forchestrate.sh\" ink \"Security audit for delivery - comprehensive review of all code changes for production readiness\" || RUN_STATUS=$?\nREPORT_STATUS=0\nVALIDATION_FILE=$(\"$OCTO_ROOT\u002Fscripts\u002Fhelpers\u002Fworkflow-result.sh\" ink \"$RUN_MARKER\" \"$RUN_STATUS\") || REPORT_STATUS=$?\nrm -f \"$RUN_MARKER\"\n[[ \"$REPORT_STATUS\" == 0 ]] || exit \"$REPORT_STATUS\"\necho \"AUDIT COMPLETE: $VALIDATION_FILE\"\n```\n\n## MANDATORY COMPLIANCE\n\n**CRITICAL: You are PROHIBITED from:**\n- Skipping Multi-AI validation\n- Doing single-provider analysis instead\n- Claiming you're \"simulating\" the audit\n- Proceeding without running orchestrate.sh\n\n#### Step 3: Verify Audit Completed\n\nStep 2 must exit successfully and validate a fresh `delivery-*.md` report\nwhose launcher status is `COMPLETE`. A report from a previous deliver run,\na partial report, or a failed command cannot pass this audit.\nUse the exact validated path printed by Step 2 for the summary.\n\n#### Step 4: Display Audit Summary\n\nRead validation file and present:\n- Overall status (PASSED \u002F PASSED WITH WARNINGS \u002F FAILED)\n- Quality score\n- Critical issues (must fix before ship)\n- Warnings (should fix)\n\n**If FAILED with critical issues:**\n```markdown\n## Audit Failed - Cannot Ship\n\nCritical issues must be resolved before shipping:\n\n1. [Issue 1 from validation]\n2. [Issue 2 from validation]\n\nResolve issues and run `\u002Focto:ship` again.\n```\n\n**STOP if critical issues found.**\n\n\n### Phase 3: Capture Lessons Learned\n\n#### Step 1: Ask User for Lessons\n\n```markdown\n## Lessons Learned\n\nBefore finalizing, let's capture what we learned from this project.\n\n**Please answer the following:**\n\n1. **What went well?** (What worked better than expected?)\n\n2. **What could improve?** (What would you do differently?)\n\n3. **Key learnings?** (What insights will you carry forward?)\n\n*Reply with your answers, or type \"skip\" to proceed without capturing lessons.*\n```\n\n**Wait for user response.**\n\n#### Step 2: Append to LESSONS.md\n\nIf user provides lessons (not \"skip\"):\n\n```bash\n# Generate timestamp\nTIMESTAMP=$(date '+%Y-%m-%d')\n\n# Ensure LESSONS.md exists\ntouch .octo\u002FLESSONS.md\n\n# Append lessons\ncat >> .octo\u002FLESSONS.md \u003C\u003C EOF\n\n## ${TIMESTAMP} - Project Delivery\n\n### What Went Well\n- ${USER_WHAT_WENT_WELL}\n\n### What Could Improve\n- ${USER_WHAT_COULD_IMPROVE}\n\n### Key Learnings\n- ${USER_KEY_LEARNINGS}\n\nEOF\n```\n\n**Count total lessons:**\n```bash\nLESSON_COUNT=$(grep -c \"^## \" .octo\u002FLESSONS.md 2>\u002Fdev\u002Fnull || echo \"0\")\necho \"Total lessons captured: $LESSON_COUNT\"\n```\n\n\n### Phase 4: Archive Project State\n\n#### Step 1: Create Archive Directory\n\n```bash\n# Generate timestamp for archive\nARCHIVE_TIMESTAMP=$(date +%Y%m%d-%H%M%S)\nARCHIVE_DIR=\".octo\u002Farchive\u002F${ARCHIVE_TIMESTAMP}\"\n\n# Create archive directory\nmkdir -p \"$ARCHIVE_DIR\"\n```\n\n#### Step 2: Copy State Files to Archive\n\n```bash\n# Archive STATE.md if exists\nif [[ -f \".octo\u002FSTATE.md\" ]]; then\n    cp .octo\u002FSTATE.md \"$ARCHIVE_DIR\u002F\"\nfi\n\n# Archive PROJECT.md if exists\nif [[ -f \".octo\u002FPROJECT.md\" ]]; then\n    cp .octo\u002FPROJECT.md \"$ARCHIVE_DIR\u002F\"\nfi\n\n# Archive ROADMAP.md if exists\nif [[ -f \".octo\u002FROADMAP.md\" ]]; then\n    cp .octo\u002FROADMAP.md \"$ARCHIVE_DIR\u002F\"\nfi\n\n# Archive ISSUES.md if exists\nif [[ -f \".octo\u002FISSUES.md\" ]]; then\n    cp .octo\u002FISSUES.md \"$ARCHIVE_DIR\u002F\"\nfi\n\necho \"Archived to: $ARCHIVE_DIR\"\n```\n\n**IMPORTANT: NEVER archive LESSONS.md** - lessons are preserved across projects.\n\n#### Step 3: Verify Archive\n\n```bash\n# List archived files\nls -la \"$ARCHIVE_DIR\"\n```\n\n\n### Phase 5: Create Delivery Summary\n\n#### Step 1: Update STATE.md\n\n```bash\n# Update status to shipped\nsed -i '' 's\u002F^status:.*\u002Fstatus: shipped\u002F' .octo\u002FSTATE.md 2>\u002Fdev\u002Fnull || \\\n    sed -i 's\u002F^status:.*\u002Fstatus: shipped\u002F' .octo\u002FSTATE.md\n\n# Append history entry\ncat >> .octo\u002FSTATE.md \u003C\u003C EOF\n\n## History - $(date '+%Y-%m-%d %H:%M')\n\n- **Event:** Project shipped\n- **Archive:** .octo\u002Farchive\u002F${ARCHIVE_TIMESTAMP}\u002F\n- **Validation:** ${VALIDATION_FILE}\n\nEOF\n```\n\n#### Step 2: Create Shipped Checkpoint\n\n```bash\n# Create git checkpoint tag\nCHECKPOINT_TAG=\"octo-checkpoint-shipped-${ARCHIVE_TIMESTAMP}\"\n\ngit tag -a \"$CHECKPOINT_TAG\" -m \"Project shipped - $(date '+%Y-%m-%d %H:%M:%S')\"\n\necho \"Checkpoint created: $CHECKPOINT_TAG\"\n```\n\n#### Step 3: Count Metrics\n\n```bash\n# Count resolved issues\nISSUES_RESOLVED=$(grep -c \"^\\- \\[x\\]\" .octo\u002FISSUES.md 2>\u002Fdev\u002Fnull || echo \"0\")\n\n# Count total lessons\nLESSONS_COUNT=$(grep -c \"^## \" .octo\u002FLESSONS.md 2>\u002Fdev\u002Fnull || echo \"0\")\n\necho \"Issues resolved: $ISSUES_RESOLVED\"\necho \"Lessons captured: $LESSONS_COUNT\"\n```\n\n\n### Phase 6: Display Completion\n\nPresent final summary:\n\n```markdown\n## Project Shipped!\n\n**Delivered:** {timestamp}\n**Phases Completed:** 4\u002F4\n**Issues Resolved:** {ISSUES_RESOLVED}\n**Lessons Captured:** {LESSONS_COUNT}\n\n### Multi-AI Audit Summary\n\n- **Security Score:** {score}\u002F100\n- **Quality Score:** {score}\u002F100\n- **Providers Used:** Claude plus available external providers\n\n### Archive\n\nLocation: `.octo\u002Farchive\u002F{ARCHIVE_TIMESTAMP}\u002F`\n\nContents:\n- STATE.md\n- PROJECT.md\n- ROADMAP.md\n- ISSUES.md\n\n### Checkpoint\n\nTag: `{CHECKPOINT_TAG}`\n\nRestore with: `\u002Focto:rollback {CHECKPOINT_TAG}`\n\n\n**To start a new project:** `\u002Focto:embrace`\n\n*Multi-AI validation powered by Claude Octopus*\n*Providers: Codex | Antigravity | Claude*\n```\n\n\n## Error Handling\n\n| Error | Resolution |\n|-------|------------|\n| No .octo\u002F directory | Suggest `\u002Focto:embrace` |\n| Project not ready | Show remaining phases |\n| orchestrate.sh fails | Show error logs, suggest retry |\n| Critical audit issues | Block ship, show issues |\n| Git tag fails | Warn but continue (non-blocking) |\n\n\n## Safety Measures\n\n| Measure | Implementation |\n|---------|----------------|\n| **Pre-ship audit** | orchestrate.sh Multi-AI validation required |\n| **Lessons preservation** | LESSONS.md never archived, always preserved |\n| **Archive before ship** | State files copied to archive directory |\n| **Git checkpoint** | Tag created for rollback capability |\n| **No file deletion** | Archive copies, doesn't delete source files |\n\n\n## Integration with Other Skills\n\n### With \u002Focto:deliver\n\n```\nUser runs \u002Focto:deliver to validate\n→ Deliver phase complete\n→ User runs \u002Focto:ship to finalize\n```\n\n### With \u002Focto:rollback\n\n```\nUser ships project\n→ Checkpoint created\n→ Later: \u002Focto:rollback octo-checkpoint-shipped-*\n```\n\n### With \u002Focto:status\n\n```\nAfter ship: status shows \"shipped\"\n→ Suggests \u002Focto:embrace for new project\n```\n\n\n## Red Flags - Never Do\n\n| Action | Why It's Wrong |\n|--------|----------------|\n| Skip Multi-AI audit | Security vulnerabilities missed |\n| Archive LESSONS.md | Loses accumulated project knowledge |\n| Delete source files | Should copy, not move |\n| Ship without ready check | Incomplete work shipped |\n| Skip checkpoint creation | No rollback recovery path |\n\n\n## Quick Reference\n\n| Step | Command | Purpose |\n|------|---------|---------|\n| 1 | Check .octo\u002FSTATE.md | Verify ready to ship |\n| 2 | orchestrate.sh ink | Multi-AI security audit |\n| 3 | Ask user | Capture lessons learned |\n| 4 | mkdir + cp | Archive state files |\n| 5 | Update STATE.md | Mark as shipped |\n| 6 | git tag | Create shipped checkpoint |\n\n\n## The Bottom Line\n\n```\nShip → Ready + Audit passed + Lessons captured + Archived + Checkpoint created\nOtherwise → Not shipped\n```\n\n**Verify ready. Run Multi-AI audit. Capture lessons. Archive state. Create checkpoint. Ship.**\n",{"name":5,"description":7,"disable-model-invocation":41},true,"main","f620abaff09061f8c8b1f1559dca3fdd031a32e5","plugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-ship",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":41},[54,57,60],{"tool":55,"command":56},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-ship",{"tool":58,"command":59},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-ship",{"tool":61,"command":62},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-ship","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-ship\u002FSKILL.md",[65],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"agents\u002Fopenai.yaml","REFERENCE","参考文档",165,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-ship\u002Fagents\u002Fopenai.yaml",[72,82,90,98,106,114],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":81},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":81},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":81},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":81},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":81},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":81},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]