[{"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",1559,"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",474,"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.","2026-11-11 14:40:14",{"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",[72,80,87,94,118,143],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":79},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":79},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":79},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":36},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[101,102,103,104,26,105,106,107,108,109,110,35,111,27,112,113,114,115,116,117],"search","deja search","never","error","memory","re","decide","fix","design","debugging","you","reviewer","io","change","cli","merge","past",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":36},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[125,126,127,113,128,129,130,131,132,133,134,135,136,137,105,138,139,140,141,142],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":156,"publishedAt":36},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[149,152,153],{"categoryNo":150,"categoryName":151,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":154,"categoryName":155,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[145,157,158,159,160,161,162,139,163,106,164,165,166,167,35,168,169,170,171,172],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]