Agent部署
- 作者仓库星标 3,406
- 作者更新于 实时读取
- 作者仓库 claude-octopus
- 领域
- 通用
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @nyldn · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: skill-ship
description: Package and finalize completed work for delivery — use when a feature is done and ready to ship…
category: 通用
runtime: 无特殊运行时
---
# skill-ship 输出预览
## PART A: 任务判断
- 适用问题:通用任务拆解、检查和交付。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“When to Use / The Process / Phase 1: Verify Project Ready to Ship”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于通用任务拆解、检查和交付,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“When to Use / The Process / Phase 1: Verify Project Ready to Ship”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、执行终端命令、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令;主要在本地完成;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文出现了 `/octo`、`/dev` 这类斜杠命令;如果你的 Agent 支持命令触发,优先用命令开场,再补充目标和边界。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件、执行终端命令。
先用一个小任务确认它会围绕“When to Use / The Process / Phase 1: Verify Project Ready to Ship”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: skill-ship
description: Package and finalize completed work for delivery — use when a feature is done and ready to ship…
category: 通用
source: nyldn/claude-octopus
---
# skill-ship
## 什么时候使用
- 把通用方向的常用动作沉淀成 Agent 可调用的技能 适合处理通用任务拆解、检查、交付和复盘,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的步骤;通常不需要额外…
- 面向通用任务拆解、检查和交付,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「When to Use / The Process / Phase 1: Verify Project Ready to Ship」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令;主要在本地完成;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "skill-ship" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> When to Use / The Process / Phase 1: Verify Project Ready to Ship
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件、执行终端命令 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} 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, seeskills/blocks/codex-host-adapter.md.
Ship Project - Multi-AI Delivery Validation
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.
When to Use
Use this skill when user asks:
- "Ship the project" or "We're done"
- "Finalize this" or "Let's deliver"
- "Complete the project" or "Ready to ship"
- "Mark as shipped" or "Time to deliver"
Do NOT use for:
- Code review (use /octo:review or flow-deliver)
- Implementation (use /octo:develop)
- Research (use /octo:research)
The Process
Phase 1: Verify Project Ready to Ship
Step 1: Check .octo/ Exists
if [[ ! -d ".octo" ]]; then
echo "No project initialized"
exit 1
fi
If .octo/ does not exist:
## 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.
Step 2: Read STATE.md Status
# 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"
Step 3: Validate Ready State
Ship is allowed when:
status= "complete" ORcurrent_phase= "4" (Deliver phase) OR- All four phases have entries in STATE.md history
If not ready:
## 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".
Phase 2: Multi-AI Security Audit
Step 1: Display Visual Indicators
# Check provider availability
command -v codex &> /dev/null && codex_status="Available" || codex_status="Not installed"
command -v gemini &> /dev/null && gemini_status="Available" || gemini_status="Not installed"
Output:
## Multi-AI Security Audit
**Providers:**
- Codex CLI: ${codex_status} - Code security analysis
- Gemini CLI: ${gemini_status} - Edge case and vulnerability detection
- Claude: Available - Synthesis and final validation
**Estimated Time:** 3-5 minutes
**Estimated Cost:** $0.02-0.08
Step 2: Execute orchestrate.sh Security Audit
You MUST execute this via native shell command tool:
# Run Multi-AI security audit for delivery
"${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh" ink "Security audit for delivery - comprehensive review of all code changes for production readiness"
MANDATORY COMPLIANCE
CRITICAL: You are PROHIBITED from:
- Skipping Multi-AI validation
- Doing single-provider analysis instead
- Claiming you're "simulating" the audit
- Proceeding without running orchestrate.sh
Step 3: Verify Audit Completed
# 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: $VALIDATION_FILE"
Step 4: Display Audit Summary
Read validation file and present:
- Overall status (PASSED / PASSED WITH WARNINGS / FAILED)
- Quality score
- Critical issues (must fix before ship)
- Warnings (should fix)
If FAILED with critical issues:
## Audit Failed - Cannot Ship
Critical issues must be resolved before shipping:
1. [Issue 1 from validation]
2. [Issue 2 from validation]
Resolve issues and run `/octo:ship` again.
STOP if critical issues found.
Phase 3: Capture Lessons Learned
Step 1: Ask User for Lessons
## Lessons Learned
Before finalizing, let's capture what we learned from this project.
**Please answer the following:**
1. **What went well?** (What worked better than expected?)
2. **What could improve?** (What would you do differently?)
3. **Key learnings?** (What insights will you carry forward?)
*Reply with your answers, or type "skip" to proceed without capturing lessons.*
Wait for user response.
Step 2: Append to LESSONS.md
If user provides lessons (not "skip"):
# Generate timestamp
TIMESTAMP=$(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
- ${USER_KEY_LEARNINGS}
EOF
Count total lessons:
LESSON_COUNT=$(grep -c "^## " .octo/LESSONS.md 2>/dev/null || echo "0")
echo "Total lessons captured: $LESSON_COUNT"
Phase 4: Archive Project State
Step 1: Create Archive Directory
# Generate timestamp for archive
ARCHIVE_TIMESTAMP=$(date +%Y%m%d-%H%M%S)
ARCHIVE_DIR=".octo/archive/${ARCHIVE_TIMESTAMP}"
# Create archive directory
mkdir -p "$ARCHIVE_DIR"
Step 2: Copy State Files to Archive
# 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: $ARCHIVE_DIR"
IMPORTANT: NEVER archive LESSONS.md - lessons are preserved across projects.
Step 3: Verify Archive
# List archived files
ls -la "$ARCHIVE_DIR"
Phase 5: Create Delivery Summary
Step 1: Update STATE.md
# 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:** ${VALIDATION_FILE}
EOF
Step 2: Create Shipped Checkpoint
# Create git checkpoint tag
CHECKPOINT_TAG="octo-checkpoint-shipped-${ARCHIVE_TIMESTAMP}"
git tag -a "$CHECKPOINT_TAG" -m "Project shipped - $(date '+%Y-%m-%d %H:%M:%S')"
echo "Checkpoint created: $CHECKPOINT_TAG"
Step 3: Count Metrics
# Count resolved issues
ISSUES_RESOLVED=$(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"
Phase 6: Display Completion
Present final summary:
## 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:** Codex + Gemini + Claude
### 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 | Gemini | Claude*
Error Handling
| 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) |
Safety Measures
| 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 |
Integration with Other Skills
With /octo:deliver
User runs /octo:deliver to validate
→ Deliver phase complete
→ User runs /octo:ship to finalize
With /octo:rollback
User ships project
→ Checkpoint created
→ Later: /octo:rollback octo-checkpoint-shipped-*
With /octo:status
After ship: status shows "shipped"
→ Suggests /octo:embrace for new project
Red Flags - Never Do
| 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 |
Quick Reference
| 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 |
The Bottom Line
Ship → Ready + Audit passed + Lessons captured + Archived + Checkpoint created
Otherwise → Not shipped
Verify ready. Run Multi-AI audit. Capture lessons. Archive state. Create checkpoint. Ship.
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核