返回技能列表

escalate-issues

pjt222
更新于 6 days ago
16 次查看
17
2
17
在 GitHub 上查看
wordaiautomationdesign

关于

This skill triages maintenance issues by severity and creates actionable reports when automated cleanup fails. It escalates problems like unsafe code deletions, breaking changes, or security findings to appropriate specialists. Use it to document and route complex issues requiring domain expertise or human review.

快速安装

Claude Code

推荐
主要方式
npx skills add pjt222/agent-almanac -a claude-code
插件命令备选方式
/plugin add https://github.com/pjt222/agent-almanac
Git 克隆备选方式
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/escalate-issues

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

escalate-issues

維護遇自動清外之議時用此技:

  • 碼可安刪否不明
  • 組態須域專(安、性、架)
  • 清中察破變
  • 須繁重構(非僅清)
  • 安感發現(硬碼密、脆弱)

勿用於有明修之簡議。僅於自動清危或不足時升。

issue_descriptionstringYesClear description of the problem
severityenumYescritical, high, medium, low
context_filesarrayNoPaths to relevant files
specialiststringNoTarget agent (auto-route if not specified)
blockingbooleanNoWhether issue blocks further cleanup (default: false)

一:估重

以標重級分之。

CRITICAL — 阻生產功能:

  • 用碼之引破
  • 安脆弱(密露、SQL 注)
  • 清作致失數
  • 生產服斷

HIGH — 損維或發效:

  • 大死碼(>1000 行)
  • CI/CD 管破
  • 環境間大組漂
  • 或動態載之無引模

MEDIUM — 微衛議:

  • 未用助函(<100 行)
  • 舊文須更
  • 棄組文(不用而存)
  • 非要路之 lint 警

LOW — 式不一:

  • 縮進混(可而不一)
  • 末空
  • 命不一(camelCase 對 snake_case)
  • 微格差

重決樹

Does it break production? → CRITICAL
Does it block development? → HIGH
Does it impact code quality? → MEDIUM
Is it purely cosmetic? → LOW

得:議以明重標已分。

敗:不確→默 HIGH 並升人重分。

二:錄發現

捕關境供專閱。

議報模

# Issue: [Brief Title]

**Severity**: CRITICAL | HIGH | MEDIUM | LOW
**Discovered During**: [Skill name, e.g., clean-codebase]
**Date**: YYYY-MM-DD
**Blocking**: Yes | No

## Description

Clear description of the problem in 2-3 sentences.

## Context

- **File(s)**: [List of affected files with line numbers]
- **Related**: [Related issues, commits, or previous attempts to fix]
- **Impact**: [What breaks if this isn't fixed, or what's wasted if not cleaned]

## Evidence

```language
# Code snippet or log excerpt showing the problem

Attempted Fixes

  • Tried X but failed because Y
  • Considered Z but uncertain due to W

Recommendation

  • Option 1: [Safe conservative approach]
  • Option 2: [More aggressive fix with risks]
  • Preferred: [Which option to pursue and why]

Specialist Routing

Suggested Agent: [agent-name] Reason: [Why this specialist is appropriate]

References

  • [Link to related documentation]
  • [Link to similar past issues]

得:議以全境錄於 `ESCALATION_REPORTS/issue_YYYYMMDD_HHMM.md`。

敗:(不適——永錄,縱不全)。

### 三:定路

匹議類於適專 agent 或人閱者。

**路表**:

| 議類 | 專 | 因 |
|------------|-----------|---------|
| Security vulnerability | security-analyst | Security expertise required |
| GxP compliance concern | gxp-validator | Regulatory knowledge needed |
| Architecture decision | senior-software-developer | Design pattern expertise |
| Config management | devops-engineer | Infrastructure knowledge |
| Dependency conflicts | devops-engineer | Package management expertise |
| Performance bottleneck | senior-data-scientist | Optimization knowledge |
| Code style dispute | code-reviewer | Style guide authority |
| Dead code uncertainty | r-developer (or lang-specific) | Language-specific knowledge |
| Broken test unclear | code-reviewer | Test design expertise |
| Documentation accuracy | senior-researcher | Domain knowledge required |
| License compatibility | auditor | Legal/compliance expertise |

**自動路邏**:
```python
def route_issue(severity, issue_type):
    if severity == "CRITICAL":
        # Always escalate to human for critical issues
        return "human"

    if "security" in issue_type or "secret" in issue_type:
        return "security-analyst"

    if "gxp" in issue_type or "compliance" in issue_type:
        return "gxp-validator"

    if "architecture" in issue_type or "design" in issue_type:
        return "senior-software-developer"

    if "config" in issue_type or "deployment" in issue_type:
        return "devops-engineer"

    # Default: code-reviewer for general code issues
    return "code-reviewer"

得:議路至適專並有理。

敗:無明專→升人手動路。

四:造可行報

生適標眾之格式報(agent 或人)。

予專 agent(MCP 工具之結構):

---
type: escalation
severity: high
from_agent: janitor
to_agent: security-analyst
blocking: false
---

# Security Concern: Hardcoded API Key in Config

**File**: config/production.yml:45
**Pattern**: API_KEY="sk_live_abc123..."

**Request**: Please review if this is a valid secret or a placeholder.
If valid, recommend secure credential management strategy.

**Context**: Discovered during config cleanup sweep.

予人閱者(詳 markdown):

# Escalation Report: Uncertain Dead Code Removal

**From**: Janitor Agent
**Date**: 2026-02-16
**Severity**: HIGH

## Problem

File `src/legacy_payments.js` (450 lines) appears unused but contains
complex payment processing logic. Static analysis shows zero references,
but name suggests business-critical functionality.

## Why Escalated

- Uncertain if payment code is dynamically loaded at runtime
- Potential data loss risk if deleted incorrectly
- Requires domain knowledge to assess business impact

## Evidence

- No direct imports found
- Last modified 8 months ago
- Git history shows it was part of payment refactor

## Recommendation

Request human review before deletion. If confirmed dead:
1. Archive to archive/legacy/ directory
2. Document in ARCHIVE_LOG.md
3. Create ticket to verify payment flows still work

## Next Steps

Awaiting human confirmation before proceeding with cleanup.

得:報以標眾適格生。

敗:(不適——不確則以通 markdown 生)。

五:追升態

守諸升之日以防重報。

# Escalation Log

| ID | Date | Severity | Issue | Specialist | Status |
|----|------|----------|-------|-----------|--------|
| ESC-001 | 2026-02-16 | CRITICAL | Broken prod import | human | Resolved |
| ESC-002 | 2026-02-16 | HIGH | Dead payment code | human | Pending |
| ESC-003 | 2026-02-16 | MEDIUM | Config drift | devops-engineer | In Progress |

得:ESCALATION_LOG.md 以新條更。

敗:日不存→造之。

六:告而阻(若須)

若議阻維→告而停清。

阻邏

  • CRITICAL 永阻
  • HIGH 於要路則阻
  • MEDIUM/LOW 不阻

⚠️ MAINTENANCE BLOCKED ⚠️

Issue ESC-002 (HIGH severity) requires human review before proceeding.

**Affected Operation**: clean-codebase (Step 5: Remove Dead Code)
**Reason**: Uncertain if src/legacy_payments.js is truly dead

**Action Required**: Review ESCALATION_REPORTS/ESC-002_2026-02-16.md

Once resolved, re-run maintenance from Step 5.

得:維暫停;明告已生。

敗:告機無→於報中錄。

升後:

  • 議重已正估
  • 全境已錄(文、證、嘗)
  • 適專已識
  • 升報已建於 ESCALATION_REPORTS/
  • ESCALATION_LOG.md 已更
  • 阻態若適已告
  • 報中無敏信露

  1. 過升:升簡議費專時。唯於真不確或危時升
  2. 漏升:刪碼「僅試過否」而未升→可致生產斷
  3. 境不足:無證而升→迫專重查。宜含文徑、行號、誤信
  4. 述模糊:「組有誤」不可行。須特:「組漂:dev 用 API v1,prod 用 v2」
  5. 不追態:重升已閱議。先察 ESCALATION_LOG.md
  6. 露密:升報中含真 API 鑰或密碼。敏值須蓋

GitHub 仓库

pjt222/agent-almanac
路径: i18n/wenyan-ultra/skills/escalate-issues
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

相关推荐技能

content-collections

Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。

查看技能

polymarket

这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。

查看技能

creating-opencode-plugins

该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。

查看技能

sglang

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能