Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zyx379/zoehis_workflownpx agentmods add skills/zyx379/zoehis_workflow/zoehis-external-analysisWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zyx379/zoehis_workflow/zoehis-external-analysis)<a href="https://agentmods.dev/skills/zyx379/zoehis_workflow/zoehis-external-analysis"><img src="https://agentmods.dev/badge/skills/zyx379/zoehis_workflow/zoehis-external-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zyx379/zoehis_workflow/zoehis-external-analysis"><img src="https://agentmods.dev/badge/skills/zyx379/zoehis_workflow/zoehis-external-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.02361 |
| Opus 5 | $0.00040 | $0.01180 |
| Sonnet 5 | $0.00016 | $0.00472 |
| Haiku 4.5 | $0.00008 | $0.00236 |
Grade A, and why
zoehis-external-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ZOEHIS 外部分析（Trae / CodeBuddy 专用）
范围：只做任务分流 → 需求理解 → 代码定位 → 需求分析（代码地图）。
禁止：改代码、git pull/commit/push、spec 最终确认。
完整流程与 Cursor 分工见 multi-editor-cursor-collab.md。
何时使用
- 用户在 Trae / CodeBuddy 中发起需求初步分析
- 用户明确要求「外部分析」「Step 0-4」「交接给 Cursor」
- 生产排查 不走本 Skill（改走
his-log-diagnosis+ MCP）
工作流（逐步执行并汇报）
外部分析进度:
- [ ] 0. 任务分流（功能 / Bug；生产排查请改 his-log-diagnosis）
- [ ] 1. 需求理解（业务域、参数体系、数据流、待确认点）
- [ ] 2. 代码定位（子仓库 + 候选文件清单）
- [ ] 4. 需求分析（代码地图 + 记忆库命中 + 待确认）
- [ ] 交接. 输出 Cursor 交接块
Step 3 Git 同步、Step 5+ 由 Cursor 执行。
Step 0 — 任务分流
| 类型 | 走本 Skill？ | 说明 |
|---|---|---|
| 功能改造 | ✅ | 新需求、增强 |
| Bug 修复 | ✅ | 先复现/定位根因 |
| 生产排查 | ❌ | 改走 his-log-diagnosis + MCP zoe-his-mcp |
有 traceId 且目的是查生产 → 不走本 Skill。
Step 1 — 需求理解
必须输出：
- 任务类型（功能 / Bug）
- 业务域：门诊 / 住院 / 收费 / 药库 / 医保 / 组件
- 参数体系识别（新增/修改开关时必填）：
- 系统参数
$getSysParamList？页面参数$getPageControlMap(configId)？ - 若已有同页面参数，保持同一体系
- 不确定时列待确认点
- 系统参数
- 预期数据流（涉及哪些表、池表→记录、预交金/流水）
- 待确认点（业务不清时必填；禁止编造表名、接口、流程）
硬约束： 信息不足时只列问题，不开始改代码。
Step 2 — 代码定位
定位手段（按优先级）：
- 长期记忆：Read
docs/memory/index.md，按页面/表/关键词找 cases - 用户线索：页面名、截图、接口名、文件路径
- 路径约定：
| 层级 | 路径模式 |
|---|---|
| 页面 | pages/{camelCase}/、components/{同名}/ |
| API | api/{kebab-service}/.../{PascalCase}.js |
| 后端 | Controller → Service → Dao → *Dao.xml |
- 定向 Grep：小范围符号、路由、
baseUrl、dictName
必须输出：
- 将改动的 子仓库清单
- 拟改动 文件清单（前/Api/Controller/Service/Dao.xml）
- 若跨仓：说明调用关系
子仓库对照
定位方法：所有子仓库均位于工作区根目录
{workspaceRoot}/下。 禁止用 Glob**/{repo-name}/**搜索子仓库（会返回空）。应直接LS {workspaceRoot}/{repo-name}/访问。
| 仓库 | 域 | 实际路径 |
|---|---|---|
| onelink-web-outp-fj-common | 门诊前端 | {workspaceRoot}/onelink-web-outp-fj-common/ |
| onelink-web-pres-fj-common | 医嘱前端 | {workspaceRoot}/onelink-web-pres-fj-common/ |
| onelink-web-his-charge-fj-common | 收费前端 | {workspaceRoot}/onelink-web-his-charge-fj-common/ |
| onelink-web-his-drug-fj-common | 药库前端 | {workspaceRoot}/onelink-web-his-drug-fj-common/ |
| onelink-web-his-fj-component | 公共组件 | {workspaceRoot}/onelink-web-his-fj-component/ |
| onelink-web-cis-common | CIS 公共组件（npm 包） | {workspaceRoot}/onelink-web-cis-common/ |
| onelink-micro-pres-fj-common | 医嘱后端 | {workspaceRoot}/onelink-micro-pres-fj-common/ |
| onelink-micro-charge-fj-common | 收费服务 | {workspaceRoot}/onelink-micro-charge-fj-common/ |
| onelink-micro-optimus-fj-common | 基础服务 | {workspaceRoot}/onelink-micro-optimus-fj-common/ |
| onelink-micro-insurance-fj-ybcommon | 医保服务 | {workspaceRoot}/onelink-micro-insurance-fj-ybcommon/ |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 238 lines · 80 tokens per session scan A 3c0fc835b7c1
zoehis-external-analysis is a skill published in the GitHub repository zyx379/zoehis_workflow (2 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 2,361 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.