Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add duolongworld/AI_Renaissance --skill industrial_sentinelgit clone --depth 1 https://github.com/duolongworld/AI_RenaissanceWrote 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/duolongworld/ai_renaissance/industrial_sentinel)<a href="https://agentmods.dev/skills/duolongworld/ai_renaissance/industrial_sentinel"><img src="https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/industrial_sentinel/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/duolongworld/ai_renaissance/industrial_sentinel"><img src="https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/industrial_sentinel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00100 | $0.04934 |
| Opus 5 | $0.00050 | $0.02467 |
| Sonnet 5 | $0.00020 | $0.00987 |
| Haiku 4.5 | $0.00010 | $0.00493 |
Grade A, and why
industrial_sentinel 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 — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Industrial Sentinel | 产业链中观分析框架
Trigger: 当用户提到"景气度"、"/景气度"时激活。
1. 快速开始
本 skill 位于 AI_Renaissance 项目
skills/industry/industrial_sentinel/目录下，由 Agent 通过runtime.py调用。
1.1 环境准备
# 进入 skill 目录（在 AI_Renaissance 项目根目录下）
cd skills/industry/industrial_sentinel
# 运行分析（支持代码/简称）
./run.sh 002916.SZ
./run.sh 深南电路
前置依赖：Python 3.9+。独立方法论框架尽量只依赖标准库；项目集成模式通过 data_sources/ 使用主项目已有 provider 与依赖。
1.2 触发方式
常见触发词：/景气度 [代码]、景气度 [行业/个股]
输入股票代码、简称、行业词或 preset 时，项目级 IndustryAgent 会先做输入归一化，再调用项目 data_sources/ 获取或注入标准化数据，最后由 runtime.py 输出行业景气度、拐点状态、生命周期、个股类型和产业链结构摘要。
项目级 IndustryAgent 接入时只返回标准 Signal 和结构化 meta，不生成、不落盘、不返回 HTML 报告路径。HTML 仅用于 ./run.sh / core/pipeline.py 的独立 CLI 或人工调试模式。
CLI 完整输出（默认）：
- 产业链结构卡片（上游/中游/下游）
- 产业链景气度判定（行业周期/供需拐点/政策催化剂）
- 拐点状态（五态模型）
- 生命周期阶段
- System B 个股类型判定
- HTML 仪表盘报告
如需轻量版（只看产业链结构）：
./run.sh <code> --lite
1.3 项目级执行流程（关键）
这是本 skill 的核心设计：Skill 不直接联网抓数，项目数据层负责 provider 获取、解析和缓存。
当主项目调用 IndustryAgent.analyze() 后，应按以下流程执行：
Step 1: IndustryAgent 识别输入类型
→ stock_code / stock_name / industry / preset
Step 2: stock_code 输入调用 data_sources.industrial_sentinel
→ 获取行业景气数据、财务数据、缓存状态与降级原因
Step 3: industry / preset 输入只做框架路由
→ 不把 preset 命中当作真实景气结论
Step 4: runtime.py 消费标准化 industry_result / financial_data / config
→ 生成 direction / confidence / reasoning / signals / meta
Step 5: IndustryAgent 包装为标准 Signal
→ Signal 构造异常时返回 neutral，并标记 needs_human_review
重要：
- 不要在 Skill 内新增 provider 抓数逻辑
- 真实 fetching/parsing/provider 放在项目
data_sources/ - 数据缺失时输出低置信降级结果、
needs_data、缺失字段和采集任务，不编造行业景气度 - HTML 只属于 CLI / 人工调试路径，不进入 Orchestrator 主流程
2. 核心架构
2.1 三维度独立展示
当前框架不合成单一“产业拐点指数”，三个维度各自独立展示：
| 维度 | 核心问题 | 展示形式 |
|---|---|---|
| 产业链景气度 | 行业当前景气如何？ | 三维度描述（行业周期/供需拐点/政策催化剂）+ 真实数据 |
| 产业链拐点 | 处于五态模型的哪个阶段？ | 五态判定 + 信号匹配详情 |
| 产业链生命周期 | 行业处于生命周期的哪个阶段？ | 大卡片（导入期/成长期/成熟期/衰退期） |
What ships with it
38 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 227 B
- CHANGELOG.md 688 B
- core/auto_detect_preset.py 21 KB runs code
- core/data_collection_guide.py 28 KB runs code
- core/name_preset_mapping.py 11 KB runs code
- core/pipeline.py 58 KB runs code
- core/system_a.py 56 KB runs code
- core/system_b.py 25 KB runs code
- data/mappings/stock-to-industry-optical.json 16 KB
- docs/pipeline-guide.md 3.0 KB
- LICENSE 1.1 KB
- README.md 5.1 KB
- references/ai-agent-guide.md 4.1 KB
- references/data-requirements.md 9.7 KB
- references/data-standardization.md 7.1 KB
- references/eastmoney-push2-api-field-reference.md 1.3 KB
- references/framework-structure.md 11 KB
- references/industry-benchmark-database.yaml 26 KB
- references/methodology-mapping.md 12 KB
- references/optical-communication-CCF-model.md 22 KB
- references/preset-chains/generic.yaml 146 B
- references/preset-chains/layer1-energy/ai-energy.yaml 11 KB
- references/preset-chains/layer2-chip/ai-chip.yaml 6.2 KB
- references/preset-chains/layer2-chip/semiconductor-equipment.yaml 8.2 KB
- references/preset-chains/layer2-chip/storage.yaml 7.4 KB
- references/preset-chains/layer3-infrastructure/ai-infrastructure.yaml 6.1 KB
- references/preset-chains/layer3-infrastructure/optical-module.yaml 8.4 KB
- references/preset-chains/layer3-infrastructure/pcb.yaml 9.1 KB
- references/preset-chains/layer4-model/ai-model.yaml 6.4 KB
- references/preset-chains/layer4-model/README.md 627 B
- references/preset-chains/layer5-application/robotics.yaml 6.4 KB
- references/stock-to-industry-mapping.json 897 B
- requirements.txt 201 B
- run.sh 4.2 KB runs code
- runtime.py 42 KB runs code
- scripts/generate_data_template.py 13 KB runs code
- scripts/validate_data.py 9.1 KB runs code
- templates/pipeline-output.html 10 KB
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 · 400 lines · 100 tokens per session scan A 63e227a2e66e
industrial_sentinel is a skill published in the GitHub repository duolongworld/AI_Renaissance (59 stars, last pushed 14d ago), licensed Apache-2.0. It adds 100 tokens to every session and 4,934 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.