Borrowing it
Nothing to install: this file belongs to spy007111/Vibe-Research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/spy007111/Vibe-Research/main/.agents/skills/catalyst-risk/SKILL.mdgit clone --depth 1 https://github.com/spy007111/Vibe-ResearchWrote 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/spy007111/vibe-research/catalyst-risk)<a href="https://agentmods.dev/skills/spy007111/vibe-research/catalyst-risk"><img src="https://agentmods.dev/badge/skills/spy007111/vibe-research/catalyst-risk/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/spy007111/vibe-research/catalyst-risk"><img src="https://agentmods.dev/badge/skills/spy007111/vibe-research/catalyst-risk.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 | $0.00206 | $0.04839 |
| Opus 5.5 | $0.00082 | $0.01936 |
| Sonnet 5.5 | $0.00041 | $0.00968 |
| Haiku 4.5 | $0.00021 | $0.00484 |
Grade A, and why
catalyst-risk 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 26d 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.
This is a copy
100% identical to catalyst-risk — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
催化剂与风险(catalyst-risk)
对应 company-research SOP 第 5 阶段(risk)与 研究宪法 §1 第 5 问("强结论先找反证")。本 skill 把"风险"从一段泛泛的文字变成可核对的清单:每条风险对应一个能观察到的数据,每个催化剂对应一个时点。
0. 三条纪律
- 强结论(充足 / 不是问题 / 无限 / 确定)必须先找一条反证,找不到才成立;找到了就把结论降级为情景。
- 每条催化剂 / 风险都要写"看什么数据、在哪个端点、下一次公开是什么时候";写不出来的不算催化剂,只算叙事。
- 不给投资动作建议;"风险高"不等于"卖","催化剂多"不等于"买"。产出只到情景概率与裁决点。
1. 催化剂分类(必须标注类型与验证时点)
| 类型 | 含义 | 验证数据 | 端点示例 |
|---|---|---|---|
| 兑现型 | 已有订单 / 产能 / 客户认证在落地,业绩能验证 | 财报单季扣非与营收、产能投放公告、大客户公告 | fetch_financials、sina_income_statement、fetch_announcements、cninfo_announcements |
| 预期型 | 市场尚未形成一致预期的变化(方向真 + 供需失衡) | 一致预期修正方向、研报覆盖数变化、行业月度数据 | fetch_estimates、em_reports、行业数据 |
| 周期型 | 行业周期位置变化(价格、库存、下游资本开支) | 价格 / 库存 / 下游 capex 指引、同行财报 | 行业端点、海外同行(yahoo_financials / sec_filings) |
| 资金 / 情绪型 | 资金流、融资余额、热度 | 只作温度计,不作结论依据 | em_margin_trading、sina_fund_flow、em_hot_rank |
催化剂写法:[类型] 事件 → 观察数据(端点)→ 下一次公开时点 → 若兑现 / 若落空 对判断的影响。
2. 风险分类与对应反证
| 风险 | 触发条件 | 反证要看的数据 |
|---|---|---|
| 技术路线断层 | 下游切换方案绕开本环节 | 下游新品规格、同行路线公告、行业研报 |
| 客户集中 | 前五大客户占比高、单一客户自研 | 年报客户集中度、客户资本开支与自研动向 |
| 产能过剩 / 价格战 | 同行扩产集中投放、产品价格下行 | 同行产能公告、价格数据、毛利变化(经 calc ratio 计算) |
| 周期顶 | 利润在峰值而 PE 最低("便宜 PEG") | 前瞻 vs TTM 判读(valuation §2)、环比拐点、行业月度数据 |
| 预期透支 | 前瞻 CAGR 远高于 TTM 同比;分歧 ≥ 2 倍 | forward_vs_ttm_judgement = forward_above;consensus_dispersion |
| 一致预期下修 | 机构数减少、均值下调 | 两次运行的 fetch_estimates 对比(alerts 工具) |
| 治理 / 合规 | 减持、质押、问询函、审计意见 | 公告端点、em_lockup_expiry、em_block_trade、em_holder_num |
| 流动性 / 交易结构 | 融资余额异常、龙虎榜频繁 | em_margin_trading、em_dragon_tiger(只作温度计) |
| 数据源冲突 | 同一事实多源不等 | 报告里逐条列出各源值与来源,不静默取舍 |
| 数据缺口 | 关键端点失败 / 部分 | 写入"数据缺口"并说明对结论的影响 |
每条风险写法:风险 → 当前证据(ev id)→ 反证数据(端点)→ 若出现则判断如何变。
3. 裁决点(Decision Points)的标准写法
裁决点 = 什么数据出来会改变判断,不是"关注后续进展"。至少三个,每个包含:
- 观察对象(具体指标 / 事件);
- 阈值或方向(例如"单季扣非环比转负两季"、"一致预期机构数 < 3"、"竞争对手通过同一客户认证");
- 数据来源(端点 id)与下一个公开时点(财报披露日、月度数据日、客户财报日、公告);
- 触发后判断怎么变(哪条结论降级、哪个估值情景切换——对应 valuation §5 四锚切换)。
4. 知识档案里的旧结论
编排器会召回 .local/knowledge/ 的历史档案(只作线索,标注"不可信数据"边界)。处理规则:
- 旧结论与本次实时数据冲突 → 用实时数据反证,在
knowledge_conflicts逐条裁决,在报告"风险与反证"写明;不顺从旧结论。 - 旧结论 status 为 stale / refuted → 不得引用为事实。
- 本次新结论也要写成可被下次运行反证的形式(带裁决点)。
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.
- 26d ago Changed cf74aa67f7fe
- 1mo ago First seen · 142 lines · 206 tokens per session scan A faeaee0c5eab
catalyst-risk is a skill published in the GitHub repository spy007111/Vibe-Research (8 stars, last pushed 8d ago), licensed MIT. It adds 206 tokens to every session and 4,839 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to catalyst-risk, differing in 0 lines, and is treated as a copy.
catalyst-risk compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| catalyst-riskspy007111/Vibe-Research | Skill | 8 | 8d ago | MIT | A | 206 | Claude Code, Codex |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 39 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 110 | Claude Code |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | 2d ago | MIT | A | 28 | Claude Code, Codex |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 2d ago | GPL-2.0 | A | 292 | Codex |