Vibe Research is a local financial research workspace in which an AI agent gathers market data, performs multi-step analysis, and preserves reports, evidence, calculations, and research history. It is for investment research across Chinese, US, and Hong Kong stocks, including market reviews, company studies, portfolios, debates, and backtesting. The catalogue contains skills and an instruction for working with this research agent.
Borrowing it
Nothing to install: this file belongs to simonlin1212/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/simonlin1212/Vibe-Research/main/.agents/skills/valuation/SKILL.mdgit clone --depth 1 https://github.com/simonlin1212/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/simonlin1212/vibe-research/valuation)<a href="https://agentmods.dev/skills/simonlin1212/vibe-research/valuation"><img src="https://agentmods.dev/badge/skills/simonlin1212/vibe-research/valuation.svg" alt="Measured on agentmods" 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 | $0.00187 | $0.02746 |
| Opus 5 | $0.00093 | $0.01373 |
| Sonnet 5 | $0.00037 | $0.00549 |
| Haiku 4.5 | $0.00019 | $0.00275 |
Grade A, and why
valuation 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 yesterday.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
成长股估值口径(valuation)
本 skill 是 company-research SOP 第 4 阶段(valuation)的口径说明书,也适用于任何"这家公司贵不贵"的讨论。原则:数字出自 calc,判读出自本手册,结论只到"情景 / 裁决点"为止(AGENTS.md §0 第 2、3 条)。
0. 四条铁律
- 每一个 PE / CAGR / PEG / 年数都必须是一次
calc/cli.py调用的输出(带 calculation_id 与输入证据 id);没有对应证据就写"未获取:原因",不拿记忆或别的口径顶替。 - 不输出价格锚(目标价 / 合理价 / 买入价 / 止损价)。消化年数的"锚"是 PE 倍数情景,不是价格;报告里只给"情景 → 年数"表和裁决点。
- PEG 低 ≠ 安全:PEG 的分母(前瞻 CAGR)是整条计算里唯一的预测,周期一转 E 被下修、PEG 跳升。任何 PEG 判读必须同时给出"前瞻 vs TTM 事实是否对得上"。
- 单位与报告期随证据原样带入 calc,由 calc 归一;不在提示词里换算万元 / 亿元、不自己年化。
1. 分子:PE 的三个口径(并列报,主用第一个)
| 口径 | 公式(calc 函数) | 用途 | 已知的坑 |
|---|---|---|---|
| 扣非×4 年化 PE(主) | 总市值 ÷ (最新单季扣非净利润 × 4) → pe_deducted_annualized(total_market_cap, cap_unit, latest_quarter_deducted_profit, profit_unit) |
抓"当前运行速率",对快速成长股比 TTM 更不滞后 | 必用扣非、不用归母(单季×4 会把投资收益 / 补助 / 减值等一次性损益放大 4 倍);季节性:淡季单季×4 会高估 PE、旺季单季×4 会低估——淡旺季方向只能从该公司自己的单季序列判断(earnings-analysis §3),不得套用行业印象;判读时必须写明最新单季是哪个季度与方向性偏差 |
| 前瞻 PE | 现价 ÷ 一致预期 EPS(FY T 均值)→ forward_pe(price, eps_forecast) |
分析师已处理季节性;与扣非×4 对照看"市场在为哪一年定价" | 依赖一致预期质量(机构数 ≥ 3;见 §3) |
| TTM PE + 历史分位 | 总市值 ÷ 近 4 季净利和 → pe_ttm_from_parts(...),并与数据源 pe_ttm 交叉;分位 percentile_rank(history={"history_csv": {"raw_ref": <PE 历史 raw 文件>, "column": "peTTM", "where": {"tradestatus": "1"}, "date_column": "date"}}, current=pe_ttm)(CLI 序列输入形式见 calc/SPEC.md §3;不是把 history_csv / where 当顶层参数) |
历史位置参考;分位 < 20 个有效样本 → not_meaningful | 对快速成长股滞后偏高(把利润低的旧季度算进去);只作参考列,不作主判 |
T 的定义:T = 当前财年(Asia/Shanghai 当日所在年)。
2. 分母:可持续增速(主用前瞻 CAGR,强制交叉验证)
- 前瞻 CAGR = (一致预期 FY T+2 EPS ÷ FY T EPS)^(1/2) − 1 →
forward_cagr(eps_t, eps_t_plus_n, years=2)。最平滑、去基数去季节性;但它是最软的一环:卖方对热门赛道系统性乐观、远年样本薄、分歧大、会被持续修正。必须同时报 min / max 与机构数(consensus_dispersion(low, mean, high),看 max ÷ min 与 (max − min) ÷ mean)。 - TTM 同比(事实,去季节性去单季基数)= 近 4 季净利和 ÷ 前 4 季净利和 − 1 →
ttm_yoy(single_quarters, end_period, unit, money=true);主用归母口径(与一致预期 EPS 同口径),扣非口径并列交叉。 - 交叉验证判读 →
forward_vs_ttm_judgement(forward_cagr_value, ttm_yoy_value, tolerance_pp=10):approx(前瞻 ≈ TTM:增长已兑现,前瞻可信)/forward_below(前瞻远低于 TTM:市场在赌大幅减速,要问为什么)/forward_above(前瞻远高于 TTM:分析师在画饼,PEG 失真风险最高)。 - 两个禁用项:❌ 单季同比做分母(去年同期低基数会假性吹大);❌ 环比做分母(季节性把增长公司算成负,年化更爆炸)。✅ 环比(
qoq)只作"拐点 / 动量"温度计,报告里标注为信号而非增速。
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.
- yesterday Changed 1599b3368650
- 8d ago First seen · 83 lines · 187 tokens per session scan A ed902049a519
valuation is a skill published in the GitHub repository simonlin1212/Vibe-Research (2,417 stars, last pushed yesterday), licensed MIT. It adds 187 tokens to every session and 2,746 once invoked, about $0.0009 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
daily-deep-brief
A scheduled, pre-market investment briefing for Hong Kong and United States stocks. A deterministic preparation step gathers data and an agent adds judgment, while a later step validates and publishes the result.
hk-stock-analysis
A workspace-aware analysis workflow for Hong Kong-listed stocks. It retrieves prices, technical indicators, market comparisons, and news through a local data pipeline, then adds Hong Kong-specific investment context.
us-stock-analysis
Workspace-aware US stock analysis for kcn. Routes through clawock analyze-us / clawock us-quotes instead of generic web search, then layers fundamental/technical/news analysis on top. Use when user asks to analyze a US ticker (e.g. "analyze AAPL", "look at RKLB", "compare TSLA vs NVDA"), check earnings, run…
portfolio-swarm-review
Multi-agent swarm review of kcn's current holdings. Inspired by TauricResearch/TradingAgents framework already in workspace — three-tier analysis (analysts → bull/bear debate → risk debate + judge) with confidence scoring. Use for post-close reviews, holiday/next-session planning, pre-add sizing decisions, and any…
investment-decision
Run a clawock investment decision — read the prepared request, research with the host's own tools, write decision.json with evidence and an explicit bull/bear debate, and let Python validate and settle. Use when the user asks for an investment decision or a clawock run request is present.
earnings-review
Manual, event-driven earnings review for a US or HK holding, backed by first-party filings. Use when a company reports, when a management promise comes due, or when a thesis review needs primary-source numbers. Produces a structured artifact under memory/earnings/ / .json whose earnings-quality math, promise ledger…