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 equity-rigor/us-equity-research --skill china-equity-ic-rigorgit clone --depth 1 https://github.com/equity-rigor/us-equity-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/equity-rigor/us-equity-research/china-equity-ic-rigor)<a href="https://agentmods.dev/skills/equity-rigor/us-equity-research/china-equity-ic-rigor"><img src="https://agentmods.dev/badge/skills/equity-rigor/us-equity-research/china-equity-ic-rigor/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/equity-rigor/us-equity-research/china-equity-ic-rigor"><img src="https://agentmods.dev/badge/skills/equity-rigor/us-equity-research/china-equity-ic-rigor.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 | $0.03244 |
| Opus 5 | $0.00103 | $0.01622 |
| Sonnet 5 | $0.00041 | $0.00649 |
| Haiku 4.5 | $0.00021 | $0.00324 |
Grade A, and why
china-equity-ic-rigor 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 11d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
China Equity IC-Rigor
This skill is the PM red-team layer on top of china-equity-research. Use the base skill to do the underlying multi-agent research; use this one to harden the deliverable to the standard a buy-side PM will sign off on.
The core insight encoded here: an institutional-grade equity opinion letter survives PM challenge not because it has a strong view, but because every specific number is sourced, every transformation reconciles, every headline acknowledges what it's contingent on, and every "what would reverse it" trigger has a numerical denominator. The bugs that kill a memo in IC are almost always mechanical (math doesn't multiply, definitions don't match, anchors aren't verified) — not directional.
When to use this skill
Trigger when ANY of the following appear, even in passing:
- Ticker (000XXX / 6XXXXX / H-share) + "投资意见书" / "IC memo" / "意见书"
- "Red team this", "score this memo", "PM review", "round N", "what would push this from 8.x to 9.x"
- Headline-language requests: 中位预期收益, 情景加权区间, 仓位建议, 减仓/加仓
- Explicit references to S1-S5 sources, 强多/多头/基础/空头/强空 scenarios, 三估值法 reconcile, GM taxonomy, bear bridge, what-would-reverse, A0 tail
- Multi-audience derivatives: 精简版 / IC pre-read / IC debate script / 零售版 / 非专业版
- The user is critiquing a memo and the language sounds like a PM ("the math doesn't add up", "where does this number come from", "this is hand-wavy", "you can't make that claim without an S1")
If the request is for initial fundamental research (no opinion letter framing yet), use china-equity-research directly. Add this skill once the memo construction or red-team phase begins.
Workflow
The work proceeds in five phases. Phases 0-3 produce the institutional version. Phase 4 hardens it. Phase 5 derives audience variants. Phases can interleave when the user explicitly directs it (e.g. "build the institutional and IC versions in parallel").
Phase 0 — Foundational research (delegate to china-equity-research)
What ships with it
17 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.
- references/bear-bridge.md 7.8 KB
- references/five-scenario-framework.md 7.5 KB
- references/gm-taxonomy.md 7.8 KB
- references/multi-audience-delivery.md 8.9 KB
- references/pm-redteam-rubric.md 9.2 KB
- references/position-sizing.md 7.0 KB
- references/source-stratification.md 8.7 KB
- references/tail-risk-mapping.md 6.6 KB
- references/three-method-valuation.md 8.0 KB
- references/what-would-reverse.md 8.8 KB
- scripts/example_boe_scenarios.json 592 B
- scripts/example_boe_segments.json 575 B
- scripts/verify_eps_pe.py 3.9 KB runs code
- scripts/verify_segment_gm.py 3.6 KB runs code
- templates/ic-debate-script-template.md 4.4 KB
- templates/opinion-letter-section-checklist.md 4.0 KB
- templates/retail-translation-glossary.md 5.6 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.
- 11d ago First seen · 146 lines · 206 tokens per session scan A bf6a5660e11d
china-equity-ic-rigor is a skill published in the GitHub repository equity-rigor/us-equity-research (4 stars, last pushed 1mo ago), licensed MIT. It adds 206 tokens to every session and 3,244 once invoked, about $0.0010 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
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.