Borrowing it
Nothing to install: this file belongs to PatrickSUDO/fadacai-portfolio. 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/PatrickSUDO/fadacai-portfolio/main/.agents/skills/trade-review/SKILL.mdgit clone --depth 1 https://github.com/PatrickSUDO/fadacai-portfolioWrote 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/patricksudo/fadacai-portfolio/trade-review)<a href="https://agentmods.dev/skills/patricksudo/fadacai-portfolio/trade-review"><img src="https://agentmods.dev/badge/skills/patricksudo/fadacai-portfolio/trade-review/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/patricksudo/fadacai-portfolio/trade-review"><img src="https://agentmods.dev/badge/skills/patricksudo/fadacai-portfolio/trade-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00085 | $0.06540 |
| Opus 5 | $0.00043 | $0.03270 |
| Sonnet 5 | $0.00017 | $0.01308 |
| Haiku 4.5 | $0.00009 | $0.00654 |
Grade A, and why
trade-review 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 2d 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trade Review — 兩週交易檢討
這是系統自我進化的引擎。 其他 skill 產生決策，這個 skill 檢查決策對不對，並把結果回饋到規則層。
Why： 2026-07-25 首次歸因調查發現，系統決策的 α 是 +6.1%（賣方 +13.0% / 71% 勝率），脫離 plan 的用戶決策是 −14.0%（12 次對 2 次）。但當時可歸因覆蓋率只有 49%，且沒有任何機制持續計分——規則寫死後永不重測。這個 skill 補上那個迴路。
Arguments
/trade-review→ 上次檢討至今（若無紀錄則近 14 天）/trade-review 4w→ 近 28 天/trade-review since 2026-06-04→ 指定起日
Step 0（沿用 AGENTS.md 統一規範）
- 0a 讀
plan.md+feedback/*.md（含feedback/RULES-LEDGER.md） - 0b
mcp__firstrade-server__get_account_position - 0c/0d journal 確認與 gap-fill
- 不需要 0e 第一性檢查——本 skill 不輸出 Verdict / 投資建議，只做事後歸因與規則計分
Step 1 — 交易帳 ingest 與歸因
python3 tools/trade_ledger.py snapshot-orders
python3 tools/trade_ledger.py ingest --range 2m
python3 tools/trade_ledger.py backfill-origin --since <期初>
python3 tools/trade_ledger.py stats
必報三個數字（覆蓋率是本迴路的健康指標，要逐期往上走）：
- 本期新增成交筆數
attribution_coverage_journaled_pct（有 journal 期間的 origin 覆蓋率）order_registry.snapshot_days（快照天數；越多，往後歸因越接近 100%）
⚠️ 覆蓋率不會靠自己變好。 對 unknown_sample 列出的每一筆，翻當日 journal / plan.md 判斷來源，然後：
python3 tools/trade_ledger.py annotate --id <fill_id> \
--origin system|user --evidence "<判定依據原文>" [--bucket 信念|認列|hedge|樂透]
補正時一併記模型（--model claude-opus-4-8 --effort high），這樣 score --by model 之後能用數據回答兩件事：貴的模型層級值不值那個成本，以及更新的模型不同意舊決策時，該不該相信它。模型版本是排覆審順序的依據，不是推翻已驗證結論的依據（同 RULES-LEDGER 的鐵則）。
判定準則（origin = 誰決定，與 exec_via 誰按按鈕 無關）：
- system — plan.md 有 ref／plan #N／規則執行（梯級停利、停損鐵律、harvest 訊號）／plan v2 砍單
- user — 未列於 plan／偏離 plan 階梯／違反既有指令／無 plan 依據的自主判斷
- 判不出來就留 unknown，不要猜
2026-06-18 是必記的反例：九檔在 App 手動出清，但砍因來自 plan v2 → 系統決策、手動執行。若用執行方式推論決策來源，會把全帳最大 alpha 事件（+$8,997）誤記成用戶自主交易。
Step 2 — 三個指標，缺一不可
三者答不同問題，只看任一個都會誤導：交易 α（進出對不對）、持有 α（該不該繼續抱）、beta capture（行情好的時候吃到沒有）。
python3 tools/trade_ledger.py score --by origin-side --since <期初>
python3 tools/trade_ledger.py score --by bucket --since <期初>
python3 tools/trade_ledger.py holding-alpha --window 90
python3 tools/trade_ledger.py beta-capture --window 180 --bench SMH
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.
- 2d ago Changed 02248fd31311
- 5d ago Changed · +5 lines c31233a22a28
- 13d ago First seen · 301 lines · 85 tokens per session scan A 3669df1e81b9
trade-review is a skill published in the GitHub repository PatrickSUDO/fadacai-portfolio (139 stars, last pushed 3d ago), licensed MIT. It adds 85 tokens to every session and 6,540 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 2026-08-30.
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.
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.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.