@v587d/capital-generation 2.7.10 → 2.7.12

package/selected-skills/InvestSkill/plugins/us-stock-analysis/skills/stock-screener/SKILL.md

@@ -61,184 +61,18 @@ Screen and rank multiple US equity tickers across five analytical dimensions —
 
 ---
 
-## Scoring Framework
+## Read the Parts
 
-Score every stock on five dimensions, each rated 0–10. Scores are composites — compute sub-scores for each factor listed, then average them into the dimension score (round to one decimal).
+Everything below the surface of this file lives in `references/`. Open a part with `read`,
+resolved against this skill's base directory; each part is sized to arrive complete in one
+`read`. If a receipt shows `[... tool result middle pruned ...]`, re-read it with `offset`
+before concluding anything is missing.
 
-### 1. Valuation Score (0–10)
+- `references/10-scoring-framework.md` — Scoring Framework
+- `references/11-output-format.md` — Output Format
+- `references/12-invalidation-and-signal.md` — Thesis Invalidation; Standard Signal Output (Multi-Stock)
 
-Higher score = cheaper relative to fundamentals.
+Loading this file is not reading the skill: the steps, templates, and thresholds exist only
+in the parts above. Say which parts you opened, name the ones you did not, and never report a
+step or a template you have not read in this session.
 
-| Sub-factor | How to score |
-|---|---|
-| P/E vs. sector median | Score 10 if P/E < 50 % of sector median, scale linearly to 0 if P/E > 200 % |
-| Price-to-Sales (P/S) | Score 10 if P/S < 1, score 0 if P/S > 20, linear in between |
-| EV/EBITDA | Score 10 if < 8x, score 0 if > 40x, linear in between |
-| PEG Ratio | Score 10 if PEG < 0.75, score 0 if PEG > 3.0, linear in between; use N/A weight if earnings negative |
-
-Average the available sub-scores → **Valuation Score**.
-
-### 2. Quality Score (0–10)
-
-Higher score = stronger business fundamentals.
-
-| Sub-factor | How to score |
-|---|---|
-| Piotroski F-Score | Score = F-Score × (10/9), capped at 10 |
-| ROIC vs. WACC spread | Score 10 if spread ≥ +10 pp, score 5 if at parity, score 0 if spread ≤ −10 pp |
-| Gross margin trend (3-year) | Score 10 if expanding ≥ +3 pp/yr, score 5 if flat, score 0 if contracting ≥ −3 pp/yr |
-| Debt-to-equity | Score 10 if D/E < 0.2, score 0 if D/E > 3.0, linear in between |
-
-Average the available sub-scores → **Quality Score**.
-
-### 3. Momentum Score (0–10)
-
-Higher score = stronger price and relative performance momentum.
-
-| Sub-factor | How to score |
-|---|---|
-| Price vs. MA50 | Score 10 if price ≥ 10 % above MA50, score 5 at MA50, score 0 if ≥ 10 % below |
-| Price vs. MA200 | Score 10 if price ≥ 20 % above MA200, score 5 at MA200, score 0 if ≥ 20 % below |
-| RSI (14-day) | Score 10 if RSI 55–70 (strong but not overbought), score 5 at RSI 50, score 0 if RSI < 30 or > 80 |
-| 3M relative performance vs. SPY | Score 10 if outperforming by ≥ +10 %, score 5 if in-line, score 0 if underperforming by ≥ −10 % |
-| 6M relative performance vs. SPY | Same scale as 3M |
-| 12M relative performance vs. SPY | Same scale as 12M |
-
-Average the available sub-scores → **Momentum Score**.
-
-### 4. Sentiment Score (0–10)
-
-Higher score = more positive smart-money and market positioning signals.
-
-| Sub-factor | How to score |
-|---|---|
-| Insider net buying (trailing 6M) | Score 10 if net buy value > $5 M, score 5 if neutral/mixed, score 0 if net sell > $5 M |
-| Institutional accumulation (QoQ) | Score 10 if institutions net added ≥ +2 % of float, score 5 if flat, score 0 if reduced ≥ −2 % |
-| Short interest direction | Score 10 if short interest fell ≥ −20 % MoM (shorts covering), score 5 if flat, score 0 if short interest rose ≥ +20 % |
-| Analyst estimate revisions (90d) | Score 10 if ≥ 3 upgrades and no downgrades, score 0 if ≥ 3 downgrades and no upgrades |
-
-Average the available sub-scores → **Sentiment Score**.
-
-### 5. Growth Score (0–10)
-
-Higher score = stronger and more reliable growth trajectory.
-
-| Sub-factor | How to score |
-|---|---|
-| Revenue growth YoY | Score 10 if ≥ 30 %, score 5 if 10 %, score 0 if ≤ 0 % |
-| EPS growth YoY | Score 10 if ≥ 40 %, score 5 if 15 %, score 0 if ≤ 0 %; use N/A weight if negative base |
-| Forward revenue growth estimate | Same scale as revenue growth YoY |
-| Guidance trend (most recent quarter) | Score 10 if raised, score 5 if maintained, score 0 if lowered or withdrawn |
-
-Average the available sub-scores → **Growth Score**.
-
-### TOTAL Score
-
-```
-TOTAL = (Valuation × 0.20) + (Quality × 0.25) + (Momentum × 0.20) + (Sentiment × 0.15) + (Growth × 0.20)
-```
-
-Weights reflect: quality as the most durable factor, with equal emphasis on valuation, momentum, and growth, and a slight discount on sentiment which is noisier.
-
----
-
-## Output Format
-
-### Section 1 — Data Sources
-
-State the date and source(s) used for prices and financials.
-
-### Section 2 — Screener Leaderboard
-
-Produce a ranked table sorted by TOTAL score descending:
-
-```
-| Rank | Ticker | Val  | Quality | Momentum | Sentiment | Growth | TOTAL | Signal     |
-|------|--------|------|---------|----------|-----------|--------|-------|------------|
-|  1   | AAPL   | 7.2  |   8.1   |   6.9    |    7.5    |  8.0   |  7.5  | BUY        |
-|  2   | MSFT   | 6.8  |   8.4   |   7.1    |    6.9    |  7.8   |  7.4  | BUY        |
-| ...  |  ...   | ...  |   ...   |   ...    |    ...    |  ...   |  ...  |    ...     |
-```
-
-Signal legend:
-- TOTAL ≥ 7.5 → 🟢 STRONG BUY
-- TOTAL 6.0–7.4 → 🟢 BUY
-- TOTAL 4.5–5.9 → 🟡 HOLD
-- TOTAL 3.0–4.4 → 🔴 AVOID
-- TOTAL < 3.0 → 🔴 STRONG AVOID
-
-### Section 3 — Top 3 Deep Dives
-
-For each of the top 3 ranked stocks, provide:
-
-**[RANK] [TICKER] — [Company Name]**
-
-- **Why it scores high**: 3–5 bullet points, one per standout dimension
-- **Key risk**: The single most important risk that could invalidate the bull case
-- **Entry consideration**: Suggested price zone or trigger (e.g., pullback to MA50, post-earnings confirmation)
-- **Investment horizon**: Short / Medium / Long-term suitability
-
-### Section 4 — Avoid List (Bottom 3)
-
-For each of the bottom 3 ranked stocks, provide:
-
-**[RANK] [TICKER] — [Company Name]**
-
-- **Why it scores low**: 2–3 bullet points identifying the weakest dimensions
-- **Potential catalyst to watch**: One event or data point that could change the thesis (don't ignore — flag for reassessment)
-
-### Section 5 — Screening Notes
-
-- Any tickers excluded by filters (and which filter triggered)
-- Data gaps or caveats (e.g., "ROIC unavailable for XXXX, sub-score excluded")
-- Sector / macro context relevant to this batch of stocks
-- Correlation warning if top picks are highly correlated (e.g., all mega-cap tech)
-
----
-
-## Thesis Invalidation
-
-A ranking is a snapshot. After the screening summary, state what would reorder it:
-
-**The Top Pick loses its rank if:**
-- Its composite falls below the #2 ticker's score on the next re-run — name the dimension most likely to slip (usually Momentum or Sentiment, which move fastest)
-- Its Valuation score was carried by a single depressed multiple that mean-reverts
-- A `bear-case` run on it surfaces a red flag none of the five dimensions weight (accounting quality, governance, customer concentration)
-
-**The Avoid list is wrong if:**
-- A name was penalized for a one-off (impairment, litigation charge, guidance reset) that the next quarter normalizes
-- Momentum was measured across a market-wide drawdown rather than a stock-specific one
-
-**The Market Bias flips if:**
-- The average composite crosses 6.0 or 4.0 — check whether one outlier dragged it, not the universe
-
-**Re-run this screen when:**
-- [ ] Any screened ticker reports earnings
-- [ ] The universe changes (add/remove a ticker — the ranking is relative)
-- [ ] 30 days have elapsed (momentum and sentiment decay fastest)
-- [ ] The sector or factor regime shifts (`economics-analysis` / `sector-analysis`)
-
----
-
-## Standard Signal Output (Multi-Stock)
-
-End every screening session with this standardized block reflecting the overall health of the screened universe:
-
-```
-╔══════════════════════════════════════════════╗
-║           INVESTMENT SIGNAL — SCREENING SUMMARY           ║
-╠══════════════════════════════════════════════╣
-║ Top Pick:    [TICKER] — Score X.X / 10       ║
-║ Avg Score:   X.X / 10 (screened universe)    ║
-║ Tickers Screened: N                          ║
-╠══════════════════════════════════════════════╣
-║ Market Bias: BULLISH / NEUTRAL / BEARISH     ║
-║ Best Sector: [SECTOR]                        ║
-╚══════════════════════════════════════════════╝
-```
-
-Score Guide: 8.0–10.0 Strongly Bullish | 6.0–7.9 Moderately Bullish | 4.0–5.9 Neutral | 2.0–3.9 Moderately Bearish | 0.0–1.9 Strongly Bearish
-Market Bias: derived from the average composite score of the screened universe. BULLISH if avg ≥ 6.0, NEUTRAL if 4.0–5.9, BEARISH if < 4.0.
-Best Sector: the GICS sector with the highest average composite score across all screened tickers in that sector.
-
-**Disclaimer:** Educational analysis only. Not financial advice.

package/selected-skills/InvestSkill/plugins/us-stock-analysis/skills/stock-screener/references/10-scoring-framework.md

@@ -0,0 +1,85 @@
+# Scoring Framework
+
+Part 1 of 3 for `stock-screener` — the five scores, their bands, and how TOTAL is composed
+See `SKILL.md` for what to read and when; this part is procedure, not routing.
+
+## Scoring Framework
+
+Score every stock on five dimensions, each rated 0–10. Scores are composites — compute sub-scores for each factor listed, then average them into the dimension score (round to one decimal).
+
+### 1. Valuation Score (0–10)
+
+Higher score = cheaper relative to fundamentals.
+
+| Sub-factor | How to score |
+|---|---|
+| P/E vs. sector median | Score 10 if P/E < 50 % of sector median, scale linearly to 0 if P/E > 200 % |
+| Price-to-Sales (P/S) | Score 10 if P/S < 1, score 0 if P/S > 20, linear in between |
+| EV/EBITDA | Score 10 if < 8x, score 0 if > 40x, linear in between |
+| PEG Ratio | Score 10 if PEG < 0.75, score 0 if PEG > 3.0, linear in between; use N/A weight if earnings negative |
+
+Average the available sub-scores → **Valuation Score**.
+
+### 2. Quality Score (0–10)
+
+Higher score = stronger business fundamentals.
+
+| Sub-factor | How to score |
+|---|---|
+| Piotroski F-Score | Score = F-Score × (10/9), capped at 10 |
+| ROIC vs. WACC spread | Score 10 if spread ≥ +10 pp, score 5 if at parity, score 0 if spread ≤ −10 pp |
+| Gross margin trend (3-year) | Score 10 if expanding ≥ +3 pp/yr, score 5 if flat, score 0 if contracting ≥ −3 pp/yr |
+| Debt-to-equity | Score 10 if D/E < 0.2, score 0 if D/E > 3.0, linear in between |
+
+Average the available sub-scores → **Quality Score**.
+
+### 3. Momentum Score (0–10)
+
+Higher score = stronger price and relative performance momentum.
+
+| Sub-factor | How to score |
+|---|---|
+| Price vs. MA50 | Score 10 if price ≥ 10 % above MA50, score 5 at MA50, score 0 if ≥ 10 % below |
+| Price vs. MA200 | Score 10 if price ≥ 20 % above MA200, score 5 at MA200, score 0 if ≥ 20 % below |
+| RSI (14-day) | Score 10 if RSI 55–70 (strong but not overbought), score 5 at RSI 50, score 0 if RSI < 30 or > 80 |
+| 3M relative performance vs. SPY | Score 10 if outperforming by ≥ +10 %, score 5 if in-line, score 0 if underperforming by ≥ −10 % |
+| 6M relative performance vs. SPY | Same scale as 3M |
+| 12M relative performance vs. SPY | Same scale as 12M |
+
+Average the available sub-scores → **Momentum Score**.
+
+### 4. Sentiment Score (0–10)
+
+Higher score = more positive smart-money and market positioning signals.
+
+| Sub-factor | How to score |
+|---|---|
+| Insider net buying (trailing 6M) | Score 10 if net buy value > $5 M, score 5 if neutral/mixed, score 0 if net sell > $5 M |
+| Institutional accumulation (QoQ) | Score 10 if institutions net added ≥ +2 % of float, score 5 if flat, score 0 if reduced ≥ −2 % |
+| Short interest direction | Score 10 if short interest fell ≥ −20 % MoM (shorts covering), score 5 if flat, score 0 if short interest rose ≥ +20 % |
+| Analyst estimate revisions (90d) | Score 10 if ≥ 3 upgrades and no downgrades, score 0 if ≥ 3 downgrades and no upgrades |
+
+Average the available sub-scores → **Sentiment Score**.
+
+### 5. Growth Score (0–10)
+
+Higher score = stronger and more reliable growth trajectory.
+
+| Sub-factor | How to score |
+|---|---|
+| Revenue growth YoY | Score 10 if ≥ 30 %, score 5 if 10 %, score 0 if ≤ 0 % |
+| EPS growth YoY | Score 10 if ≥ 40 %, score 5 if 15 %, score 0 if ≤ 0 %; use N/A weight if negative base |
+| Forward revenue growth estimate | Same scale as revenue growth YoY |
+| Guidance trend (most recent quarter) | Score 10 if raised, score 5 if maintained, score 0 if lowered or withdrawn |
+
+Average the available sub-scores → **Growth Score**.
+
+### TOTAL Score
+
+```
+TOTAL = (Valuation × 0.20) + (Quality × 0.25) + (Momentum × 0.20) + (Sentiment × 0.15) + (Growth × 0.20)
+```
+
+Weights reflect: quality as the most durable factor, with equal emphasis on valuation, momentum, and growth, and a slight discount on sentiment which is noisier.
+
+---

package/selected-skills/InvestSkill/plugins/us-stock-analysis/skills/stock-screener/references/11-output-format.md

@@ -0,0 +1,58 @@
+# Output Format
+
+Part 2 of 3 for `stock-screener` — the five output sections of a screening report
+See `SKILL.md` for what to read and when; this part is procedure, not routing.
+
+## Output Format
+
+### Section 1 — Data Sources
+
+State the date and source(s) used for prices and financials.
+
+### Section 2 — Screener Leaderboard
+
+Produce a ranked table sorted by TOTAL score descending:
+
+```
+| Rank | Ticker | Val  | Quality | Momentum | Sentiment | Growth | TOTAL | Signal     |
+|------|--------|------|---------|----------|-----------|--------|-------|------------|
+|  1   | AAPL   | 7.2  |   8.1   |   6.9    |    7.5    |  8.0   |  7.5  | BUY        |
+|  2   | MSFT   | 6.8  |   8.4   |   7.1    |    6.9    |  7.8   |  7.4  | BUY        |
+| ...  |  ...   | ...  |   ...   |   ...    |    ...    |  ...   |  ...  |    ...     |
+```
+
+Signal legend:
+- TOTAL ≥ 7.5 → 🟢 STRONG BUY
+- TOTAL 6.0–7.4 → 🟢 BUY
+- TOTAL 4.5–5.9 → 🟡 HOLD
+- TOTAL 3.0–4.4 → 🔴 AVOID
+- TOTAL < 3.0 → 🔴 STRONG AVOID
+
+### Section 3 — Top 3 Deep Dives
+
+For each of the top 3 ranked stocks, provide:
+
+**[RANK] [TICKER] — [Company Name]**
+
+- **Why it scores high**: 3–5 bullet points, one per standout dimension
+- **Key risk**: The single most important risk that could invalidate the bull case
+- **Entry consideration**: Suggested price zone or trigger (e.g., pullback to MA50, post-earnings confirmation)
+- **Investment horizon**: Short / Medium / Long-term suitability
+
+### Section 4 — Avoid List (Bottom 3)
+
+For each of the bottom 3 ranked stocks, provide:
+
+**[RANK] [TICKER] — [Company Name]**
+
+- **Why it scores low**: 2–3 bullet points identifying the weakest dimensions
+- **Potential catalyst to watch**: One event or data point that could change the thesis (don't ignore — flag for reassessment)
+
+### Section 5 — Screening Notes
+
+- Any tickers excluded by filters (and which filter triggered)
+- Data gaps or caveats (e.g., "ROIC unavailable for XXXX, sub-score excluded")
+- Sector / macro context relevant to this batch of stocks
+- Correlation warning if top picks are highly correlated (e.g., all mega-cap tech)
+
+---

package/selected-skills/InvestSkill/plugins/us-stock-analysis/skills/stock-screener/references/12-invalidation-and-signal.md

@@ -0,0 +1,51 @@
+# Thesis Invalidation and Signal Output
+
+Part 3 of 3 for `stock-screener` — the invalidation contract and the multi-stock signal shape
+See `SKILL.md` for what to read and when; this part is procedure, not routing.
+
+## Thesis Invalidation
+
+A ranking is a snapshot. After the screening summary, state what would reorder it:
+
+**The Top Pick loses its rank if:**
+- Its composite falls below the #2 ticker's score on the next re-run — name the dimension most likely to slip (usually Momentum or Sentiment, which move fastest)
+- Its Valuation score was carried by a single depressed multiple that mean-reverts
+- A `bear-case` run on it surfaces a red flag none of the five dimensions weight (accounting quality, governance, customer concentration)
+
+**The Avoid list is wrong if:**
+- A name was penalized for a one-off (impairment, litigation charge, guidance reset) that the next quarter normalizes
+- Momentum was measured across a market-wide drawdown rather than a stock-specific one
+
+**The Market Bias flips if:**
+- The average composite crosses 6.0 or 4.0 — check whether one outlier dragged it, not the universe
+
+**Re-run this screen when:**
+- [ ] Any screened ticker reports earnings
+- [ ] The universe changes (add/remove a ticker — the ranking is relative)
+- [ ] 30 days have elapsed (momentum and sentiment decay fastest)
+- [ ] The sector or factor regime shifts (`economics-analysis` / `sector-analysis`)
+
+---
+
+## Standard Signal Output (Multi-Stock)
+
+End every screening session with this standardized block reflecting the overall health of the screened universe:
+
+```
+╔══════════════════════════════════════════════╗
+║           INVESTMENT SIGNAL — SCREENING SUMMARY           ║
+╠══════════════════════════════════════════════╣
+║ Top Pick:    [TICKER] — Score X.X / 10       ║
+║ Avg Score:   X.X / 10 (screened universe)    ║
+║ Tickers Screened: N                          ║
+╠══════════════════════════════════════════════╣
+║ Market Bias: BULLISH / NEUTRAL / BEARISH     ║
+║ Best Sector: [SECTOR]                        ║
+╚══════════════════════════════════════════════╝
+```
+
+Score Guide: 8.0–10.0 Strongly Bullish | 6.0–7.9 Moderately Bullish | 4.0–5.9 Neutral | 2.0–3.9 Moderately Bearish | 0.0–1.9 Strongly Bearish
+Market Bias: derived from the average composite score of the screened universe. BULLISH if avg ≥ 6.0, NEUTRAL if 4.0–5.9, BEARISH if < 4.0.
+Best Sector: the GICS sector with the highest average composite score across all screened tickers in that sector.
+
+**Disclaimer:** Educational analysis only. Not financial advice.

package/selected-skills/claude-for-financial-services-cn/UPSTREAM.md

@@ -166,6 +166,7 @@
   而 catalog 反查只会说"包里找不到 SKILL.md"）。
   `package.json` 的 `files` 已登记 `selected-skills/claude-for-financial-services-cn`；随包的是 63 份
   `SKILL.md`（规范根 31 + 另五条线 32）+ `LICENSE` + 本文件，净增 65 个文件，整包未压缩 3.49 → 3.98 MiB。
+- Visibility layering（2026-10-14，§8.6 第三个改写理由）：`china-idea-generation`、`china-sector-overview`、`china-catalyst-calendar` 三颗的 `SKILL.md` 超过宿主一次加载的可见上限（剪枝阈值 8,192 码点，回执里中段换成 `[... tool result middle pruned ...]`），改成「入口册 + 分册」：流程与模板搬进 `references/10-*.md`、`11-*.md`，入口只留 Purpose、Data Sources、China-Specific 与 Quality Checks。三颗分别 8,475→9,385、8,600→9,523、9,121→10,512 字符（只增不减），逐行核对原正文**没有一行丢失**，只有入口里那几行分派指针是我改写的。**Apache-2.0 §4(b) 那行声明跟着搬**：每份新分册的第一行都带同一句可见声明（口径已定：凡被改写的正文各带一行，不留给入口册独占），`test/selected-skills-content.test.mjs` 现在逐份 `.md` 问这一行，不只问 `SKILL.md`。分层的体积判据是 `read` **渲染后**的长度（每行前缀 `N: ` + `<path>`/`<content>` 包装），不是文件字符数，建模只在那条闸门的 `readEnvelopeChars` 有一份。
 - Maintenance snapshot (checked 2026-10-11): 15 次提交里 10 次落在 2026-06-08 与 06-09 两天，
   此后三个月无动作，直到 2026-09-14 那一次修 AkShare 服务端返回空数组的 bug（也就是本 commit）。
   831 stars、3 open issue，无 release / tag。因此标 `watchlist`：内容成体系、维护靠一次性的集中搬运，

package/selected-skills/claude-for-financial-services-cn/vertical-plugins/china-finance/skills/china-catalyst-calendar/SKILL.md

@@ -11,64 +11,6 @@ description: Track upcoming catalysts for A-share coverage universe — earnings
 
 Build and maintain a **A股催化剂日历** tracking upcoming events that could materially impact stock prices within a coverage universe.
 
-## Catalyst Types (A-share Specific)
-
-### 1. Earnings & Financial Reports
-
-| Event | Typical Timing | Notes |
-|-------|---------------|-------|
-| 业绩预告 (earnings preview) | 1-4 weeks before | Mandatory if variance >50% from prior |
-| 季报 (quarterly report) | 1 month after quarter-end | 10-day grace period possible |
-| 中报 (semi-annual report) | 2 months after H1 | 15-day grace period |
-| 年报 (annual report) | 4 months after year-end | Most important event of the year |
-| 业绩说明会 (earnings call) | Same day or next trading day | 上证e互动 / 深交所互动易 |
-
-### 2. Regulatory & Policy Events
-
-| Event | Impact | Typical Timing |
-|-------|--------|---------------|
-| 央行MLF/LPR操作 | High (liquidity, rates) | 15th of each month (MLF) |
-| 央行降准/降息 | Very high | Ad-hoc, 国新办发布会 |
-| 国务院政策发布 | Sector-specific | Ad-hoc |
-| 部委监管政策 (NMPA, MIIT, etc.) | Industry-specific | Ad-hoc |
-| 集采结果 (volume-based procurement) | Pharma/medtech | Quarterly cycles |
-| 行业准入政策变化 | Sector-specific | Ad-hoc |
-| 反垄断调查 | Specific companies | Ad-hoc |
-
-### 3. Corporate Events
-
-| Event | Impact | Notes |
-|-------|--------|-------|
-| 股东大会 (AGM) | Low-medium | Voting on key items |
-| 分红/送股/转增 (dividend/rights) | Medium | Ex-dividend date matters |
-| 限售股解禁 (lock-up expiry) | Medium-high | Watch large blocks |
-| 增减持公告 (shareholder transactions) | Low-medium | 5% threshold triggers disclosure |
-| 回购 (share buyback) | Low-medium | Implementation tracking |
-| 并购重组 (M&A announcements) | High | 停牌 until announcement |
-| 增发/配股 (seasoned equity) | High | Dilution impact |
-| 可转债发行/转股 | Medium | Conversion tracking |
-
-### 4. Sector / Industry Events
-
-| Event | Example Sectors | Notes |
-|-------|----------------|-------|
-| 行业展会/论坛 | 新能源, 半导体, 医药 | Networking, product announcements |
-| 政策研讨会 | 环保, 教育, 互联网 | Policy direction signals |
-| 行业协会数据发布 | 汽车, 光伏, 风电 | Monthly/quarterly stats |
-| 国际展会 (CES, IFA, etc.) | 消费电子 | New product launches |
-
-### 5. Macro Data Releases
-
-| Indicator | Frequency | Impact |
-|-----------|-----------|--------|
-| PMI (制造业/非制造业) | Monthly (1st) | Market-wide |
-| CPI / PPI | Monthly (9-10th) | Rates, commodities |
-| 社会融资规模 / M2 | Monthly (10-15th) | Liquidity |
-| 外汇储备 | Monthly | FX sentiment |
-| 工业增加值 | Monthly | Growth indicator |
-| 零售数据 | Monthly | Consumption |
-| 就业数据 | Quarterly | Labor market |
-
 ## Data Sources
 
 A calendar is a list of dates and documents, and this plugin obtains none of them from inside this step: retrieval has exactly one entry — the main agent delegating it to the role that owns market data or web and disclosure material — and a calendar holds no data-service key and issues no query of its own.
@@ -79,123 +21,10 @@ Hand over one brief per family, each naming the ticker or the indicator, the fie
 - 公司底色：profile, 股本结构, and the historical earnings pattern that tells you which quarter is material
 - 交易状态：current quote and trading context for each name on the calendar
 - 全市场：指数行情 as macro backdrop, and market-wide news flow
-- 宏观发布：the indicator calendar above (CPI / PMI / 工业增加值 / 零售 / 就业) with its release dates
+- 宏观发布：the indicator calendar in `references/10-catalyst-types.md` (CPI / PMI / 工业增加值 / 零售 / 就业) with its release dates
 
 The disclosure venues these briefs eventually resolve to — 巨潮公告、上交所公告、深交所公告 — are the host retrieval role's business, not a browsing task for this step: name the document type you need and let the retrieval path decide where it lives. In a role-split host, delegate rather than searching from here, then keep calendar entries that came back and mark the rest as unconfirmed dates.
 
-## Workflow
-
-### Step 1: Define Coverage Universe
-
-Identify the stocks and sectors to track. Typical A-share coverage universe:
-- 50-200 names
-- Organized by sector/industry
-- Priority tiers (P1 = must-track, P2 = watchlist)
-
-### Step 2: Build Calendar Entries
-
-**For each catalyst, record:**
-
-```json
-{
-  "date": "2024-04-25",
-  "type": "earnings",
-  "subtype": "季报",
-  "ticker": "{{TICKER}}",
-  "company": "{{COMPANY_NAME}}",
-  "importance": "high",
-  "notes": "Q1 2024 results; watch 批价 and inventory",
-  "status": "confirmed"
-}
-```
-
-**Catalyst types in JSON:**
-- `earnings` — quarterly/semi/annual reports
-- `earnings_call` — 业绩说明会
-- `regulatory` — 监管政策发布
-- `policy` — 宏观政策 (央行, 国务院)
-- `corporate` — 公司事件 (分红, 解禁, M&A)
-- `macro_data` — 经济数据发布
-- `sector_event` — 行业展会/论坛
-- `lockup_expiry` — 限售股解禁
-
-### Step 3: Prioritize Catalysts
-
-**Importance levels:**
-- **Critical**: Likely to move stock >10% (earnings, M&A, major policy)
-- **High**: Likely to move stock 5-10% (regulatory decisions, industry data)
-- **Medium**: Watch item, context-setting (dividend, conference participation)
-- **Low**: Background noise (routine filings, minor announcements)
-
-### Step 4: Pre-Catalyst Preparation
-
-**1 week before critical catalysts:**
-- Pull latest data and consensus
-- Prepare scenario analysis
-- Draft preliminary positioning note
-- Alert stakeholders if high-impact
-
-**1 day before critical catalysts:**
-- Final data check
-- Confirm release timing (morning vs afternoon)
-- Prepare pre-market positioning note
-- Set monitoring alerts
-
-### Step 5: Post-Catalyst Update
-
-After catalyst passes:
-- Record actual outcome
-- Compare vs scenario framework
-- Update price target / thesis if material
-- Move to "completed" section
-- Flag next catalyst in queue
-
-## Calendar Format
-
-### Weekly View
-
-```
-【本周催化剂日历】[YYYY-MM-DD 至 YYYY-MM-DD]
-
-周一 [Date]
-  - [Time] [Ticker] [Company] — [Event type] — [Importance]
-  - [Time] [Macro event] — [Impact assessment]
-
-周二 [Date]
-  ...
-
-本周重点：
-- [Top 2-3 catalysts to watch]
-- [Market-wide risk events]
-```
-
-### Monthly View
-
-```
-【X月重要事件日历】
-
-财报窗口:
-- [Week 1]: [Sector] Q[X] results: [List of companies]
-- [Week 2]: [Sector] Q[X] results: [List of companies]
-
-政策窗口:
-- [Date]: [Policy event] — [Expected impact]
-
-解禁窗口:
-- [Date]: [Ticker] — [Amount] shares unlocking — [Risk assessment]
-
-宏观数据:
-- [Date]: [Indicator] — [Consensus] — [Previous]
-```
-
-### Upcoming Catalysts Table
-
-| Date | Company | Event | Importance | Watch Item |
-|------|---------|-------|------------|------------|
-| {{DATE}} | {{COMPANY_NAME}} ({{TICKER}}) | {{EVENT_TYPE}} | {{IMPORTANCE}} | {{WATCH_ITEMS}} |
-| Example | 贵州茅台 (600519) | Q1 年报 | Critical | 批价, 动销 |
-| 04-30 | 工信部 | 新能源车月度数据 | Medium | 销量, 渗透率 |
-
 ## China-Specific Considerations
 
 ### Earnings Calendar Patterns
@@ -235,18 +64,6 @@ After catalyst passes:
 - 分红实施公告: typically 2-4 weeks after AGM approval
 - 高送转 (high bonus issue): historically market-positive event
 
-## Integration with Other Skills
-
-| Related Skill | Integration Point |
-|---------------|-------------------|
-| china-earnings-analysis | Post-earnings catalyst review |
-| china-earnings-preview | Pre-earnings scenario setup |
-| china-thesis-tracker | Catalyst milestone tracking |
-| china-morning-note | Daily catalyst briefing |
-| china-market-researcher | Sector catalyst themes |
-
-A skill named above is an option for the user, not a step this role can take: only the skills the user switched on exist in this session, and what this plugin deliberately does not offer — placing or amending an order on the user's behalf — is not reachable at all. Say what you would check next and let the user decide.
-
 ## Quality Checks
 
 Before delivering:
@@ -256,3 +73,18 @@ Before delivering:
 - [ ] Importance levels assigned consistently
 - [ ] Watch items specific and actionable
 - [ ] Pre-catalyst preparation tasks defined
+
+## Read the Parts
+
+Everything below the surface of this file lives in `references/`. Open a part with `read`,
+resolved against this skill's base directory; each part is sized to arrive complete in one
+`read`. If a receipt shows `[... tool result middle pruned ...]`, re-read it with `offset`
+before concluding anything is missing.
+
+- `references/10-catalyst-types.md` — Catalyst Types (A-share Specific)
+- `references/11-workflow-and-calendar.md` — Workflow; Calendar Format; Integration with Other Skills
+
+Loading this file is not reading the skill: the steps, templates, and thresholds exist only
+in the parts above. Say which parts you opened, name the ones you did not, and never report a
+step or a template you have not read in this session.
+