@v587d/capital-generation 2.7.10 → 2.7.12

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

@@ -33,161 +33,6 @@ Hand the retrieval roles one brief per family of material:
 
 In a role-split host, delegate with those briefs rather than reaching for a feed from here. What does not come back is written up as a gap in that section; a sector size or growth rate is never rounded off from memory.
 
-## Workflow
-
-### Step 1: Define Scope & Angle
-
-**Clarify:**
-- Sector / industry focus (e.g., 白酒, 半导体, 新能源汽车)
-- Angle (e.g., investment theme, competitive analysis, turnaround story)
-- Geographic scope (A-share only, or include HK-listed / US-listed Chinese)
-- Time horizon (cyclical analysis, secular trends, near-term trade)
-
-### Step 2: Market Size & Structure
-
-**Industry overview:**
-
-| Metric | Data | Source |
-|--------|------|--------|
-| Total market size | 市场规模 (亿元/亿元) | 国家统计局, 行业协会 |
-| Growth rate | 同比增速 / CAGR | Historical data |
-| Market share | CR5, CR10 concentration | Company filings |
-| Penetration rate | For new industries | Industry reports |
-| Export/import | 进出口数据 | 海关总署 |
-
-**A-share representation:**
-- Number of listed companies in sector
-- Total market cap (总市值 / 流通市值)
-- Average PE / PB multiples
-- Liquidity (average daily turnover)
-
-### Step 3: Competitive Landscape
-
-**Peer mapping:**
-
-Ask the host's retrieval path for the 板块成分股 list of the industry being covered, by its Chinese industry name, and take the constituents from what comes back.
-
-**For each major player, retrieve:** 最新价 / 市值 / 倍数, 收入与利润率的历史序列, and the business description — one brief per field family, same as-of date across the whole peer set.
-
-**Competitive analysis table:**
-
-| Company | Ticker | Market Cap (亿) | Revenue (亿) | YoY Growth | Gross Margin | Net Margin | PE (TTM) | Market Share |
-|---------|--------|----------------|-------------|------------|-------------|------------|----------|-------------|
-| | | | | | | | | |
-
-**Competitive positioning:**
-- Market share trends (gaining or losing)
-- Product positioning (premium, mid-tier, mass market)
-- Geographic footprint (national vs regional)
-- Distribution strength (渠道能力)
-- Brand equity (品牌力)
-
-### Step 4: Trading Multiples & Valuation
-
-**Sector multiples:**
-
-| Metric | Current | 1Y High | 1Y Low | 5Y Average | Historical High | Historical Low |
-|--------|---------|---------|--------|------------|----------------|----------------|
-| Average PE | | | | | | |
-| Average PB | | | | | | |
-| Average PS | | | | | | |
-| EV/EBITDA | | | | | | |
-
-**Multiple dispersion:**
-- Premium names (high multiple vs sector)
-- Value names (low multiple vs sector)
-- Historical range and where we are in cycle
-
-### Step 5: Policy Environment
-
-**China-specific policy analysis:**
-
-| Policy Area | Current Status | Impact |
-|-------------|---------------|--------|
-| 产业政策 | 支持/限制/中性 | Direct sector impact |
-| 环保政策 | 双碳目标 | Cost structure impact |
-| 监管政策 | 集采/反垄断 | Margin / market share impact |
-| 补贴政策 | 新能源/半导体补贴 | Competitiveness impact |
-| 货币政策 | 宽松/中性/紧缩 | Financing cost impact |
-
-**Key regulatory bodies:**
-- 发改委 (NDRC) — industrial policy, pricing
-- 工信部 (MIIT) — manufacturing, tech, telecom
-- 生态环境部 (MEE) — environmental compliance
-- 卫健委 (NHC) — healthcare, pharmaceuticals
-- 证监会 (CSRC) — capital markets
-- 央行 (PBoC) — monetary policy
-
-### Step 6: Key Drivers & Trends
-
-**Secular trends (3-5 year):**
-- Technology adoption (技术替代)
-- Consumption upgrade/downgrade (消费升级/降级)
-- Demographic shifts (人口结构)
-- Supply chain localization (供应链国产化)
-- Environmental transition (双碳/ESG)
-
-**Cyclical factors:**
-- Inventory cycles (库存周期)
-- Capacity utilization (产能利用率)
-- Pricing trends (价格趋势)
-- Demand momentum (需求 momentum)
-
-### Step 7: Investment Themes
-
-**Thematic angles:**
-
-1. **Policy-driven**: 国产替代, 新基建, 乡村振兴
-2. **Demand-driven**: 消费升级, 老龄化, 出海
-3. **Supply-driven**: 产能出清, 行业整合, 龙头集中
-4. **Technology-driven**: AI应用, 新能源, 生物医药创新
-
-**For each theme:**
-- Investment thesis
-- Key names to express the theme
-- Timeline and catalysts
-- Risks and headwinds
-
-### Step 8: Trading Ideas
-
-**Ideas shortlist (from sector overview):**
-
-| Idea | Ticker | Direction | Thesis | Catalyst | Risk |
-|------|--------|-----------|--------|----------|------|
-| | | Long / Short | | | |
-
-### Step 9: Report Structure
-
-**Standard A-share sector overview format:**
-
-```
-【XX证券】[行业] 深度报告：[标题]
-
-一、行业概述
-   市场规模、增速、发展阶段
-
-二、竞争格局
-   主要玩家、市场份额、竞争要素
-
-三、政策环境
-   监管框架、产业政策、影响分析
-
-四、财务分析
-   行业盈利能力、ROE、杠杆水平
-
-五、估值分析
-   当前 multiples vs 历史 vs 国际对标
-
-六、核心驱动因素
-   长期趋势、短期催化、周期位置
-
-七、投资建议
-   重点标的、目标价、评级
-
-八、风险提示
-   政策风险、需求风险、竞争风险
-```
-
 ## China-Specific Considerations
 
 ### A-share Market Structure
@@ -254,4 +99,18 @@ Before delivering:
 - [ ] Ideas shortlist included (3-5 names)
 - [ ] Risk factors specific to China market included
 > 取数档位（接哪家数据服务、用哪个密钥）由宿主的凭据域决定：这份行业报告不配置它，也不向使用者索取凭据。
-> Step 8 的 Long / Short 一览与第七节的重点标的、目标价、评级是把上面这些材料写成结论的**推演练习**：本插件没有券商接口，不据它下单，也不会替你执行任何一笔。
+> 分册 `references/10-workflow.md` 里 Step 8 的 Long / Short 一览与第七节的重点标的、目标价、评级，是把上面这些材料写成结论的**推演练习**：本插件没有券商接口，不据它下单，也不会替你执行任何一笔。
+
+## 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-workflow.md` — Workflow
+
+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.
+

package/selected-skills/claude-for-financial-services-cn/vertical-plugins/china-finance/skills/china-sector-overview/references/10-workflow.md

@@ -0,0 +1,161 @@
+> 本文件相对上游 `d7585ca` 快照做过合规改写（取数与凭据口径），逐条记在快照根目录的 UPSTREAM.md；方法论、阈值与输出模板未改。
+
+# Workflow
+
+Part 1 of 1 for `china-sector-overview` — the nine steps of a sector overview, with the report structure
+See `SKILL.md` for what to read and when; this part is procedure, not routing.
+
+## Workflow
+
+### Step 1: Define Scope & Angle
+
+**Clarify:**
+- Sector / industry focus (e.g., 白酒, 半导体, 新能源汽车)
+- Angle (e.g., investment theme, competitive analysis, turnaround story)
+- Geographic scope (A-share only, or include HK-listed / US-listed Chinese)
+- Time horizon (cyclical analysis, secular trends, near-term trade)
+
+### Step 2: Market Size & Structure
+
+**Industry overview:**
+
+| Metric | Data | Source |
+|--------|------|--------|
+| Total market size | 市场规模 (亿元/亿元) | 国家统计局, 行业协会 |
+| Growth rate | 同比增速 / CAGR | Historical data |
+| Market share | CR5, CR10 concentration | Company filings |
+| Penetration rate | For new industries | Industry reports |
+| Export/import | 进出口数据 | 海关总署 |
+
+**A-share representation:**
+- Number of listed companies in sector
+- Total market cap (总市值 / 流通市值)
+- Average PE / PB multiples
+- Liquidity (average daily turnover)
+
+### Step 3: Competitive Landscape
+
+**Peer mapping:**
+
+Ask the host's retrieval path for the 板块成分股 list of the industry being covered, by its Chinese industry name, and take the constituents from what comes back.
+
+**For each major player, retrieve:** 最新价 / 市值 / 倍数, 收入与利润率的历史序列, and the business description — one brief per field family, same as-of date across the whole peer set.
+
+**Competitive analysis table:**
+
+| Company | Ticker | Market Cap (亿) | Revenue (亿) | YoY Growth | Gross Margin | Net Margin | PE (TTM) | Market Share |
+|---------|--------|----------------|-------------|------------|-------------|------------|----------|-------------|
+| | | | | | | | | |
+
+**Competitive positioning:**
+- Market share trends (gaining or losing)
+- Product positioning (premium, mid-tier, mass market)
+- Geographic footprint (national vs regional)
+- Distribution strength (渠道能力)
+- Brand equity (品牌力)
+
+### Step 4: Trading Multiples & Valuation
+
+**Sector multiples:**
+
+| Metric | Current | 1Y High | 1Y Low | 5Y Average | Historical High | Historical Low |
+|--------|---------|---------|--------|------------|----------------|----------------|
+| Average PE | | | | | | |
+| Average PB | | | | | | |
+| Average PS | | | | | | |
+| EV/EBITDA | | | | | | |
+
+**Multiple dispersion:**
+- Premium names (high multiple vs sector)
+- Value names (low multiple vs sector)
+- Historical range and where we are in cycle
+
+### Step 5: Policy Environment
+
+**China-specific policy analysis:**
+
+| Policy Area | Current Status | Impact |
+|-------------|---------------|--------|
+| 产业政策 | 支持/限制/中性 | Direct sector impact |
+| 环保政策 | 双碳目标 | Cost structure impact |
+| 监管政策 | 集采/反垄断 | Margin / market share impact |
+| 补贴政策 | 新能源/半导体补贴 | Competitiveness impact |
+| 货币政策 | 宽松/中性/紧缩 | Financing cost impact |
+
+**Key regulatory bodies:**
+- 发改委 (NDRC) — industrial policy, pricing
+- 工信部 (MIIT) — manufacturing, tech, telecom
+- 生态环境部 (MEE) — environmental compliance
+- 卫健委 (NHC) — healthcare, pharmaceuticals
+- 证监会 (CSRC) — capital markets
+- 央行 (PBoC) — monetary policy
+
+### Step 6: Key Drivers & Trends
+
+**Secular trends (3-5 year):**
+- Technology adoption (技术替代)
+- Consumption upgrade/downgrade (消费升级/降级)
+- Demographic shifts (人口结构)
+- Supply chain localization (供应链国产化)
+- Environmental transition (双碳/ESG)
+
+**Cyclical factors:**
+- Inventory cycles (库存周期)
+- Capacity utilization (产能利用率)
+- Pricing trends (价格趋势)
+- Demand momentum (需求 momentum)
+
+### Step 7: Investment Themes
+
+**Thematic angles:**
+
+1. **Policy-driven**: 国产替代, 新基建, 乡村振兴
+2. **Demand-driven**: 消费升级, 老龄化, 出海
+3. **Supply-driven**: 产能出清, 行业整合, 龙头集中
+4. **Technology-driven**: AI应用, 新能源, 生物医药创新
+
+**For each theme:**
+- Investment thesis
+- Key names to express the theme
+- Timeline and catalysts
+- Risks and headwinds
+
+### Step 8: Trading Ideas
+
+**Ideas shortlist (from sector overview):**
+
+| Idea | Ticker | Direction | Thesis | Catalyst | Risk |
+|------|--------|-----------|--------|----------|------|
+| | | Long / Short | | | |
+
+### Step 9: Report Structure
+
+**Standard A-share sector overview format:**
+
+```
+【XX证券】[行业] 深度报告：[标题]
+
+一、行业概述
+   市场规模、增速、发展阶段
+
+二、竞争格局
+   主要玩家、市场份额、竞争要素
+
+三、政策环境
+   监管框架、产业政策、影响分析
+
+四、财务分析
+   行业盈利能力、ROE、杠杆水平
+
+五、估值分析
+   当前 multiples vs 历史 vs 国际对标
+
+六、核心驱动因素
+   长期趋势、短期催化、周期位置
+
+七、投资建议
+   重点标的、目标价、评级
+
+八、风险提示
+   政策风险、需求风险、竞争风险
+```

package/selected-skills/financeskills/UPSTREAM.md

@@ -17,7 +17,7 @@
   `LICENSE` 的版权行是 **`Copyright (c) 2026 KOMVIA`**；`marketplace.json` 的 `publisher` 也是 `KOMVIA`，
   上游 `AGENTS.md:11` 自述 `**Creator**: KOMVIA`；而仓库 owner 与 `README.md:5` 的 "Built by" 都是
   **Ayotunde Oso（账号 `GAJETOso`）**。catalog 的 `owner` 用仓库账号 `GAJETOso`——设置卡片那条
-  上游链接是按 `https://github.com/${owner}/${repository}` 拼的（`capital-config/client.src.cjs:576`），
+  上游链接是按 `https://github.com/${owner}/${repository}` 拼的（`config/client.src.cjs:576`），
   换成品牌名就是死链。MIT 与 Apache-2.0 的差别在本仓有实际后果，见下面"许可义务"一节。
 - Imported content: 只带 `skills/` 这一棵树（48 颗，337 个文件 / 2.4 MB）与 `LICENSE` 原件，
   与所钉 commit 逐字节相同（除下面列出的 10 份）。**上游仓库根其余材料整个不复制进本仓**，

package/selected-skills/investment-skills/UPSTREAM.md

@@ -8,6 +8,7 @@
 - Removed from the snapshot: the upstream ignore rules — `.gitignore` at the snapshot root (`__pycache__/`, `*.pyc`), plus the nested ones under `.tbd/` and `viz/vendor/`. Vendored snapshots do not carry ignore rules into this repo (`docs/dev/selected-skills.md` §8.6: an inherited ignore pattern can silently hide files when the snapshot is re-imported). Nothing committed was hidden by them. Note that `viz/vendor/.gitignore` used to hide two artifacts upstream fetches on demand (`elk.bundled.js`, `elkjs-license.txt` via `fetch-elk.sh`); neither exists in this repo, and `viz/` is excluded from the published package anyway.
 - Local modifications: one sentence, on the router block. Upstream wrote "Use the bundled deterministic router when a shell is available" and four `python3 scripts/framework.py …` examples; under Capital the root role has no shell (§1.6), so that conditional left a dead end with nothing to fall back to. The sentence now states the two preconditions (a shell **and** a reachable skill directory) and names the fallback: skip the router and open the `references/` file for the chosen module directly, since the router only picks which file to read. No card, workflow, or analytical text was touched; `scripts/framework.py` itself is unmodified. Recorded here per `docs/dev/selected-skills.md` §8.6, and enforced by `test/selected-skills-content.test.mjs` (a file may mention `python3 scripts/` only if it also carries the no-shell fallback). This record and the Capital selected-skill catalog are maintained by Capital Generation.
 - Packaging: a Capital-owned `.npmignore` beside these files keeps only the runtime skill body and this record in the published npm package. Excluded: `images/` and `viz/` (2.3 MB of README artwork — the same four PNGs exist twice — plus the upstream visualization site), `.github/` (its CI), `.tbd/` and `docs/` (upstream roadmap/development notes), and `README*.md`. No skill body references any of them. Kept on purpose: `skills/buffett-investment-framework/scripts/framework.py` and `Makefile` — this skill's own prose names the deterministic router as a methodology entry point and carries the no-shell fallback, so shipping them as review material while never executing them (intake and activation only read documents) is the honest shape; see `docs/dev/selected-skills.md` §8.6 item 4. The complete snapshot stays committed here, so `github:` installs and provenance review are unaffected.
+- Visibility layering (2026-10-14, third allowed reason — `docs/dev/selected-skills.md` §8.6): the surface was re-laid out as an entry file plus per-part reference files, because the host prunes any tool result over 8,192 code points (head 4,096 + `[... tool result middle pruned ...]` + tail 1,024) and both `SKILL.md` (11,296) and all nine original `references/` files exceeded that. `references/01…08` are split at card boundaries into 18 files named by their card run (e.g. `01-decision-posture-D01-D04.md`); the three workflow sections and the output contract moved verbatim to `references/09-workflows.md`; `references/` went from 9 files to 22: the provenance paragraph moved to `references/10-method.md`, and `references/11-deterministic-router.md` took the upstream router paragraph with its four `python3 scripts/framework.py` examples; the entry keeps a one-line non-affiliation statement. Nothing was deleted or reworded: all 65 cards appear exactly once, the entry is 6,605 code points on the `skill` channel (7,825 if opened with `read`), the largest part renders to 7,629 through `read`, and the directory's `.md` total went 113,052 → 117,909 — the added lines are part headers and entry pointers. Sizes are judged on the **rendered** receipt, not the file: `read` prefixes every line with `N: ` and wraps it in `<path>`/`<content>` (7,302 characters over 95 lines renders to 7,894). Enforced by `test/selected-skills-content.test.mjs` ("分层条目" two tests: every part arrives complete through whichever channel loads it, named files exist, no orphan part, totals may only grow, filename card ranges match content); the entry no longer appears in the oversized ratchet baseline in `test/persona.test.mjs`.
 - Maintenance snapshot (checked 2026-10-08): latest commit 2026-07-22; no later commits observed through the review date (78 days). See [GitHub commit history](https://github.com/finterm-ai/investment-skills/commits/main/).
 - Runtime status: `experimental` / explicit experiment. The skill remains disabled until explicitly selected in Capital settings and is registered only in a Capital root Agent's own scope. Its capability tags and warning are maintained in `selected-skills/catalog.js`.
 - Review status: imported for user-directed evaluation; not endorsed by Warren Buffett, Berkshire Hathaway, or Capital Generation. Its US-centric framework must not be treated as A-share rules. Validate all financial claims against primary evidence.

package/selected-skills/investment-skills/skills/buffett-investment-framework/SKILL.md

@@ -17,17 +17,12 @@ into investment actions.
 4. Read only the reference modules containing those cards, or print single routed cards
    with `show --id`.
 5. Apply each card’s question, actions, output, and limits.
-6. Return supported, challenged, or unresolved findings using the output contract.
+6. Return supported, challenged, or unresolved findings using the output contract
+   ([workflows](references/09-workflows.md)).
 
-Use the bundled deterministic router when the host gives this role a shell **and** this skill's directory is reachable. Where either is missing — a role-split host that grants no shell, or an install without `scripts/` — skip the router and open the `references/` file for the chosen module directly, using the mapping in *Choose the Workflow* below. The router only decides which file to read; it holds no analysis of its own, so nothing is lost by reading the file.
-From the skill directory, run:
-
-```bash
-python3 scripts/framework.py route --intent financial-analysis --topic insurance
-python3 scripts/framework.py route --intent memo-review --topic acquisition
-python3 scripts/framework.py show --id C08
-python3 scripts/framework.py validate
-```
+The upstream deterministic router needs a shell, which this host's root role does not have: skip it
+and open the `references/` files named below (see [11-deterministic-router](references/11-deterministic-router.md)
+for what it would have done). It only decides which file to read; it holds no analysis of its own.
 
 ## Choose the Workflow
 
@@ -50,89 +45,37 @@ Before writing, count the final card set and make the reported count match the l
 IDs exactly. When replacing a routed card, state the substitution and its evidence
 trigger.
 
-| Module | Load when material evidence concerns | Cards | Reference |
+| Module | Load when material evidence concerns | Cards | Reference files (under `references/`) |
 | --- | --- | --- | --- |
-| Decision posture | competence, ownership, inversion, price, alternatives, concentration, active skill, or speculation | `D01`–`D09` | [Decision posture](references/01-decision-posture.md) |
-| Business economics | business model, moat, capital intensity, reinvestment, or structural change | `B01`–`B07` | [Business economics](references/02-business-economics.md) |
-| Management | conduct, operating execution, incentives, governance, controls, or succession | `M01`–`M08` | [Management and governance](references/03-management-governance.md) |
-| Financial reality | filings, owner cash, normalization, segments, capital returns, or obligations | `F01`–`F07` | [Financial reality](references/04-financial-reality.md) |
-| Valuation | value, method, normalized base, growth, sensitivity, or price discipline | `V01`–`V06` | [Valuation](references/05-valuation.md) |
-| Capital allocation | reserves, retention, payout, repurchase, issuance, or acquisitions | `C01`–`C09` | [Capital allocation](references/06-capital-allocation.md) |
-| Risk | permanent harm, forced action, leverage, contingent claims, inflation, exit, or monitoring | `R01`–`R07` | [Risk and monitoring](references/07-risk-monitoring.md) |
-| Specialized overlay | insurance, banking, consumer, infrastructure, technology, commodities, or special instruments | `S01`–`S12` | [Specialized overlays](references/08-specialized-overlays.md) |
+| Decision posture | competence, ownership, inversion, price, alternatives, concentration, active skill, or speculation | `D01`–`D09` | `01-decision-posture-D01-D04.md`、`01-decision-posture-D05-D09.md` |
+| Business economics | business model, moat, capital intensity, reinvestment, or structural change | `B01`–`B07` | `02-business-economics-B01-B03.md`、`02-business-economics-B04-B07.md` |
+| Management | conduct, operating execution, incentives, governance, controls, or succession | `M01`–`M08` | `03-management-governance-M01-M04.md`、`03-management-governance-M05-M08.md` |
+| Financial reality | filings, owner cash, normalization, segments, capital returns, or obligations | `F01`–`F07` | `04-financial-reality-F01-F03.md`、`04-financial-reality-F04-F07.md` |
+| Valuation | value, method, normalized base, growth, sensitivity, or price discipline | `V01`–`V06` | `05-valuation-V01-V03.md`、`05-valuation-V04-V06.md` |
+| Capital allocation | reserves, retention, payout, repurchase, issuance, or acquisitions | `C01`–`C09` | `06-capital-allocation-C01-C04.md`、`06-capital-allocation-C05-C09.md` |
+| Risk | permanent harm, forced action, leverage, contingent claims, inflation, exit, or monitoring | `R01`–`R07` | `07-risk-monitoring-R01-R03.md`、`07-risk-monitoring-R04-R07.md` |
+| Specialized overlay | insurance, banking, consumer, infrastructure, technology, commodities, or special instruments | `S01`–`S12` | `08-specialized-overlays-S01-S03.md`、`08-specialized-overlays-S04-S06.md`、`08-specialized-overlays-S07-S09.md`、`08-specialized-overlays-S10-S12.md` |
 
 Add a specialized overlay only when the supplied evidence triggers it.
 An industry label does not load every overlay.
 
-## Run Financial Analysis
-
-Require exact filings and periods, policies and notes, segment schedules, cash-flow and
-capital-expenditure data, and material financing and obligation disclosures.
-Treat market price as a separate input only when valuation is in scope.
-
-1. Apply `F01` and `F05` to inventory the package and reconcile reported results into
-   comparable segments without discarding genuine costs.
-2. Apply `F02` to bridge reported earnings to a range of owner earnings.
-   Add `F03` when maintenance, growth, restricted, or distributable capital must be
-   separated. Show every maintenance-capital, working-capital, compensation, and
-   recurring-cost judgment.
-3. Apply `F06`, and `B06` when prospective reinvestment matters, to separate historical
-   returns from the future reinvestment runway.
-4. Add `F07`, `C02`, `R02`, and `R03` as needed to inventory obligations and stress
-   financing, liquidity, collateral, and nonlinear claims.
-5. Add `F04` for material partial ownership and only the triggered `S01`–`S11` overlay
-   for industry-specific accounting or risk.
-
-Return a package inventory, reported-to-analytical bridge, normalized segment base,
-owner-earnings range, capital-return calculations, obligation ledger, assumptions,
-sensitivities, and blocked calculations.
-
-## Review an Investment Memo
-
-Require the complete memo and appendices, cited primary sources and models, decision
-question, horizon, business and management claims, valuation bridge, alternatives,
-risks, and invalidation conditions.
-
-1. Apply `D01` and `D03` to test estimability, separate facts, calculations, and
-   inference, and seek disconfirming evidence.
-   Add `D02` when ownership framing is material.
-2. Apply `B02` to test a claimed moat as a causal mechanism.
-   Add `B01` and only the relevant `B03`–`B07` cards when the memo’s claims require
-   them.
-3. Add only material `M01`–`M08` and `C01`–`C09` cards; use `C09` when a transaction is
-   central.
-4. Apply `V01`, `V05`, and `V06` to reconstruct value and expose sensitivities.
-   Add `V03` when the normalized base is material and `V04` when projected growth
-   contributes materially to value; use `D04` when price action is being treated as
-   business evidence.
-5. Apply `R01` and `R07` to trace owner harm and invalidation.
-   Add `R02` or `R03` only for financing or contingent paths actually present.
-
-Return one row per material claim: claimed consequence, evidence and source quality,
-applicable cards, supported/challenged/unresolved disposition, counterevidence or
-alternate mechanism, and evidence still needed.
-
-## Evaluate a Thesis
-
-Require explicit thesis components and horizon, primary evidence for the claimed
-business and management mechanisms, valuation inputs, financing and risk evidence,
-market price when price versus value is asked, and failure conditions.
-
-1. Apply `D02`, `D03`, and `R07` to rewrite the thesis as testable components while
-   preserving the author’s meaning and invalidation conditions.
-2. Apply `B01`, `B02`, `B06`, and `B07` as relevant to test business mechanisms,
-   incremental-return economics, and structural change.
-3. Add only the `M01`–`M08` and `C01`–`C09` cards needed by stated management or
-   allocation dependencies.
-4. Apply `V01`, `V03`, `V04`, `V05`, and `V06` as relevant to reconstruct value from
-   supplied evidence and keep quality, value, and price as separate judgments.
-5. Add `R01`, `R02`, `R03`, and a triggered `S01`–`S12` overlay to trace owner-harm,
-   financing, contingent, and specialized risks.
-
-Return a component map, evidence and counterevidence table, mechanism tests, valuation
-assumptions and sensitivities, owner-harm paths, invalidation indicators, missing
-evidence, and a separate disposition for each component.
-Do not aggregate component dispositions into an investment recommendation.
+## Load These Files
+
+Card definitions, workflows, and the output contract live in `references/`: the modules are
+listed in the table above, [`09-workflows.md`](references/09-workflows.md) holds the three card
+sequences with their required inputs and the output contract, and [`10-method.md`](references/10-method.md)
+the decomposition method. Open each with `read`, resolved against this skill's base directory.
+Parts are sized to arrive complete in one `read`; if a receipt shows
+`[... tool result middle pruned ...]`, re-read it with `offset` before concluding a card is
+absent, and never reconstruct a card from its ID or from a file you did not open.
+
+Loading this file is not reading the framework: the cards, the workflow steps, and the output
+contract exist only in the parts above. Say which parts you opened, name the ones you did not,
+and never report a card or a step you have not read in this session.
+
+## Source and Method
+
+The framework is not affiliated with or endorsed by Warren Buffett or Berkshire Hathaway.
 
 ## Preserve Evidence Boundaries
 
@@ -153,40 +96,6 @@ Do not aggregate component dispositions into an investment recommendation.
 - When a prerequisite is absent, name it, mark the affected branch unresolved, and stop
   that branch.
 
-## Use This Output Contract
-
-Every response must contain:
-
-1. **Question and scope:** task intent, horizon, entity, and exclusions.
-2. **Evidence receipt:** supplied primary evidence, periods, missing inputs, and source
-   limitations.
-3. **Card load:** five to 12 IDs and why each was selected.
-4. **Analytical work:** sourced bridges, calculations, mechanism tests, and
-   sensitivities.
-5. **Findings:** supported, challenged, or unresolved, one decision question at a time.
-6. **Counterevidence and alternatives:** strongest contrary account and competing
-   mechanism.
-7. **Limits and blocked branches:** missing evidence and uncertainty that affect the
-   result.
-8. **Monitoring and invalidation:** observations that would strengthen, weaken, revise,
-   or retire each material finding.
-
-End with an analytical summary, not a buy, sell, hold, entry-price, position-size, or
-trade instruction.
-
-## Source and Method
-
-The 65 cards are an editorial synthesis of published Buffett and Berkshire writings.
-Source material was decomposed into claims, definitions, tactics, examples, and
-references; recurring decision questions were inventoried; overlaps were reconciled by
-analytical consequence; and the result was organized into eight modules and three task
-workflows. The cards provide representative, not exhaustive, coverage of the source
-material. Each card includes one to three readable source notes, abbreviated
-corroboration citations reconciled against the wider published record and resolved in
-the [source key](references/00-source-key.md), and its own preserved limits.
-The framework is not affiliated with or endorsed by Warren Buffett or Berkshire
-Hathaway.
-
 <!-- This document follows common-doc-guidelines.md.
 See github.com/jlevy/practical-prose and review guidelines before editing.
 -->