diff --git a/README.md b/README.md
index 0d1e982..81af843 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 # Knowledge Vault
 
-个人长期知识库。它的定位是“矿山和档案馆”：保存长期知识源、正式文章、面向人的模型文档、历史讨论、资料来源和项目归档。
+个人长期知识库。它的定位是“矿山和档案馆”：保存长期知识源、正式文章、面向人的模型文档、历史讨论、资料来源、项目归档和知识加工能力的本地运行规则。
 
 本仓库不承担 Writing Workbench、CCPE System 或 Delivery Systems 的职责。
 
@@ -8,7 +8,7 @@
 
 | 层级 | 定位 | 主要内容 | 不做什么 |
 | --- | --- | --- | --- |
-| Knowledge Vault | 长期知识源与归档 | 日记、讨论归档、模型说明、文章、资料源、项目归档 | 不承载文章生产流水线，不承载 AI 资产工程 |
+| Knowledge Vault | 长期知识源与归档 | 日记、讨论归档、模型说明、文章、资料源、项目归档、知识加工能力运行规则 | 不承载文章生产流水线，不替代 CCPE 的 AI 资产工程 |
 | Writing Workbench | 写作工地 | 素材整理、提纲、正文、评审、润色、Metadata、发布 | 不做长期知识分类的唯一入口 |
 | CCPE System | 造锤子的车间 | Agent、Skill、Runtime、Model Card、Model Index | 不保存面向人阅读的完整知识库 |
 | Delivery Systems | 外部交付系统 | 客户或项目级 Agentic 产品 | 不和个人创作体系混放 |
@@ -29,6 +29,7 @@ knowledge-vault/
   work/
   indexes/
   templates/
+  skills/
 ```
 
 ## 核心原则
@@ -40,6 +41,7 @@ knowledge-vault/
 - `discussions/` 主要归档历史讨论、非工作台讨论和与 Agent 交流的过程记录。
 - `indexes/` 由 Codex 按需维护，不要求人工每新增文件都同步更新。
 - `templates/` 提供后续人工和 Codex 生成文档时使用的统一格式。
+- `skills/` 保存 Knowledge Vault 本地知识加工能力的运行规则、调用治理、上下文治理、模板和 runbook；不保存 CCPE canonical Skill/Agent/Runtime。
 
 ## 命名与层级规则
 
@@ -61,6 +63,13 @@ C:\Users\wangq\Documents\Codex\ccpe-system
 - `knowledge-vault/rules/...`：基模、衍生模型、版本说明、面向人的解释。
 - `ccpe-system/model-cards/...`：AI-Oriented Model Card。
 
+知识加工能力也采用双轨：
+
+- `knowledge-vault/skills/...`：本仓库如何调用、落盘、分段、交接和验收能力。
+- `ccpe-system/agents|skills|runtimes/...`：canonical Agent、Skill、Runtime 定义。
+
+如果 CCPE 提供的规则不足以真实调用 participant，Knowledge Vault 应暂停并记录阻塞状态，不模拟正式 Agent 输出。
+
 ## Codex 维护触发语
 
 可以用以下方式触发维护：
@@ -69,4 +78,5 @@ C:\Users\wangq\Documents\Codex\ccpe-system
 - “我新增了某模型，请更新模型索引和版本关系。”
 - “请按目录生成迁移清单，不要移动文件。”
 - “请执行这份迁移清单。”
-
+- “请按 skills 中的某个能力处理这份材料。”
+- “请为某个知识加工流程生成 invocation packet 或 continuation handoff。”
diff --git a/VAULT.md b/VAULT.md
index 049ca3d..44263ec 100644
--- a/VAULT.md
+++ b/VAULT.md
@@ -4,7 +4,7 @@
 
 ## 1. Vault 定位
 
-Knowledge Vault 是个人知识管理与写作工程体系中的长期层。它负责保存“值得长期留存、可被重新发现、可被重新加工”的材料。
+Knowledge Vault 是个人知识管理与写作工程体系中的长期层。它负责保存“值得长期留存、可被重新发现、可被重新加工”的材料，以及本仓库执行知识加工时需要遵守的本地运行规则。
 
 它不是：
 
@@ -25,6 +25,7 @@ Knowledge Vault 是个人知识管理与写作工程体系中的长期层。它
 | `work/` | 工作归档 | 内部项目、客户项目、敏感本地资料 |
 | `indexes/` | 人和 Codex 共用索引 | 文章、模型、提示词、来源、项目索引 |
 | `templates/` | 文档模板 | 模型文档、衍生模型、来源笔记、讨论归档、saying metadata |
+| `skills/` | 知识加工能力运行层 | 调用治理、上下文治理、能力 runbook、调用模板、Knowledge 侧能力规格 |
 
 ## 3. 层级与命名
 
@@ -103,7 +104,37 @@ prompts/
 
 其中 `agents/` 用于保存与个人 Agent 交流的过程；`creative/` 用于音乐、图片、视频等创意讨论；`technology/` 用于技术相关讨论。
 
-## 7. `sources/` 规则
+## 7. `skills/` 规则
+
+`skills/` 是 Knowledge Vault 的本地知识加工能力层。它保存“在本仓库中如何运行能力”的规则，而不是保存 CCPE canonical 资产。
+
+它可以包含：
+
+- 调用治理规则，例如 `invocation-policy.md`。
+- 上下文治理规则，例如 `context-management-policy.md`。
+- 面向具体知识加工能力的 runbook、context strategy、invocation contract。
+- invocation、prompt-to-send、skill-execution-record、thread handoff 等模板。
+- 本地脚本或代码型加工能力的运行说明。
+
+它不应包含：
+
+- CCPE System 中的 canonical Agent / Skill / Runtime 全文副本，除非 prompt-to-send 明确需要粘贴。
+- 某次具体任务的大量运行日志。
+- 某次具体任务的 source-map、topic-map、routing-log、topic docs 或 audit。
+- 文章生产流水线。
+
+具体任务的运行记录应放在对应工作目录，例如：
+
+```text
+discussions/viewpoint-development/{date}-{topic}/
+  invocations/
+  handoff/
+  audits/
+```
+
+公共层只保留可复用规则和模板。若 CCPE 规则不足以真实调用 participant，必须暂停并记录阻塞状态，不能模拟正式 Agent 输出。
+
+## 8. `sources/` 规则
 
 `sources/` 合并旧的 sources 和 notes 职责。它保存外部材料和对材料的初步处理。
 
@@ -121,7 +152,7 @@ sources/
 
 当来源材料被提炼为模型、文章或项目资产时，应在对应索引中建立回链，而不是复制多份。
 
-## 8. 索引维护
+## 9. 索引维护
 
 `indexes/` 由 Codex 按需维护。人工不需要每次新增文件都手动更新。
 
@@ -132,6 +163,7 @@ sources/
 - 从旧库导入一批材料。
 - 某个项目阶段完成，需要归档。
 - 需要从文章、讨论或来源材料中提炼模型关系。
+- 新增或调整公共知识加工能力。
 
 索引原则：
 
@@ -140,7 +172,13 @@ sources/
 - 对版本关系给出明确说明。
 - 对迁移中的旧目录保留过渡说明。
 
-## 9. 迁移规则
+`skills/` 的公共能力发现入口是：
+
+```text
+indexes/skill-index.md
+```
+
+## 10. 迁移规则
 
 迁移按文件夹进行，不做零散手工搬运。
 
diff --git a/indexes/skill-index.md b/indexes/skill-index.md
new file mode 100644
index 0000000..2507ec7
--- /dev/null
+++ b/indexes/skill-index.md
@@ -0,0 +1,34 @@
+# Skill Index
+
+本索引记录 Knowledge Vault 中的本地知识加工能力层。它不同于 CCPE System 的 Agent / Skill / Runtime 索引。
+
+## 维护原则
+
+- `skills/` 记录 Knowledge Vault 如何运行、调用、分段、交接和验收能力。
+- CCPE System 记录 canonical Agent、Skill、Runtime 和 Model Card。
+- 具体任务的运行记录不放在本索引，也不放在公共 `skills/` 根层。
+- 如果能力依赖 CCPE participant，必须记录对应 canonical 路径和 no-simulation 规则。
+
+## 公共规则
+
+| 规则 | 路径 | 状态 | 说明 |
+| --- | --- | --- | --- |
+| Invocation Policy | `skills/invocation-policy.md` | active | 规定真实调用、外部返回、本地 Skill 执行记录、规则不足即暂停 |
+| Context Management Policy | `skills/context-management-policy.md` | active | 规定长文档加工的主/子会话、worker thread、continuation handoff 和上下文预算 |
+
+## 能力列表
+
+| 能力 | 路径 | 类型 | 状态 | CCPE 对应 | 说明 |
+| --- | --- | --- | --- | --- | --- |
+| Viewpoint Discussion Distillation | `skills/knowledge-processing/viewpoint-discussion-distillation/` | knowledge-processing | draft | `ccpe-system/runtimes/hybrid/viewpoint-discussion-distillation.runtime.md` | 将长观点讨论稿整理为 source-map、topic-map、routing-log、topic docs、audit 和 downstream handoff |
+
+## 模板
+
+| 模板 | 路径 | 用途 |
+| --- | --- | --- |
+| Agent Invocation Packet | `skills/templates/agent-invocation-packet.template.md` | 记录 canonical participant 调用边界 |
+| Prompt To Send | `skills/templates/prompt-to-send.template.md` | 外部 participant 不能读取本地路径时使用 |
+| Skill Execution Record | `skills/templates/skill-execution-record.template.md` | 本地执行 CCPE Skill 或本地能力时记录输入、输出和验证 |
+| Thread Start Packet | `skills/templates/thread-start-packet.template.md` | 启动 worker thread 或子会话 |
+| Thread Return Packet | `skills/templates/thread-return-packet.template.md` | worker thread 返回结构化结果 |
+| Continuation Handoff | `skills/templates/continuation-handoff.template.md` | 到达确认点、上下文压力点或阻塞点时交接 |
diff --git a/skills/README.md b/skills/README.md
new file mode 100644
index 0000000..f25686e
--- /dev/null
+++ b/skills/README.md
@@ -0,0 +1,37 @@
+# Knowledge Vault Skills
+
+`skills/` is the Knowledge Vault capability layer for reusable knowledge-processing work.
+
+It records how this vault invokes, governs, logs, and verifies reusable processing capabilities. It does not replace CCPE System artifacts.
+
+## Boundary
+
+```text
+ccpe-system:
+  Defines canonical Agent, Skill, Runtime, Model Card, and invocation protocol.
+
+knowledge-vault/skills:
+  Defines local operating rules, context policy, invocation policy, templates, runbooks, and acceptance gates.
+
+specific work directory:
+  Stores source maps, topic maps, routing logs, topic documents, audits, handoffs, and run-specific invocation records.
+```
+
+## Directory Layout
+
+```text
+skills/
+  README.md
+  invocation-policy.md
+  context-management-policy.md
+  templates/
+  knowledge-processing/
+```
+
+## Principles
+
+- Do not store raw long-running task logs in the public capability layer.
+- Keep run-specific records inside the related `discussions/`, `sources/`, `rules/`, or `work/` item directory.
+- Reference CCPE canonical artifacts by path instead of copying their full content unless a prompt-to-send packet requires it.
+- When a participant cannot be truly invoked or faithfully executed, stop and record the blocked state.
+- Long source processing must be file-based and batch-based, not dependent on one chat context.
diff --git a/skills/context-management-policy.md b/skills/context-management-policy.md
new file mode 100644
index 0000000..236733b
--- /dev/null
+++ b/skills/context-management-policy.md
@@ -0,0 +1,113 @@
+# Knowledge Vault Context Management Policy
+
+## 1. Purpose
+
+Long discussion files can exceed a single model context and degrade judgment quality. Knowledge Vault workflows must process long sources through file-based ranges, worker threads, and continuation handoffs.
+
+## 2. Main Rule
+
+The main session must not load or reason over an entire long source document when the task can be split by source range.
+
+The main session is responsible for:
+
+```text
+- source registration
+- output directory creation
+- invocation packet creation
+- worker dispatch
+- returned-output collection
+- cross-range consistency checks
+- user confirmation gates
+```
+
+Worker sessions are responsible for:
+
+```text
+- one H1 round
+- one source block batch
+- one bounded participant task
+- one explicit output contract
+```
+
+## 3. Default Split Strategy
+
+Use this sequence:
+
+```text
+1. Split by Markdown H1 round.
+2. If a round is too large, split by H2 section.
+3. If a section is still too large, split by source block batch.
+4. Assign stable range ids such as R01, R04-S02, or R04-B001-B030.
+```
+
+## 4. Thread Strategy
+
+Use worker threads when a processing pass needs to read large source ranges or preserve participant focus.
+
+Each worker thread should receive a thread-start packet and return a thread-return packet.
+
+Run-specific packet paths:
+
+```text
+handoff/thread-start-packets/
+handoff/thread-return-packets/
+```
+
+Worker outputs must be written to files before the main session synthesizes them.
+
+## 5. Continuation Handoff
+
+Create a continuation handoff when any condition is met:
+
+```text
+- a major pass is complete
+- several large source ranges have been read
+- a participant boundary changes
+- the run is blocked waiting for external output
+- a user confirmation gate is reached
+- context pressure may affect judgment quality
+- the next session must continue without relying on chat history
+```
+
+Recommended path:
+
+```text
+handoff/continuation/{date}-{stage}.md
+```
+
+## 6. What The Main Session May Read
+
+The main session may read:
+
+```text
+- source-map
+- topic-map
+- routing-log indexes
+- worker return summaries
+- audit summaries
+- unresolved issue lists
+- bounded excerpts needed to verify a claim
+```
+
+The main session should avoid repeatedly loading:
+
+```text
+- full original source
+- all worker outputs at once
+- all topic documents at once
+- all external returned outputs at once
+```
+
+## 7. Quality Gate
+
+Before starting a large pass, the run must define:
+
+```text
+- input range
+- output path
+- expected record file
+- acceptance check
+- continuation point
+```
+
+If these are missing, pause and create the missing run-control files first.
diff --git a/skills/invocation-policy.md b/skills/invocation-policy.md
new file mode 100644
index 0000000..d7917ff
--- /dev/null
+++ b/skills/invocation-policy.md
@@ -0,0 +1,127 @@
+# Knowledge Vault Invocation Policy
+
+## 1. Purpose
+
+This policy defines how Knowledge Vault invokes reusable capabilities, CCPE participants, local scripts, and external agents.
+
+It is a vault-side operating rule. CCPE defines canonical participants; this file defines how this repository accepts or rejects participant outputs during real knowledge-processing work.
+
+## 2. Scope
+
+Use this policy when a Knowledge Vault workflow invokes:
+
+```text
+- CCPE Agent
+- CCPE Skill
+- CCPE Runtime node
+- native platform agent
+- external GPT / Gemini / Claude / manual participant
+- local script or code-based processor
+```
+
+## 3. Run-Specific Records
+
+Run-specific invocation records belong in the work item directory, not in `skills/`.
+
+Example:
+
+```text
+discussions/viewpoint-development/{date}-{topic}/
+  invocations/
+    {participant-id}/
+      agent-invocation-packet.md
+      prompt-to-send.md
+      returned-output.md
+      skill-execution-record.md
+      run-log.md
+```
+
+The public `skills/templates/` directory only stores templates.
+
+## 4. No-Simulation Rule
+
+The main session may:
+
+```text
+- create directories and templates
+- prepare invocation packets
+- prepare prompt-to-send files
+- execute local skills when the procedure is explicit
+- run scripts and record their inputs and outputs
+- collect real participant outputs
+- synthesize results that are backed by records
+- ask the user for decisions
+```
+
+The main session must not:
+
+```text
+- write a formal Agent output as if a canonical Agent produced it
+- write a Skill result without a skill-execution-record
+- treat a convenience summary as a participant report
+- accept an external participant result without source metadata
+- proceed when CCPE rules are insufficient to launch the participant safely
+```
+
+If a required participant cannot be truly invoked, mark the stage:
+
+```text
+blocked_waiting_for_participant_output
+```
+
+## 5. Acceptance Rule
+
+A participant output may be accepted only when at least one condition is true:
+
+```text
+- a completed participant startup packet returned a real output
+- a prompt-to-send file was executed externally and the returned output was saved
+- a local Skill execution record identifies procedure, inputs, outputs, and validation
+- a local script record identifies command, inputs, outputs, and validation
+- the user explicitly labels material as simulation-only and it is excluded from formal synthesis
+```
+
+## 6. Insufficient Rule Handling
+
+If CCPE provides an Agent, Skill, Runtime, or protocol that is not specific enough to run safely, Knowledge Vault must pause before formal processing.
+
+Record:
+
+```text
+- missing rule or unclear boundary
+- affected participant
+- blocked output files
+- proposed clarification needed
+- user decision required
+```
+
+## 7. External Participant Metadata
+
+Returned external outputs must record:
+
+```text
+- participant name
+- platform or tool
+- date
+- prompt-to-send path
+- source input range
+- returned output path
+- operator note, if manually pasted back
+```
+
+## 8. Local Script Or Code-Based Capability
+
+Some Knowledge Vault capabilities may be implemented as scripts rather than CCPE participants.
+
+The run record must include:
+
+```text
+- script path
+- command or entrypoint
+- input files
+- output files
+- validation checks
+- known limitations
+```
+
+Script output is not an Agent judgment. It must be labeled as deterministic or tool-assisted processing.
diff --git a/skills/knowledge-processing/viewpoint-discussion-distillation/README.md b/skills/knowledge-processing/viewpoint-discussion-distillation/README.md
new file mode 100644
index 0000000..0d83ff2
--- /dev/null
+++ b/skills/knowledge-processing/viewpoint-discussion-distillation/README.md
@@ -0,0 +1,38 @@
+# Viewpoint Discussion Distillation
+
+This Knowledge Vault capability organizes long viewpoint discussions into reusable, traceable viewpoint material packages.
+
+It is the vault-side operating layer for the CCPE `viewpoint-discussion-distillation` Runtime.
+
+## Use When
+
+Use this capability when a long diary or discussion file should be transformed into:
+
+```text
+- source-map
+- topic-map
+- material-routing-log
+- topic documents
+- coverage audit
+- downstream handoff packets
+```
+
+## Do Not Use For
+
+```text
+- direct article writing
+- automatic writing-workbench project creation
+- deleting or moving the original source
+- summary-only compression
+- formal Agent output without a real invocation record
+```
+
+## Required Public Rules
+
+Read before running:
+
+```text
+skills/invocation-policy.md
+skills/context-management-policy.md
+skills/knowledge-processing/viewpoint-discussion-distillation/runbook.md
+```
diff --git a/skills/knowledge-processing/viewpoint-discussion-distillation/capability-spec.md b/skills/knowledge-processing/viewpoint-discussion-distillation/capability-spec.md
new file mode 100644
index 0000000..e4b72df
--- /dev/null
+++ b/skills/knowledge-processing/viewpoint-discussion-distillation/capability-spec.md
@@ -0,0 +1,60 @@
+# Capability Spec: Viewpoint Discussion Distillation
+
+## 1. Purpose
+
+Convert a long viewpoint discussion into a durable Knowledge Vault material package without losing source traceability.
+
+## 2. Inputs
+
+```text
+- source document path
+- source type
+- known boundary rule
+- intended use
+- output workspace path
+- optional seed topics
+- optional forbidden merges
+- optional downstream intent
+```
+
+## 3. Outputs
+
+```text
+- README.md
+- 00-source-map.md
+- 01-topic-map.md
+- 02-material-routing-log.md
+- 03-run-notes.md
+- topics/
+- audits/
+- model-mining/
+- handoff/
+- invocations/
+```
+
+## 4. Operating Principle
+
+First preserve, then structure.
+
+The source material layer must remain separate from the structured viewpoint layer. Topic documents may reorganize ideas, but must keep source block ids and enough original material to support later reuse.
+
+## 5. Human Gates
+
+```text
+Gate 1: Confirm workspace path.
+Gate 2: Confirm source block convention.
+Gate 3: Confirm candidate topic-map.
+Gate 4: Confirm audit repair strategy.
+Gate 5: Confirm downstream routing.
+```
+
+## 6. Acceptance Criteria
+
+```text
+- every source block has a routing status
+- every formal participant output has a valid record
+- no topic document relies only on summary
+- low-confidence routing remains visible
+- source-disposable claims are blocked until coverage audit
+- downstream work is optional and user-confirmed
+```
diff --git a/skills/knowledge-processing/viewpoint-discussion-distillation/ccpe-runtime-alignment.md b/skills/knowledge-processing/viewpoint-discussion-distillation/ccpe-runtime-alignment.md
new file mode 100644
index 0000000..5b6971b
--- /dev/null
+++ b/skills/knowledge-processing/viewpoint-discussion-distillation/ccpe-runtime-alignment.md
@@ -0,0 +1,35 @@
+# CCPE Runtime Alignment
+
+## 1. Canonical CCPE References
+
+```text
+C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\viewpoint-discussion-distillation.runtime.md
+C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\agent-invocation-packet.protocol.md
+C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\topic-discovery-router.agent.md
+C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\lossless-coverage-auditor.agent.md
+C:\Users\wangq\Documents\Codex\ccpe-system\skills\workflow\conversation-segmentation.skill.md
+C:\Users\wangq\Documents\Codex\ccpe-system\skills\workflow\evidence-routing-and-topic-doc-builder.skill.md
+```
+
+## 2. Responsibility Split
+
+```text
+CCPE System:
+  Defines canonical behavior, roles, participant specs, and runtime protocol.
+
+Knowledge Vault:
+  Defines local workspace layout, context control, invocation records, run handoffs, and acceptance policy.
+
+Writing Workbench:
+  Receives a writing-intake packet only after user confirmation.
+```
+
+## 3. If CCPE Is Insufficient
+
+If a canonical artifact is missing, ambiguous, or not specific enough to run a participant, stop the current stage and record:
+
+```text
+blocked_waiting_for_participant_output
+```
+
+Do not fill the missing gap by writing a simulated Agent report.
diff --git a/skills/knowledge-processing/viewpoint-discussion-distillation/context-strategy.md b/skills/knowledge-processing/viewpoint-discussion-distillation/context-strategy.md
new file mode 100644
index 0000000..2e4eeaa
--- /dev/null
+++ b/skills/knowledge-processing/viewpoint-discussion-distillation/context-strategy.md
@@ -0,0 +1,53 @@
+# Context Strategy
+
+## 1. Default Strategy
+
+The orchestrator should not process the full source in one context.
+
+Use:
+
+```text
+main session -> source registration and orchestration
+worker thread -> bounded range processing
+file handoff -> durable cross-session state
+```
+
+## 2. Range Order
+
+```text
+1. H1 rounds: R01, R02, R03
+2. H2 sections when a round is too large
+3. source block batches when a section is too large
+```
+
+## 3. Worker Input
+
+Each worker gets:
+
+```text
+- thread-start packet
+- participant invocation packet
+- exact source range
+- output path
+- forbidden actions
+- return packet template
+```
+
+## 4. Worker Output
+
+Each worker writes:
+
+```text
+- participant output file
+- execution or returned-output record
+- thread-return packet
+- unresolved issue list, if needed
+```
+
+## 5. Main Session Reading Rule
+
+The main session reads worker summaries and indexes first. It reads source excerpts only for verification or repair.
+
+## 6. Continuation Rule
+
+Create a continuation handoff after each major pass or before any expected context pressure.
diff --git a/skills/knowledge-processing/viewpoint-discussion-distillation/invocation-contract.md b/skills/knowledge-processing/viewpoint-discussion-distillation/invocation-contract.md
new file mode 100644
index 0000000..78837c8
--- /dev/null
+++ b/skills/knowledge-processing/viewpoint-discussion-distillation/invocation-contract.md
@@ -0,0 +1,65 @@
+# Invocation Contract
+
+## 1. Minimum Runtime Input
+
+```yaml
+runtime_id: viewpoint-discussion-distillation
+source_document_path:
+source_type:
+round_boundary_rule:
+intended_use: viewpoint-development
+output_workspace_path:
+lossless_requirement: true
+allow_topic_overlap: true
+writing_handoff_required: optional
+model_mining_required: optional
+no_simulation_requirement: true
+human_confirmation_required_before:
+  - final_topic_map
+  - source_disposable_claim
+  - writing_workbench_handoff
+  - downstream_task_routing
+```
+
+## 2. Run Directory Contract
+
+```text
+{workspace}/
+  README.md
+  00-source-map.md
+  01-topic-map.md
+  02-material-routing-log.md
+  03-run-notes.md
+  topics/
+  audits/
+  model-mining/
+  handoff/
+  invocations/
+```
+
+## 3. Invocation Directory Contract
+
+```text
+invocations/
+  conversation-segmentation/
+  topic-discovery-router/
+  evidence-routing-and-topic-doc-builder/
+  lossless-coverage-auditor/
+```
+
+Subdirectories may be split by range:
+
+```text
+conversation-segmentation/R01/
+conversation-segmentation/R02/
+```
+
+## 4. Blocked State
+
+Use this state when the run cannot accept a participant output:
+
+```text
+blocked_waiting_for_participant_output
+```
+
+Record the reason in `03-run-notes.md` or the relevant invocation directory.
diff --git a/skills/knowledge-processing/viewpoint-discussion-distillation/participant-registry.md b/skills/knowledge-processing/viewpoint-discussion-distillation/participant-registry.md
new file mode 100644
index 0000000..7607445
--- /dev/null
+++ b/skills/knowledge-processing/viewpoint-discussion-distillation/participant-registry.md
@@ -0,0 +1,35 @@
+# Participant Registry
+
+## conversation-segmentation
+
+- participant_type: ccpe_skill
+- canonical_artifact_path: `C:\Users\wangq\Documents\Codex\ccpe-system\skills\workflow\conversation-segmentation.skill.md`
+- default_invocation_mode: local_skill_execution
+- required_record: `skill-execution-record.md`
+- output_kind: source block index
+
+## topic-discovery-router
+
+- participant_type: ccpe_agent
+- canonical_artifact_path: `C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\topic-discovery-router.agent.md`
+- default_invocation_mode: prompt_path_reference or full_prompt_paste
+- required_record: `agent-invocation-packet.md`
+- external_record_when_needed: `prompt-to-send.md` plus returned output
+- output_kind: candidate topic map
+
+## evidence-routing-and-topic-doc-builder
+
+- participant_type: ccpe_skill
+- canonical_artifact_path: `C:\Users\wangq\Documents\Codex\ccpe-system\skills\workflow\evidence-routing-and-topic-doc-builder.skill.md`
+- default_invocation_mode: local_skill_execution
+- required_record: `skill-execution-record.md`
+- output_kind: routing log and topic document draft
+
+## lossless-coverage-auditor
+
+- participant_type: ccpe_agent
+- canonical_artifact_path: `C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\lossless-coverage-auditor.agent.md`
+- default_invocation_mode: prompt_path_reference or full_prompt_paste
+- required_record: `agent-invocation-packet.md`
+- external_record_when_needed: `prompt-to-send.md` plus returned output
+- output_kind: coverage audit and distortion risk log
diff --git a/skills/knowledge-processing/viewpoint-discussion-distillation/runbook.md b/skills/knowledge-processing/viewpoint-discussion-distillation/runbook.md
new file mode 100644
index 0000000..756431a
--- /dev/null
+++ b/skills/knowledge-processing/viewpoint-discussion-distillation/runbook.md
@@ -0,0 +1,79 @@
+# Runbook: Viewpoint Discussion Distillation
+
+## 1. Before Creating A Work Directory
+
+```text
+1. Read Knowledge Vault README and VAULT rules.
+2. Read this capability folder.
+3. Read CCPE runtime handoff and invocation protocol.
+4. Confirm target work directory with the user.
+5. Confirm whether the first pass stops after source registration or proceeds to segmentation.
+```
+
+## 2. First Pass
+
+```text
+1. Create the confirmed work directory.
+2. Create required subdirectories.
+3. Write README.md.
+4. Write 00-source-map.md with source metadata and round boundaries.
+5. Write 03-run-notes.md with decisions and gates.
+6. Create invocation records for the first participant.
+7. Stop at the agreed confirmation point.
+```
+
+## 3. Segmentation Pass
+
+```text
+1. Create worker thread-start packets by source range.
+2. Execute or dispatch conversation-segmentation.
+3. Write skill-execution-record.md for local execution.
+4. Collect source block indexes and worker return packets.
+5. Create a continuation handoff before topic discovery.
+```
+
+## 4. Topic Discovery Pass
+
+```text
+1. Prepare topic-discovery-router invocation packet.
+2. Prepare prompt-to-send.md if the participant is external.
+3. Stop if real invocation is unavailable.
+4. Save returned output with metadata.
+5. Draft 01-topic-map.md from accepted returned output.
+6. Pause for user confirmation.
+```
+
+## 5. Routing And Topic Docs
+
+```text
+1. Confirm topic-map.
+2. Execute evidence-routing-and-topic-doc-builder by range or topic group.
+3. Write 02-material-routing-log.md.
+4. Generate topic docs with source material layer and source index.
+5. Do not declare completion until coverage audit is accepted.
+```
+
+## 6. Audit
+
+```text
+1. Prepare lossless-coverage-auditor invocation packet.
+2. Save real returned output.
+3. Write audits/coverage-audit.md and audits/distortion-risk-log.md.
+4. Repair missing or distorted routing.
+5. Ask user before any source-disposable claim.
+```
+
+## 7. Downstream Handoff
+
+Create downstream packets only after user confirmation.
+
+Possible downstream tracks:
+
+```text
+- writing-workbench
+- CCPE model or participant work
+- engineering project
+- scale or rubric extraction
+- todo extraction
+- continued research
+```
diff --git a/skills/templates/agent-invocation-packet.template.md b/skills/templates/agent-invocation-packet.template.md
new file mode 100644
index 0000000..f9a47a8
--- /dev/null
+++ b/skills/templates/agent-invocation-packet.template.md
@@ -0,0 +1,44 @@
+# Agent Invocation Packet: {participant_id}
+
+## 1. Invocation Identity
+
+- project_id:
+- workflow:
+- stage:
+- run_id:
+- participant_id:
+- target_participant_name:
+- participant_type:
+- canonical_artifact_path:
+- canonical_artifact_version:
+- invocation_mode:
+- packet_type:
+
+## 2. Canonical Artifact Handling
+
+- should_paste_full_prompt_or_spec:
+- prompt_to_send_path:
+- role_integrity_requirement:
+- allowed_wrapper_instructions:
+- forbidden_role_changes:
+- no_simulation_requirement:
+
+## 3. Current Task
+
+## 4. Input Files
+
+## 5. Context Files
+
+## 6. Embedded Inputs
+
+## 7. Output Contract
+
+## 8. Continuity Policy
+
+## 9. Session Logging
+
+## 10. Forbidden Actions
+
+## 11. Return Path
+
+## 12. Runtime Acceptance Rule
diff --git a/skills/templates/continuation-handoff.template.md b/skills/templates/continuation-handoff.template.md
new file mode 100644
index 0000000..f4014ba
--- /dev/null
+++ b/skills/templates/continuation-handoff.template.md
@@ -0,0 +1,21 @@
+# Continuation Handoff: {stage}
+
+## 1. Current State
+
+## 2. Completed Work
+
+## 3. Files Created Or Updated
+
+## 4. Decisions Already Settled
+
+## 5. Do Not Repeat
+
+## 6. Blockers Or Waiting Points
+
+## 7. Next Actions
+
+## 8. Context Needed For Next Session
+
+## 9. Source Ranges Already Processed
+
+## 10. Source Ranges Not Yet Processed
diff --git a/skills/templates/prompt-to-send.template.md b/skills/templates/prompt-to-send.template.md
new file mode 100644
index 0000000..14f4a17
--- /dev/null
+++ b/skills/templates/prompt-to-send.template.md
@@ -0,0 +1,23 @@
+# Prompt To Send: {participant_id}
+
+## 1. Canonical Agent Prompt Or Spec
+
+Paste the canonical prompt or spec here when the participant cannot read the local artifact path.
+
+## 2. Runtime Wrapper
+
+You are being invoked for one stage of a larger Knowledge Vault workflow. Preserve your canonical role and follow the task below.
+
+## 3. Current Task
+
+## 4. Project Context
+
+## 5. Input Files Or Embedded Inputs
+
+## 6. Context Pack
+
+## 7. Output Requirements
+
+## 8. Session Continuity Instructions
+
+## 9. Return Instructions
diff --git a/skills/templates/skill-execution-record.template.md b/skills/templates/skill-execution-record.template.md
new file mode 100644
index 0000000..57c081d
--- /dev/null
+++ b/skills/templates/skill-execution-record.template.md
@@ -0,0 +1,24 @@
+# Skill Execution Record: {skill_id}
+
+## 1. Skill Identity
+
+- skill_id:
+- canonical_skill_path:
+- skill_version:
+- execution_mode: local_skill_execution
+
+## 2. Task Input
+
+## 3. Files Read
+
+## 4. Files Written
+
+## 5. Procedure Steps Completed
+
+## 6. Validation Checks
+
+## 7. Skipped Or Failed Steps
+
+## 8. Output Summary
+
+## 9. Return Path
diff --git a/skills/templates/thread-return-packet.template.md b/skills/templates/thread-return-packet.template.md
new file mode 100644
index 0000000..6579dcf
--- /dev/null
+++ b/skills/templates/thread-return-packet.template.md
@@ -0,0 +1,24 @@
+# Thread Return Packet: {range_or_stage_id}
+
+## 1. Identity
+
+- parent_workflow:
+- run_id:
+- worker_id:
+- stage:
+- source_range:
+- participant:
+
+## 2. Files Read
+
+## 3. Files Written
+
+## 4. Completed Work
+
+## 5. Unresolved Issues
+
+## 6. Validation Checks
+
+## 7. Context Or Quality Risks
+
+## 8. Recommended Next Step
diff --git a/skills/templates/thread-start-packet.template.md b/skills/templates/thread-start-packet.template.md
new file mode 100644
index 0000000..df40c02
--- /dev/null
+++ b/skills/templates/thread-start-packet.template.md
@@ -0,0 +1,27 @@
+# Thread Start Packet: {range_or_stage_id}
+
+## 1. Identity
+
+- parent_workflow:
+- run_id:
+- worker_id:
+- stage:
+- source_range:
+- assigned_participant:
+- invocation_record_path:
+
+## 2. Objective
+
+## 3. Inputs
+
+## 4. Files To Read
+
+## 5. Files To Write
+
+## 6. Output Contract
+
+## 7. Context Limits
+
+## 8. Forbidden Actions
+
+## 9. Return Instructions