@pigcloud/skills 1.0.3 → 1.0.5

package/skills/references/skill-boundary-template.md

@@ -1,38 +1,71 @@
-# Skill 边界模板
+# Skill Boundary Template
 
-这是一份给基础 skill 复用的短模板。正文只保留可执行边界，不写长背景。
+Use this template for simple routing, capture, or handoff skills where the body should stay very small. If the skill needs Quick Start, Inputs / Outputs, or Gotchas, it should probably use the enhanced template instead.
 
-## 默认结构
+## Copyable SKILL.md skeleton
+
+```markdown
+---
+name: example-skill
+description: What the skill does and when to use it, written as one clear sentence.
+lifecycle_stage: [routing|capture|scaffold]
+rule_profile: [router|capture|scaffold]
+dependencies:
+  - [only hard prerequisites]
+triggers:
+  - [exact phrases or intent keywords]
+inputs:
+  - [artifacts or facts the skill consumes]
+outputs:
+  - [artifacts the skill must produce]
+workflow:
+  - [step 1]
+  - [step 2]
+  - [step 3]
+gates:
+  - [objective stop condition]
+refs:
+  - [smallest needed reference file]
+---
+
+# Example Skill
 
-```text
 ## Purpose
-一句话说明这个 skill 只负责什么。
+
+Describe the skill in one sentence. Keep it narrow.
 
 ## Suitable / Unsuitable
-- Suitable: 该 skill 该接的输入类型
-- Unsuitable: 该 skill 不该碰的工作
+
+- Suitable: [what this skill should handle]
+- Unsuitable: [what this skill should not handle]
 
 ## Workflow
-1. 识别输入。
-2. 执行本阶段工作。
-3. 产出本阶段工件。
-4. 交接到下一 skill。
+
+1. Identify the request type and boundary.
+2. Do the one bounded step.
+3. Produce the handoff artifact or stop.
 
 ## Replay Signals
-- Input signal: 什么输入会触发这个 skill。
-- Output to verify: 需要检查什么产物。
-- Stop signal: 什么行为说明越界了。
-- Handoff signal: 什么时候交给下一 skill。
+
+- Input signal: [what should trigger this skill]
+- Output to verify: [what a correct output should include]
+- Stop signal: [what means the skill has gone too far]
+- Handoff signal: [when to pass control onward]
 
 ## Stop Rules
-- 停在本阶段。
-- 不做下一阶段的工作。
-- 不跳过规则加载。
+
+- Stop after the bounded step is complete.
+- Do not expand into adjacent skills.
+- Do not add long background or policy details.
+
+## References
+
+- [skill-authoring-standard.md](skill-authoring-standard.md)
+- [skill-enhanced-template.md](skill-enhanced-template.md)
 ```
 
-## 使用原则
+## When to choose the short template
 
-- `Replay Signals` 只写可验证的信号。
-- `Stop Rules` 只写硬边界。
-- 两者都要短，不要写成说明文。
-- 复杂 skill 需要升级到 [`skill-enhanced-template.md`](skill-enhanced-template.md)。
+- Use it for routing-only, capture-only, or single-boundary skills.
+- Keep replay signals and stop rules concise.
+- Move any detailed guidance into `references/` only if it is truly needed.

package/skills/references/skill-enhanced-template.md

@@ -1,53 +1,103 @@
-# Skill 增强模板
+# Skill Enhanced Template
 
-这是一份给复杂 skill 复用的增强模板。它在短边界模板之上补充快速启动、输入输出和常见坑。
+Use this template for complex skills that need a clear boundary, explicit replay signals, and a small amount of reusable structure. Keep the final skill body short; move long explanations into `references/`.
 
-## 默认结构
+## Copyable SKILL.md skeleton
+
+```markdown
+---
+name: example-skill
+description: What the skill does and when to use it, written as one clear sentence.
+lifecycle_stage: [routing|refinement|analysis|implementation|testing|capture|scaffold]
+rule_profile: [router|refinement|analysis|implementation|testing|capture|api|scaffold|security|performance|modeling|code]
+dependencies:
+  - [only hard prerequisites]
+triggers:
+  - [exact phrases or intent keywords]
+inputs:
+  - [artifacts or facts the skill consumes]
+outputs:
+  - [artifacts the skill must produce]
+workflow:
+  - [step 1]
+  - [step 2]
+  - [step 3]
+gates:
+  - [objective stop condition]
+refs:
+  - [smallest needed reference file]
+---
+
+# Example Skill
 
-```text
 ## Purpose
-一句话说明这个 skill 只负责什么。
+
+Describe the skill in one sentence. State the outcome, not the implementation.
 
 ## Suitable / Unsuitable
-- Suitable: 该 skill 该接的输入类型
-- Unsuitable: 该 skill 不该碰的工作
+
+- Suitable: [what this skill should handle]
+- Unsuitable: [what this skill should not handle]
 
 ## Quick Start
-- 一句话说明怎么进入这个 skill。
-- 一句话说明第一步看什么。
+
+- State the first action the model should take.
+- State the first artifact it should inspect or produce.
+- State the handoff point if another skill should continue.
 
 ## Inputs / Outputs
-- Inputs: 这个 skill 需要什么输入。
-- Outputs: 这个 skill 要交付什么产物。
+
+- Inputs:
+  - [input 1]
+  - [input 2]
+- Outputs:
+  - [output 1]
+  - [output 2]
 
 ## Workflow
-1. 识别输入。
-2. 执行本阶段工作。
-3. 产出本阶段工件。
-4. 交接到下一 skill。
+
+1. Identify the request type and the boundary.
+2. Gather only the facts needed for this step.
+3. Produce the step-specific artifact.
+4. Hand off or stop when the boundary is reached.
 
 ## Replay Signals
-- Input signal: 什么输入会触发这个 skill。
-- Output to verify: 需要检查什么产物。
-- Stop signal: 什么行为说明越界了。
-- Handoff signal: 什么时候交给下一 skill。
+
+- Input signal: [what should trigger this skill]
+- Output to verify: [what a correct output should include]
+- Stop signal: [what means the skill has gone too far]
+- Handoff signal: [when to pass control onward]
 
 ## Gotchas
-- 该 skill 最容易犯的 2-4 个错误。
+
+- [common failure mode 1]
+- [common failure mode 2]
+- [common failure mode 3]
 
 ## Stop Rules
-- 停在本阶段。
-- 不做下一阶段的工作。
-- 不跳过规则加载。
+
+- Stop when the step-specific artifact is complete.
+- Do not cross into the next skill's work.
+- Do not add unrelated context or policy details.
 
 ## References
-- 该 skill 依赖的最小 references。
+
+- [skill-authoring-standard.md](skill-authoring-standard.md)
+- [skill-boundary-template.md](skill-boundary-template.md)
+- [rule-loading-map.md](rule-loading-map.md)
 ```
 
-## 使用原则
+## How to use this template
+
+- Start with the `description` field. It is the primary trigger.
+- Keep `dependencies` for hard prerequisites only.
+- Put exact trigger phrases in `triggers`.
+- Use `workflow` for the minimal reliable procedure.
+- Put hard stop conditions in `gates` and `Stop Rules`.
+- Keep detailed notes, examples, and variant-specific guidance in `references/`.
+
+## When to choose the enhanced template
 
-- 增强模板只给复杂 skill。
-- `Quick Start` 先帮模型快速进入任务。
-- `Inputs / Outputs` 让产出更稳定。
-- `Gotchas` 只写最常见、最容易越界的点。
-- `References` 只挂最小必要文件，不要堆背景。
+- Use it for skills with multiple steps, strict boundaries, or meaningful handoff behavior.
+- Use the short template in `skill-boundary-template.md` for simpler routing or capture tasks.
+- Prefer the smallest possible reference set that still keeps the skill reliable.

package/skills/references/skill-reference-matrix.md

@@ -1,25 +1,25 @@
-# Skill Reference Matrix
-
-## Governance Context
-
-- Skills are the execution layer.
-- Rules are the constraint layer.
-- Workflow decides routing before execution.
-- For a broader system view, see [docs/agent-governance-overview.md](../../docs/agent-governance-overview.md).
-
-## Borrowed Patterns
+# Skill Reference Matrix
+
+## Governance Context
+
+- Skills are the execution layer.
+- Rules are the constraint layer.
+- Workflow decides routing before execution.
+- For a broader system view, see [docs/agent-governance-overview.md](../../docs/agent-governance-overview.md).
+
+## Borrowed Patterns
 
 | Source | Best Practice | Applies To |
 |---|---|---|
-| GitHub Spec Kit | Define before build | `spec-refinement` |
-| AWS Kiro EARS | Structured requirement writing | `spec-refinement` |
-| RIPER | Research / Innovate / Plan / Execute / Review | `spec-refinement` / routing context |
+| GitHub Spec Kit | Define before build | `spec` |
+| AWS Kiro EARS | Structured requirement writing | `spec` |
+| RIPER | Research / Innovate / Plan / Execute / Review | `spec` / routing context |
 | Claude Code | Short, dense prompts | all skills |
 | open-code-review | Deterministic review plus agent review | `code-review` |
 | Skill Reviewer | Rubric-based review gate | `code-review` / `performance-check` / `security-review` |
 | Short boundary template | One screen for Purpose / Workflow / Replay Signals / Stop Rules | low-complexity skills |
-| Enhanced template | Add Quick Start / Inputs / Outputs / Gotchas / References | `spec-refinement` / `technical-design` / `feature-build` / `code-review` / `security-review` / `performance-check` |
-| Negative replay | Use counterexamples to verify stop boundaries | `spec-refinement` / `technical-design` / `feature-build` / `test-design` |
+| Enhanced template | Add Quick Start / Inputs / Outputs / Gotchas / References | `spec` / `technical-design` / `feature-build` / `code-review` / `security-review` / `performance-check` |
+| Negative replay | Use counterexamples to verify stop boundaries | `spec` / `technical-design` / `feature-build` / `test-design` |
 | Engineering delivery method | Decide complexity first, then split and implement inside `feature-build` | `feature-build` / `test-design` / `code-review` |
 | Engineering delivery template | One-page task card with facts, complexity, tasks, self-test, and validation | `feature-build` / `test-design` |
 
@@ -34,14 +34,14 @@
 
 ## Applicable Skills
 
-- `product-intake`: turn business intent into a PRD-ready brief
-- `spec-refinement`: turn approved requirements into an executable spec
+- `spec`: turn product input, current facts, and implementation evidence into an executable spec
 - `technical-design`: turn complex changes into boundaries, dependencies, and rollback
 - `feature-build`: turn the confirmed spec into code
 - `test-design`: turn implementation results into a validation plan
-- `knowledge-capture`: turn product and engineering facts into requirements knowledge, realtime code facts, CodeWiki entries, and enterprise knowledge
+- `knowledge-capture`: turn product and engineering facts into requirements knowledge, realtime code facts, CodeWiki entries, enterprise knowledge, and persisted knowledge-base packs
 - `api-docs`: turn confirmed interfaces into docs
 - `domain-modeling`: turn domain language into boundaries
+- `extract-business-facts`: turn code-backed evidence into code facts, business facts, CodeWiki deltas, and file targets
 - `workflow-router`: route the stage
 - `code-review`: output generic review findings
 - `security-review`: output security findings
@@ -49,8 +49,8 @@
 
 ## Template Selection
 
-- Short template: `workflow-router`, `product-intake`, `knowledge-capture`, `api-docs`, `test-design`, `domain-modeling`, `project-bootstrap`, `environment-deploy`
-- Enhanced template: `spec-refinement`, `technical-design`, `feature-build`, `code-review`, `security-review`, `performance-check`
+- Short template: `workflow-router`, `knowledge-capture`, `api-docs`, `test-design`, `domain-modeling`, `project-bootstrap`, `environment-deploy`
+- Enhanced template: `spec`, `technical-design`, `feature-build`, `code-review`, `security-review`, `performance-check`, `extract-business-facts`
 
 ## Rules Loading
 
@@ -58,3 +58,4 @@
 - Use `skills/references/rule-loading-map.md` to decide which bundle to load.
 - Load the smallest bundle that covers the task.
 - Skills should reference at least one `rules` bundle when the task touches code.
+

package/skills/{spec-refinement → spec}/SKILL.md

@@ -1,16 +1,18 @@
 ---
-name: spec-refinement
-description: 通过对齐产品意图、项目事实、原型、实现事实和知识库证据，将已批准的需求细化为可执行规格，适用于仍存在验收缺口、约束或实现输入时
+name: spec
+description: Turn PRDs, prototypes, current project facts, implementation facts, and knowledge-base evidence into an executable engineering spec, task breakdown, and confirmation package; use when requirements must be clarified and aligned before design or implementation.
 lifecycle_stage: refinement
 rule_profile: refinement
 dependencies:
-  - product-intake
+  - workflow-router
 triggers:
+  - spec
   - requirement clarification
   - acceptance gap
-  - impact analysis
   - engineering spec
-  - open question
+  - task breakdown
+  - execution direction
+  - confirmation package
 inputs:
   - approved product brief
   - current project facts
@@ -27,17 +29,17 @@ outputs:
   - implementation inputs
   - alignment notes
   - task breakdown plan
+  - conflict map
   - confirmation package
 workflow:
   - verify the product brief is approved
   - compare the brief with current project facts, prototype notes, implementation facts, and knowledge snippets
-  - clarify boundaries, assumptions, and acceptance gaps
-  - identify conflicts between intent and current facts
+  - clarify boundaries, assumptions, acceptance gaps, and fact conflicts
   - decide the task execution direction before splitting tasks
   - extract a task breakdown plan for user confirmation
   - define implementation-facing constraints and verification inputs
   - assemble a confirmation package for user sign-off
-  - hand off to technical-design or feature-build only after confirmation
+  - hand off to `technical-design` or `feature-build` only after confirmation
 gates:
   - stop at spec clarity
   - do not restart PRD writing
@@ -55,16 +57,16 @@ refs:
   - rules/index.md
 ---
 
-# Spec Refinement
+# Spec
 
 ## Purpose
 
-Turn approved product input into an executable spec for engineering. This skill ends when the scope is clear enough for design or implementation.
+Turn product input, current project facts, and implementation evidence into an executable engineering spec.
 
 ## Suitable / Unsuitable
 
-- Suitable: requirement clarification, boundary checks, acceptance gaps, impact analysis, project-fact alignment, prototype alignment, implementation-fact alignment
-- Unsuitable: redoing the PRD, writing code, selecting rule bundles, skipping the rules bundle
+- Suitable: requirement clarification, boundary checks, acceptance gaps, impact analysis, project-fact alignment, prototype alignment, implementation-fact alignment, task breakdown, user confirmation
+- Unsuitable: redoing the PRD, writing code, selecting rule bundles, skipping the rules bundle, starting implementation before confirmation
 
 ## Quick Start
 
@@ -73,7 +75,7 @@ Turn approved product input into an executable spec for engineering. This skill
 - Decide the task execution direction before extracting the task breakdown plan.
 - Extract the task breakdown plan so feature-build can break the work into small tasks.
 - Convert the result into an executable spec that AI can follow without re-interpreting the PRD.
-  - Package the spec, task plan, and acceptance criteria into a confirmation package before execution starts.
+- Package the spec, task plan, and acceptance criteria into a confirmation package before execution starts.
 - If scope is still unstable, stop and keep the output at spec clarity.
 
 ## Inputs / Outputs
@@ -138,6 +140,9 @@ Turn approved product input into an executable spec for engineering. This skill
 ## References
 
 - `skills/references/requirements-separation-map.md`
+- `skills/references/project-requirement-alignment.md`
+- `skills/references/engineering-delivery-method.md`
+- `skills/references/engineering-delivery-template.md`
 - `skills/references/rule-loading-map.md`
-- `skills/references/flow-test-cases.md`
 - `rules/index.md`
+

package/skills/technical-design/SKILL.md

@@ -1,10 +1,10 @@
 ---
 name: technical-design
-description: 当模块、接口或依赖仍需决策时，在稳定规格基础上梳理架构与实现边界
+description: 当模块、接口或依赖仍需决策时，在稳定规格基础上梳理架构与实现边界
 lifecycle_stage: design
 rule_profile: analysis
 dependencies:
-  - spec-refinement
+  - spec
 triggers:
   - architecture decision
   - module split
@@ -54,7 +54,7 @@ Turn a stable spec into concrete architecture and implementation boundaries.
 - Start from the stable spec and isolate the decisions that affect boundaries or dependencies.
 - Load the smallest rules bundle that matches the current task context.
 - Turn design choices into implementation constraints, not code.
-- If the spec is still unstable, stop and return to `spec-refinement`.
+- If the spec is still unstable, stop and return to `spec`.
 
 ## Inputs / Outputs
 
@@ -72,7 +72,7 @@ Turn a stable spec into concrete architecture and implementation boundaries.
 
 1. Confirm the spec is stable enough for design work.
 2. Define boundaries, dependencies, and interfaces.
-3. Route scope gaps back to `spec-refinement` instead of forcing design decisions.
+3. Route scope gaps back to `spec` instead of forcing design decisions.
 4. Map design decisions to the rules bundle.
 5. Produce implementation constraints for `feature-build`.
 

package/pig-cloud-skills-commands/.codex-plugin/plugin.json

@@ -1,35 +0,0 @@
-{
-  "name": "pig-cloud-skills-commands",
-  "version": "1.1.0",
-  "description": "Codex command pack for Pig Cloud skills. Exposes direct command-style entrypoints such as /prd and /analyze so the skill pack can be invoked without memorizing raw skill names.",
-  "author": {
-    "name": "pig-cloud-framework",
-    "url": "https://gitee.com/rebys/pig-skills"
-  },
-  "homepage": "https://gitee.com/rebys/pig-skills",
-  "repository": "https://gitee.com/rebys/pig-skills.git",
-  "license": "MIT",
-  "keywords": [
-    "codex",
-    "commands",
-    "skills",
-    "prd",
-    "analysis"
-  ],
-  "interface": {
-    "displayName": "Pig Cloud Skills Commands",
-    "shortDescription": "Command-style entrypoints for the Pig Cloud skill pack",
-    "longDescription": "Provides Codex command files like /prd, /analyze, /design, /build, and /kb that route into the Pig Cloud skills pack with stable, low-token prompts and clear execution gates.",
-    "developerName": "pig-cloud-framework",
-    "category": "Productivity",
-    "capabilities": [
-      "Interactive",
-      "Read"
-    ],
-    "websiteURL": "https://gitee.com/rebys/pig-skills",
-    "defaultPrompt": [
-      "Use /prd, /analyze, /design, /build, /review, or /kb to route work into the correct Pig Cloud skill"
-    ],
-    "brandColor": "#2563EB"
-  }
-}

package/pig-cloud-skills-commands/README.md

@@ -1,24 +0,0 @@
-# Pig Cloud Skills Commands
-
-本插件提供 Pig Cloud skill pack 的命令式入口。
-
-先安装 skill pack，再重启 Codex，命令才会生效。
-
-## Commands
-
-- `/prd` -> `product-intake`
-- `/analyze` -> `spec-refinement`
-- `/design` -> `technical-design`
-- `/build` -> `feature-build`
-- `/review` -> `code-review`
-- `/security` -> `security-review`
-- `/perf` -> `performance-check`
-- `/test` -> `test-design`
-- `/doc` -> `api-docs`
-- `/distill` -> `domain-modeling`
-- `/workflow` -> `workflow-router`
-- `/kb` -> `knowledge-capture`
-- `/init` -> `project-bootstrap`
-- `/infra` -> `environment-deploy`
-
-这些命令页保持短小，是为了让 Codex 更快定位到正确的 skill。

package/pig-cloud-skills-commands/commands/analyze.md

@@ -1,21 +0,0 @@
-# /analyze
-
-把已经确认的需求收敛成研发可执行的规格。
-
-## Route
-
-- 对应 skill：`spec-refinement`
-- 适用：需求拆解、边界梳理、依赖确认、验收标准补全
-- 不适用：还没收口的产品讨论
-
-## Workflow
-
-1. 先确认输入来自 `product-intake` 的收口结果，或至少已经完成初步收敛。
-2. 把目标、边界、依赖、约束和验收条件整理成可执行规格。
-3. 输出研发分析结果，明确后续实现所需输入。
-4. 必要时交给 `technical-design` 或 `knowledge-capture`。
-
-## Guardrails
-
-- 不直接写实现代码。
-- 不把未确认假设当结论。

package/pig-cloud-skills-commands/commands/build.md

@@ -1,21 +0,0 @@
-# /build
-
-按方案规范实现已经收口的需求。
-
-## Route
-
-- 对应 skill：`feature-build`
-- 适用：开发实现、增量改造、接口联动、落地代码
-- 不适用：需求还没收口，或者设计还没稳定
-
-## Workflow
-
-1. 先确认输入来自 `spec-refinement` 或 `technical-design`。
-2. 按分层、事务和返回值规范实现。
-3. 保持改动最小，优先可验证。
-4. 交给 `test-design` 和 `code-review` 收口。
-
-## Guardrails
-
-- 不绕过架构约束。
-- 不把临时修补当作最终实现。

package/pig-cloud-skills-commands/commands/design.md

@@ -1,21 +0,0 @@
-# /design
-
-把已经收口的需求补成可实现的技术方案。
-
-## Route
-
-- 对应 skill：`technical-design`
-- 适用：架构选型、模块拆分、接口设计、数据流设计、实现前补充设计
-- 不适用：尚未收口的需求讨论
-
-## Workflow
-
-1. 读取 `spec-refinement` 的结论。
-2. 拆分模块、接口、数据结构、事务边界和异常路径。
-3. 输出方案草图、关键决策和落地顺序。
-4. 给 `feature-build` 准备实现输入。
-
-## Guardrails
-
-- 不重新发散需求范围。
-- 不跳过架构约束直接写实现。

package/pig-cloud-skills-commands/commands/distill.md

@@ -1,21 +0,0 @@
-# /distill
-
-把业务事实提炼成可复用的领域知识。
-
-## Route
-
-- 对应 skill：`domain-modeling`
-- 适用：领域边界、实体关系、核心概念、规则沉淀
-- 不适用：纯接口变更说明
-
-## Workflow
-
-1. 识别业务对象、边界和核心规则。
-2. 抽取实体、关系、状态和约束。
-3. 输出可复用的领域索引和冲突点。
-4. 不把命名本身当作领域模型。
-
-## Guardrails
-
-- 不忽略规则冲突。
-- 不把实现细节冒充领域知识。

package/pig-cloud-skills-commands/commands/doc.md

@@ -1,21 +0,0 @@
-# /doc
-
-把接口和变更整理成可对接的文档。
-
-## Route
-
-- 对应 skill：`api-docs`
-- 适用：接口说明、变更说明、联调说明、同步文档
-- 不适用：纯代码审查
-
-## Workflow
-
-1. 先确认接口边界和输入输出。
-2. 提炼请求、响应、错误码和调用顺序。
-3. 输出可联调的文档草案。
-4. 变更后同步到知识沉淀。
-
-## Guardrails
-
-- 不遗漏错误返回和约束。
-- 不把空泛说明当成文档交付。

package/pig-cloud-skills-commands/commands/infra.md

@@ -1,21 +0,0 @@
-# /infra
-
-准备或管理开发依赖的基础设施。
-
-## Route
-
-- 对应 skill：`environment-deploy`
-- 适用：Docker Compose、依赖服务启动、开发联调环境准备
-- 不适用：业务需求分析
-
-## Workflow
-
-1. 识别需要启动的基础设施组件。
-2. 只拉起最小可用组合。
-3. 输出启动状态和常见失败点。
-4. 不把生产部署和本地开发混在一起。
-
-## Guardrails
-
-- 不默认启动多余服务。
-- 不混淆生产环境和本地环境。

package/pig-cloud-skills-commands/commands/init.md

@@ -1,20 +0,0 @@
-# /init
-
-初始化项目或模块脚手架。
-
-## Route
-
-- 对应 skill：`project-bootstrap`
-- 适用：新建项目、模块初始化、标准目录生成
-- 不适用：业务分析
-
-## Workflow
-
-1. 确认初始化对象是项目还是模块。
-2. 生成标准目录、基础配置和依赖边界。
-3. 输出后续应该进入的 skill。
-4. 不触碰具体业务逻辑。
-
-## Guardrails
-
-- 不跳过基础配置检查。

package/pig-cloud-skills-commands/commands/kb.md

@@ -1,20 +0,0 @@
-# /kb
-
-把项目事实整理成可检索、可复用、可过期治理的知识中心。
-
-## Route
-
-- 对应 skill：`knowledge-capture`
-- 适用：项目概览、模块索引、领域知识、方案沉淀、交接归档
-
-## Workflow
-
-1. 收集事实、来源、适用场景和限制条件。
-2. 分类沉淀到项目、模块、领域、方案或协作索引。
-3. 标明哪些内容可复用，哪些内容应过期清理。
-4. 让归档结果反哺后续分析和实现。
-
-## Guardrails
-
-- 不堆文档。
-- 不把未经验证的信息当知识沉淀。