审计

其他 社区

技能解读

当前原文的自动摘译,尚未人工审校。

什么时候读什么

此工作区上的新会话:首先是.claude/BOOT.md,然后是三个强制读取它列出的内容。了解 A2A 两层模型:concepts.md。与官方克劳德代码约定相比:

一个段落中的想法

每个新会话都会花费 30 轮的重新发现税重建上下文,了解存在哪些类型、锁定哪些约定、排队哪些工作。 CCA2A 是将其减少到 3-5 个回合的脚手架:两个说明当前库存和决策历史的强制性知识文件、一个用于路由子代理的代理集成文件、一个钩子

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
通用
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@tomevault-io · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
即装即用
是否需要外部接口密钥
不需要
兼容的系统
未声明(默认跨平台)
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# CCA2A — Claude Code Agent-to-Agent

Explanation-only skill. Documents the pattern so a new session can
grok it once instead of the user re-deriving it for 30 turns.

**Canonical files** (read these, not template copies):

**Entry points:**
- `.claude/BOOT.md` — session entry point (one page).
- `CLAUDE.md` — workspace spec, links to all of the below.

**Eight bookkeeping files** (rows are history; specific fields are
state; never delete a row; method hierarchy: APPEND preferred →
Edit-field after prior Read → Write prompts for confirmation):

_History / dashboards:_
- `.claude/board/LATEST_STATE.md` — current contract inventory.
- `.claude/board/PR_ARC_INVENTORY.md` — APPEND-ONLY per-PR arc.
- `.claude/board/STATUS_BOARD.md` — deliverable-level dashboard.
- `.claude/board/INTEGRATION_PLANS.md` — versioned plan index.

_Kanban / audit (priority + scope tags on every entry):_
- `.claude/board/EPIPHANIES.md` — date-prefixed insight log.
  Status: FINDING / CONJECTURE / SUPERSEDED.
- `.claude/board/ISSUES.md` — Open + Resolved bugs / regressions.
  Double-entry: issue captured on discovery; Resolution appends on
  close. Priority P0-P3, Scope @agent D<N> domain:<tag>.
- `.claude/board/IDEAS.md` — Open + Implemented + Rejected
  speculation. Triple-entry: idea captured, shipped appended,
  plan-update logged. Priority + Scope.
- `.claude/board/TECH_DEBT.md` — Open + Paid knowingly-deferred
  work. Priority + Scope + Introduced-by-PR + Payoff-estimate.

**Agent ensemble + orchestration:**
- `.claude/agents/BOOT.md` — orchestration spec + Knowledge
  Activation + Handover Protocol.
- `.claude/agents/README.md` — function inventory of all agents.

**Governance + hooks:**
- `.claude/settings.json` — team-shared governance (ask-on-Edit for
  the two strictest bookkeeping files, deny on destructive ops,
  SessionStart + PostCompact hooks).
- `.claude/hooks/session-start.sh` / `post-compact.sh` — inject
  bootload context at turn 0 / after compaction.

**Active plans:**
- `.claude/plans/<name>-v<N>.md` — indexed via
  `INTEGRATION_PLANS.md`. Old versions stay with Status annotation;
  new versions prepend.

## What to read when

- **New session on this workspace:** `.claude/BOOT.md` first, then
  the three mandatory reads it lists.
- **Understanding the A2A two-layer model:**
  [concepts.md](concepts.md).
- **Comparing to official Claude Code conventions:**
  [divergence.md](divergence.md).
- **Concrete recipe: code awareness in ~90 s via prompt↔PR ledger:**
  [procedure-bookkeeping.md](procedure-bookkeeping.md). Three-pass
  Haiku→Opus→main-thread pipeline. First deployment: PR #213
  (lance-graph, 41 prompts) + PR #110 (ndarray, 25 prompts) on
  2026-04-19, both ~90 s wall clock.

## The idea in one paragraph

Every new session pays a 30-turn rediscovery tax rebuilding context
about what types exist, which conventions are locked, what work is
queued. CCA2A is the scaffold that cuts that to 3-5 turns: two
mandatory knowledge files that state current inventory and decision
history, one agent ensemble file that routes subagents, one hook
that injects critical state after compaction. Append-only
governance on the history files so drift can't erode the arc.

---
> Source: [AdaWorldAPI/lance-graph](https://github.com/AdaWorldAPI/lance-graph) — distributed by [TomeVault](https://tomevault.io).
<!-- tomevault:4.0:skill_md:2026-05-23 -->

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。