@baoanaz/cviauto 0.6.5 → 0.6.8

package/dist/templates/common/bundled-skills/trellis-meta/references/platform-files/platform-map.md

@@ -1,34 +1,33 @@
-# Platform File Map
+# Platform File Map（平台文件映射）
 
-This page lists common Cviauto file locations in a user project by platform. Whether a platform directory exists in an actual project depends on which `cviauto init --<platform>` commands the user ran.
+本页列出了各平台在用户项目中的常见 Cviauto 文件位置。实际项目中是否存在某个平台目录，取决于用户运行了哪些 `cviauto init --<platform>` 命令。
 
-## Matrix
+## Matrix（矩阵）
 
-| Platform | CLI flag | Main directory | Skill directory | Agent directory | Hooks/extensions |
+| Platform（平台） | CLI flag（CLI 标志） | Main directory（主目录） | Skill directory（技能目录） | Agent directory（代理目录） | Hooks/extensions（钩子/扩展） |
 | --- | --- | --- | --- | --- | --- |
 | Claude Code | `--claude` | `.claude/` | `.claude/skills/` | `.claude/agents/` | `.claude/hooks/` + `.claude/settings.json` |
 | Cursor | `--cursor` | `.cursor/` | `.cursor/skills/` | `.cursor/agents/` | `.cursor/hooks.json` + `.cursor/hooks/` |
 | OpenCode | `--opencode` | `.opencode/` | `.opencode/skills/` | `.opencode/agents/` | `.opencode/plugins/` |
 | Codex | `--codex` | `.codex/` | `.agents/skills/` | `.codex/agents/` | `.codex/hooks/` + `.codex/hooks.json` |
-| Kilo | `--kilo` | `.kilocode/` | `.kilocode/skills/` | Usually none | `.kilocode/workflows/` |
+| Kilo | `--kilo` | `.kilocode/` | `.kilocode/skills/` | 通常无 | `.kilocode/workflows/` |
 | Kiro | `--kiro` | `.kiro/` | `.kiro/skills/` | `.kiro/agents/` | `.kiro/hooks/` |
 | Gemini CLI | `--gemini` | `.gemini/` | `.agents/skills/` | `.gemini/agents/` | `.gemini/settings.json` + `.gemini/hooks/` |
-| Antigravity | `--antigravity` | `.agent/` | `.agent/skills/` | Usually none | `.agent/workflows/` |
-| Devin | `--devin` | `.devin/` | `.devin/skills/` | Usually none | `.devin/workflows/` |
+| Antigravity | `--antigravity` | `.agent/` | `.agent/skills/` | 通常无 | `.agent/workflows/` |
+| Devin | `--devin` | `.devin/` | `.devin/skills/` | 通常无 | `.devin/workflows/` |
 | Qoder | `--qoder` | `.qoder/` | `.qoder/skills/` | `.qoder/agents/` | `.qoder/hooks/` + `.qoder/settings.json` |
 | CodeBuddy | `--codebuddy` | `.codebuddy/` | `.codebuddy/skills/` | `.codebuddy/agents/` | `.codebuddy/hooks/` + `.codebuddy/settings.json` |
 | GitHub Copilot | `--copilot` | `.github/` | `.github/skills/` | `.github/agents/` | `.github/copilot/hooks/` + prompts |
 | Factory Droid | `--droid` | `.factory/` | `.factory/skills/` | `.factory/droids/` | `.factory/hooks/` + settings |
-| Pi Agent | `--pi` | `.pi/` | `.pi/skills/` | `.pi/agents/` | `.pi/extensions/trellis/` (native `trellis_subagent` tool) + `.pi/settings.json` |
-| Trae IDE | `--trae` | `.trae/` | `.trae/skills/` | `.trae/agents/` | `.trae/hooks/` + `.trae/hooks.json` |
-| Reasonix | `--reasonix` | `.reasonix/` | `.reasonix/skills/` | None — sub-agents are skills with `runAs: subagent` frontmatter | None |
-| ZCode | `--zcode` | `.zcode/` | `.agents/skills/` | `.zcode/cli/agents/` | pull-based prelude (no hooks) |
+| Pi Agent | `--pi` | `.pi/` | `.pi/skills/` | `.pi/agents/` | `.pi/extensions/cviauto/`（原生 `trellis_subagent` 工具） + `.pi/settings.json` |
+| Reasonix | `--reasonix` | `.reasonix/` | `.reasonix/skills/` | 无 — sub-agent 是带有 `runAs: subagent` 前置元数据的 skills | 无 |
+| ZCode | `--zcode` | `.zcode/` | `.agents/skills/` | `.zcode/cli/agents/` | pull-based prelude（拉取模式序言，无 hooks） |
 
-## Capability Groups
+## Capability Groups（能力分组）
 
-### Cviauto Sub-Agent Support
+### Cviauto Sub-Agent Support（Cviauto Sub-Agent 支持）
 
-These platforms usually have `cviauto-research`, `cviauto-implement`, and `cviauto-check` files:
+以下平台通常有 `cviauto-research`、`cviauto-implement` 和 `cviauto-check` 文件：
 
 - Claude Code
 - Cursor
@@ -41,48 +40,47 @@ These platforms usually have `cviauto-research`, `cviauto-implement`, and `cviau
 - GitHub Copilot
 - Factory Droid
 - Pi Agent
-- Trae IDE
-- Reasonix (delivered as skills with `runAs: subagent` under `.reasonix/skills/`, not as a separate `agents/` directory)
+- Reasonix（以带有 `runAs: subagent` 的 skills 形式交付，位于 `.reasonix/skills/` 下，而非独立的 `agents/` 目录）
 - ZCode
 
-When changing implementation/check/research behavior, look for the corresponding platform agent files first.
+更改 implementation/check/research 行为时，请先查找对应平台的 agent 文件。
 
-### Native Cviauto Sub-Agent Tool
+### Native Cviauto Sub-Agent Tool（原生 Cviauto Sub-Agent 工具）
 
-Some platforms expose a first-class tool that the host runtime understands. The model calls it like any other tool and the host renders progress cards, validates the agent name against `.<platform>/agents/`, and enforces dispatch modes.
+某些平台暴露了一个宿主运行时理解的一级工具。模型像调用其他工具一样调用它，宿主渲染进度卡片、根据 `.<platform>/agents/` 验证 agent 名称，并强制执行分发模式。
 
-- Pi Agent — `trellis_subagent` tool, defined in `.pi/extensions/trellis/index.ts`. Supports `single` / `parallel` / `chain` dispatch modes and emits live `trellis-subagent-progress` events.
+- Pi Agent — `trellis_subagent` 工具，定义在 `.pi/extensions/cviauto/index.ts`。支持 `single` / `parallel` / `chain` 分发模式，并发出实时的 `cviauto-subagent-progress` 事件。
 
-When changing sub-agent dispatch behavior on these platforms, edit the extension file, **not** the agent markdown — the agent markdown defines responsibilities, but the host extension owns dispatch, validation, and progress rendering.
+在这些平台上更改 sub-agent 分发行为时，请编辑扩展文件，**而非** agent 的 markdown 文件 — agent markdown 定义职责，但宿主扩展负责分发、验证和进度渲染。
 
-### Main-Session Workflow Platforms
+### Main-Session Workflow Platforms（主会话工作流平台）
 
-These platforms rely more on workflows/skills to guide the main session:
+以下平台更依赖 workflows/skills 来引导主会话：
 
 - Kilo
 - Antigravity
 - Devin
 
-When changing behavior, inspect workflows and skills first. Do not assume Cviauto sub-agents exist.
+更改行为时，请先检查 workflows 和 skills。不要假设存在 Cviauto sub-agent。
 
-### Shared `.agents/skills/`
+### Shared `.agents/skills/`（共享 `.agents/skills/`）
 
-Codex writes the shared `.agents/skills/` layer. Some tools that support agentskills.io can also read this directory. If the user wants multiple compatible tools to share one skill, consider `.agents/skills/` first, but do not assume every platform reads it.
+Codex 写入共享的 `.agents/skills/` 层。某些支持 agentskills.io 的工具也可以读取此目录。如果用户希望多个兼容工具共享一个 skill，可优先考虑 `.agents/skills/`，但不要假设每个平台都会读取它。
 
-## Decision Rules When Modifying Platform Files
+## Decision Rules When Modifying Platform Files（修改平台文件时的决策规则）
 
-1. User specified a platform: modify only that platform directory unless shared workflow/spec files must also change.
-2. User says "all platforms should do this": synchronize equivalent entry points platform by platform; do not modify only one directory.
-3. User only says "my AI": inspect the configuration directories that actually exist in the project and infer the current AI platform.
-4. User wants project rules: prefer `.cviauto/spec/` or a project-local skill.
-5. User wants Cviauto behavior: edit `.cviauto/workflow.md` plus platform hooks/agents/skills/commands.
+1. 用户指定了平台：仅修改该平台目录，除非共享的 workflow/spec 文件也必须更改。
+2. 用户说"所有平台都应该这样做"：逐平台同步等效入口点；不要只修改一个目录。
+3. 用户只说"我的 AI"：检查项目中实际存在的配置目录，推断当前 AI 平台。
+4. 用户想要项目规则：优先使用 `.cviauto/spec/` 或项目本地 skill。
+5. 用户想要 Cviauto 行为：编辑 `.cviauto/workflow.md` 以及平台 hooks/agents/skills/commands。
 
-## When Paths Differ
+## When Paths Differ（当路径不一致时）
 
-Platform ecosystems change, and user projects may already be customized. If this table disagrees with local files, use the actual settings/config in the user project as authoritative:
+平台生态会变化，用户项目可能已经自定义过。如果此表与本地文件不一致，请以用户项目中实际的 settings/config 为准：
 
-- Check the hook that settings registers.
-- Check the script that a command/prompt/workflow points to.
-- Judge behavior by the read rules currently written in the agent file.
+- 检查 settings 注册的 hook。
+- 检查 command/prompt/workflow 指向的脚本。
+- 根据 agent 文件中当前编写的读取规则判断行为。
 
-Do not delete a custom file just because it is not listed in this path table.
+不要仅因为某个自定义文件不在本路径表中就将其删除。

package/dist/templates/common/bundled-skills/trellis-meta/references/platform-files/skills-and-commands.md

@@ -1,44 +1,44 @@
-# Skills, Commands, Prompts, And Workflows
+# Skills（技能）、Commands（命令）、Prompts（提示）与 Workflows（工作流）
 
-Skills and commands are textual entry points for user interaction with Cviauto. Different platforms use different names, but their core purpose is the same: tell the AI how to enter the Cviauto flow when the user expresses a certain intent.
+Skills 和 commands 是用户与 Cviauto 交互的文本入口。不同平台使用不同的名称，但它们的核心目的相同：告诉 AI 在用户表达特定意图时如何进入 Cviauto 流程。
 
-## Conceptual Differences
+## 概念差异
 
-| Type | Trigger mode | Best for |
+| 类型 | 触发方式 | 最适合 |
 | --- | --- | --- |
-| skill | AI auto-match or explicit user mention | Long-term capabilities, workflow rules, modification guides. |
-| command | Explicit user invocation | Clear operation entry points such as continue and finish-work. |
-| prompt | Explicit user invocation or platform selection | Similar to command, but in a platform prompt format. |
-| workflow | Explicit user selection or platform auto-match | Guides the main session when no sub-agent/hook exists. |
+| skill | AI 自动匹配或用户显式提及 | 长期能力、工作流规则、修改指南。 |
+| command | 用户显式调用 | 明确的操作入口，如 continue、finish-work。 |
+| prompt | 用户显式调用或平台选择 | 与 command 类似，但采用平台 prompt 格式。 |
+| workflow | 用户显式选择或平台自动匹配 | 在无子代理/钩子时引导主会话。 |
 
-Cviauto workflow skills usually share one semantic set: brainstorm, before-dev, check, update-spec, break-loop. Multi-file built-in skills such as `cviauto-meta` use layered references.
+Cviauto 工作流技能通常共享一套语义集合：brainstorm、before-dev、check、update-spec、break-loop。多文件内置技能如 `cviauto-meta` 使用分层引用。
 
-## Common Paths
+## 常见路径
 
-| Platform | Common entries |
+| 平台 | 常见入口 |
 | --- | --- |
-| Claude Code | `.claude/skills/`, `.claude/commands/` |
-| Cursor | `.cursor/skills/`, `.cursor/commands/` |
-| OpenCode | `.opencode/skills/`, `.opencode/commands/` |
-| Codex | `.agents/skills/`, `.codex/skills/` |
-| Kilo | `.kilocode/skills/`, `.kilocode/workflows/` |
+| Claude Code | `.claude/skills/`、`.claude/commands/` |
+| Cursor | `.cursor/skills/`、`.cursor/commands/` |
+| OpenCode | `.opencode/skills/`、`.opencode/commands/` |
+| Codex | `.agents/skills/`、`.codex/skills/` |
+| Kilo | `.kilocode/skills/`、`.kilocode/workflows/` |
 | Kiro | `.kiro/skills/` |
-| Gemini CLI | `.agents/skills/`, `.gemini/commands/` |
-| Antigravity | `.agent/skills/`, `.agent/workflows/` |
-| Devin | `.devin/skills/`, `.devin/workflows/` |
-| Qoder | `.qoder/skills/`, `.qoder/commands/` |
-| CodeBuddy | `.codebuddy/skills/`, `.codebuddy/commands/` |
-| GitHub Copilot | `.github/skills/`, `.github/prompts/` |
-| Factory Droid | `.factory/skills/`, `.factory/commands/` |
+| Gemini CLI | `.agents/skills/`、`.gemini/commands/` |
+| Antigravity | `.agent/skills/`、`.agent/workflows/` |
+| Devin | `.devin/skills/`、`.devin/workflows/` |
+| Qoder | `.qoder/skills/`、`.qoder/commands/` |
+| CodeBuddy | `.codebuddy/skills/`、`.codebuddy/commands/` |
+| GitHub Copilot | `.github/skills/`、`.github/prompts/` |
+| Factory Droid | `.factory/skills/`、`.factory/commands/` |
 | Pi Agent | `.pi/skills/` |
 | Reasonix | `.reasonix/skills/` |
-| ZCode | `.agents/skills/`, `.zcode/commands/` |
+| ZCode | `.agents/skills/`、`.zcode/commands/` |
 
-In a user project, use the files actually generated by init as authoritative.
+在用户项目中，以 `init` 实际生成的文件为准。
 
-## Skill Structure
+## Skill 结构
 
-A common skill is a directory:
+一个常见的 skill 是一个目录：
 
 ```text
 cviauto-meta/
@@ -46,40 +46,40 @@ cviauto-meta/
 └── references/
 ```
 
-`SKILL.md` should tell the AI:
+`SKILL.md` 应告诉 AI：
 
-- When to use this skill.
-- Which reference to read first for the current task.
-- What not to do.
+- 何时使用此技能。
+- 当前任务应首先阅读哪个参考文件。
+- 不应做什么。
 
-References hold longer explanations so the entry file does not contain everything.
+references 存放较长的说明，使入口文件不必包含所有内容。
 
-## Command/Prompt/Workflow Structure
+## Command/Prompt/Workflow 结构
 
-Commands, prompts, and workflows are usually single files. Their content should include:
+Commands、prompts 和 workflows 通常是单个文件。其内容应包括：
 
-- When to use it.
-- Which `.cviauto/` files to read.
-- Which scripts to run.
-- How to report after completion.
+- 何时使用。
+- 要读取哪些 `.cviauto/` 文件。
+- 要运行哪些脚本。
+- 完成后如何报告。
 
-They should not store task state; task state belongs in `.cviauto/tasks/` and `.cviauto/.runtime/`.
+它们不应存储任务状态；任务状态属于 `.cviauto/tasks/` 和 `.cviauto/.runtime/`。
 
-## Local Change Scenarios
+## 本地修改场景
 
-| User need | Edit location |
+| 用户需求 | 编辑位置 |
 | --- | --- |
-| Change AI auto-trigger rules | The corresponding skill's frontmatter description. |
-| Change user command behavior | The corresponding command/prompt/workflow file. |
-| Add a project-local skill | Platform skill directory, or shared `.agents/skills/`. |
-| Let multiple platforms share one capability | Write equivalent skills in each platform skill directory, or use the `.agents/skills/` shared layer on platforms that support it. |
-| Change finish/continue entry points | Platform commands/prompts/workflows. |
+| 修改 AI 自动触发规则 | 对应 skill 的 frontmatter 描述。 |
+| 修改用户命令行为 | 对应的 command/prompt/workflow 文件。 |
+| 添加项目本地 skill | 平台 skill 目录，或共享的 `.agents/skills/`。 |
+| 让多个平台共享一个能力 | 在各平台 skill 目录中编写等效 skill，或在支持 `.agents/skills/` 共享层的平台上使用该层。 |
+| 修改 finish/continue 入口 | 平台的 commands/prompts/workflows。 |
 
-## Modification Principles
+## 修改原则
 
-1. **Keep entry files short; references carry long content**. This matters especially for multi-file skills like `cviauto-meta`.
-2. **Make trigger descriptions specific**. A description that is too broad can mis-trigger; one that is too narrow may not trigger.
-3. **Keep the same semantics consistent across platforms**. File formats can differ, but behavior descriptions should match.
-4. **Put project-specific capabilities in local skills**. Do not put team-private flows into public `cviauto-meta`.
+1. **保持入口文件简短；references 承载长内容**。这对 `cviauto-meta` 等多文件技能尤为重要。
+2. **让触发描述具体明确**。过于宽泛的描述可能误触发；过于狭窄可能无法触发。
+3. **跨平台保持语义一致**。文件格式可以不同，但行为描述应匹配。
+4. **将项目特定能力放在本地 skill 中**。不要将团队私有流程放入公共 `cviauto-meta`。
 
-If the user only wants local AI to know one more project rule, usually create a project-local skill or update `.cviauto/spec/` instead of changing a Cviauto built-in workflow skill.
+如果用户只想让本地 AI 多了解一条项目规则，通常应创建项目本地 skill 或更新 `.cviauto/spec/`，而不是修改 Cviauto 内置工作流技能。

package/dist/templates/common/bundled-skills/trellis-session-insight/SKILL.md

@@ -3,79 +3,79 @@ name: cviauto-session-insight
 description: "Reach into past AI conversation history through the `cviauto mem` CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work, debugging a familiar bug, continuing a task across sessions, or doing a finish-work review. Returns raw past dialogue; decide for the moment whether to update spec, append to task notes, quote inline in the answer, or just internalize."
 ---
 
-# Cviauto Session Insight
+# Cviauto 会话洞察
 
-This skill teaches an AI **how to call `cviauto mem`** — the project's cross-session memory feedstock — and **when reaching for it is the right move**.
+此技能教 AI **如何调用 `cviauto mem`**——项目的跨会话记忆原料——以及**何时使用它是正确的选择**。
 
-It is intentionally a **capability skill, not a workflow**. There is no fixed output file, no required write-back step, no "always run after finish-work" rule. What to do with what `mem` returns is a judgement call made in the moment of the conversation. The skill exists so the AI knows the capability is there and can decide.
+它有意设计为**能力技能，而非工作流**。没有固定的输出文件，没有必需的写回步骤，没有"始终在 finish-work 后运行"的规则。如何处理 `mem` 返回的内容是在对话当下做出的判断。此技能的存在是为了让 AI 知道这个能力的存在并可以自行决定。
 
-## What `cviauto mem` is
+## `cviauto mem` 是什么
 
-A local CLI that indexes the user's past Claude Code, Codex, and Pi Agent conversation logs (the JSONL files each platform stores under `~/.claude/projects/`, `~/.codex/sessions/`, and `~/.pi/agent/sessions/`) and lets you list, search, slice by Cviauto task boundaries, and dump cleaned dialogue from them. OpenCode logs are not yet indexable (provider adapter pending) — when an OpenCode session is the obvious target, surface that limitation rather than guessing.
+一个本地 CLI，索引用户过去的 Claude Code、Codex 和 Pi Agent 对话日志（每个平台存储在 `~/.claude/projects/`、`~/.codex/sessions/` 和 `~/.pi/agent/sessions/` 下的 JSONL 文件），并允许你列出、搜索、按 Cviauto 任务边界切片，以及从中导出清洗后的对话内容。OpenCode 日志尚不可索引（provider adapter 待完成）——当 OpenCode 会话是明显目标时，应说明此限制而非猜测。
 
-Nothing in `mem` is uploaded. All reads are local.
+`mem` 中的任何内容都不会上传。所有读取都在本地。
 
-## When to reach for it
+## 何时使用它
 
-The bar is "would a senior teammate ask 'didn't we already talk about this?'" — those are the moments. Some concrete patterns:
+标准是"资深同事会不会问'我们不是已经讨论过这个了吗？'"——那些就是使用的时刻。一些具体模式：
 
-- **Brainstorm rerun risk.** Starting a new task that touches an area the user has been in before, and you want to check whether a decision was already made — before re-asking the user.
-- **Familiar-bug debugging.** The current bug pattern feels like one the user reported / fixed before. Pulling the relevant past session can save a full debugging loop.
-- **Cross-session continuation.** The user resumes work after a gap and says "where were we" / "继续上次的" without being specific.
-- **Decision retrieval.** The user references "the decision we made about X" but the decision lives in an old brainstorm, not in any `prd.md` / `spec/`.
-- **Finish-work retrospective.** When the user explicitly asks for a wrap-up of what was decided / what hurt / what surprised them in this task — not as a forced step on every finish-work.
-- **Pattern-spotting across past work.** The user asks "do I keep making the same mistake on X" / "我每次都踩这个坑吗" — search across sessions answers that.
+- **Brainstorm 重复风险。** 开始一个涉及用户之前接触过的领域的新任务时，你想在重新询问用户之前检查是否已经做过决定。
+- **熟悉的 bug 调试。** 当前的 bug 模式感觉像是用户之前报告/修复过的。拉取相关的过往会话可以节省整个调试循环。
+- **跨会话续接。** 用户在中断后恢复工作，说"我们上次做到哪了"/"继续上次的"，但没有具体说明。
+- **决策检索。** 用户提到"我们关于 X 做的决定"，但该决定存在于旧的 brainstorm 中，而非任何 `prd.md` / `spec/` 中。
+- **Finish-work 回顾。** 当用户明确要求总结此任务中决定了什么/什么令人痛苦/什么令人惊讶——不是每次 finish-work 的强制步骤。
+- **跨过往工作的模式发现。** 用户问"我是不是一直在犯同样的 X 错误"/"我每次都踩这个坑吗"——跨会话搜索可以回答。
 
-If none of these apply, don't call `mem`. It is a tool, not a ceremony.
+如果以上都不适用，不要调用 `mem`。它是一个工具，不是仪式。
 
-## When NOT to reach for it
+## 何时不使用它
 
-- The relevant context is already in the current turn, `prd.md`, `design.md`, recent `git log`, or the open files. `mem` is for stuff that has fallen out of immediate reach.
-- The user is asking about a fact in the code, not a fact from a past conversation. `git log -p` / `grep` / reading the file directly is faster and more authoritative.
-- You are in a sub-agent (`cviauto-implement` / `cviauto-check`) whose dispatch prompt already includes the curated `implement.jsonl` / `check.jsonl` context. Adding `mem` on top usually just clutters.
-- The user has explicitly said "don't dig through history, just answer what I asked".
+- 相关上下文已经在当前轮次、`prd.md`、`design.md`、最近的 `git log` 或打开的文件中。`mem` 用于已经脱离即时范围的内容。
+- 用户问的是代码中的事实，而非过往对话中的事实。`git log -p` / `grep` / 直接读文件更快且更权威。
+- 你在 sub-agent（`cviauto-implement` / `cviauto-check`）中，其分发 prompt 已包含整理好的 `implement.jsonl` / `check.jsonl` 上下文。在此基础上加 `mem` 通常只会增加杂乱。
+- 用户明确表示"不要翻历史，按我问的回答"。
 
-## What to do with what `mem` returns
+## 如何处理 `mem` 返回的内容
 
-Treat the output as **raw material**, not a deliverable. Once you have it, decide based on the live conversation:
+将输出视为**原材料**，而非交付物。获得之后，根据实时对话决定：
 
-- **Quote inline in your reply** if a specific past exchange answers the user's current question — and cite the session-id / phase so the user can verify.
-- **Update `<task>/prd.md` or `<task>/design.md`** if `mem` surfaced a load-bearing decision that should have been written down but wasn't. Surface the proposed edit to the user first.
-- **Append to a task-local notes file** (e.g. `<task>/notes.md` or extending an existing one) if the finding belongs to the current task's record but doesn't fit the PRD.
-- **Update `.cviauto/spec/`** if the finding is a project-wide convention or gotcha that would help future tasks. Run the `cviauto-update-spec` skill for that — `session-insight` ends at the discovery.
-- **Just absorb it** for the next few turns and answer better, without writing anything. This is often the right move for one-off recall.
+- **在你的回复中内联引用**，如果具体的过往交流能回答用户当前的问题——并引用 session-id / phase 以便用户验证。
+- **更新 `<task>/prd.md` 或 `<task>/design.md`**，如果 `mem` 发现了一个应当被记录但未记录的关键决策。先向用户展示建议的编辑。
+- **追加到任务本地笔记文件**（如 `<task>/notes.md` 或扩展现有文件），如果发现的内容属于当前任务记录但不适合放入 PRD。
+- **更新 `.cviauto/spec/`**，如果发现的是项目级约定或陷阱，会对未来任务有帮助。运行 `cviauto-update-spec` 技能来处理——`session-insight` 止步于发现。
+- **仅吸收**，在接下来的几轮中更好地回答，而不写入任何内容。这对一次性回忆通常是正确的做法。
 
-Cviauto does not prescribe a single destination. Forcing every recall into a fixed file makes the file grow into noise. Let the situation decide.
+Cviauto 不规定单一目的地。把每次回忆强制写入固定文件会让文件膨胀成噪音。让情境决定。
 
-## How to call it
+## 如何调用
 
-Full CLI reference is in `references/cli-quick-reference.md`. The 80% case is one of:
+完整 CLI 参考在 `references/cli-quick-reference.md`。80% 的情况是以下之一：
 
 ```bash
-# Find sessions whose contents mention a keyword (project-scope is default;
-# add --global to search every project on this machine).
-cviauto mem search "<keyword>"
+# 查找内容包含关键词的会话（project-scope 是默认；
+# 添加 --global 搜索此机器上的所有项目）。
+cviauto mem search "<关键词>"
 
-# Dump dialogue from one session, optionally filtered by phase or keyword.
+# 导出一个会话的对话内容，可选按阶段或关键词过滤。
 cviauto mem extract <session-id> --phase brainstorm
-cviauto mem extract <session-id> --grep "<keyword>"
+cviauto mem extract <session-id> --grep "<关键词>"
 
-# Drill into a session: top-N hit turns + surrounding context.
+# 深入一个会话：top-N 命中轮次 + 周围上下文。
 cviauto mem context <session-id> --turns 3 --around 2
 
-# When you do not know the session id yet, start with list + filter.
+# 当还不知道 session id 时，从 list + filter 开始。
 cviauto mem list --cwd <project-path>
-cviauto mem projects   # → list active project cwds, then narrow
+cviauto mem projects   # → 列出活动项目 cwd，然后缩小范围
 ```
 
-Phase slicing (`--phase brainstorm|implement|all`) cuts the session at `task.py create` and `task.py start` boundaries. For a finish-work review of the current task, `--phase brainstorm` recovers the planning discussion and `--phase implement` recovers the execution loop. Default is `all`.
+阶段切片（`--phase brainstorm|implement|all`）在 `task.py create` 和 `task.py start` 边界处切割会话。对当前任务的 finish-work 回顾，`--phase brainstorm` 恢复规划讨论，`--phase implement` 恢复执行循环。默认为 `all`。
 
-## Triggering patterns
+## 触发模式
 
-`references/triggering-patterns.md` lists more verbatim user phrasings (English + Chinese) that should make you think "reach for `mem`" — keep that handy when training instinct.
+`references/triggering-patterns.md` 列出了更多应当让你想到"使用 `mem`"的逐字用户表述（英文 + 中文）——在训练直觉时随时参考。
 
-## Out of scope
+## 超出范围
 
-- `mem` does not edit code or update files. Any write-back is your decision in the moment.
-- `mem` is read-only on the platform JSONL stores. It does not push or sync to remote.
-- This skill does not replace `cviauto-update-spec` (which is the right tool for promoting a finding into project-wide guidance) or the platform-native task / spec workflow.
+- `mem` 不编辑代码或更新文件。任何写回是你在当下做出的决定。
+- `mem` 对平台 JSONL 存储是只读的。它不推送或同步到远程。
+- 此技能不替代 `cviauto-update-spec`（后者是将发现推广为项目级指南的正确工具）或平台原生的 task / spec 工作流。

package/dist/templates/common/bundled-skills/trellis-session-insight/references/cli-quick-reference.md

@@ -1,65 +1,64 @@
-# `cviauto mem` CLI Reference
+# `cviauto mem` CLI 参考
 
-Full flag reference for the five subcommands. Pin this as the authoritative source — `cviauto mem help` prints the same content at runtime, so anything here that drifts is a bug.
+五个子命令的完整标志参考。将此作为权威来源——`cviauto mem help` 在运行时会打印相同内容，因此此处任何与运行时不一致的内容都属于 bug。
 
-## Subcommands
+## 子命令
 
-| Command                | Purpose                                                                                                                |
+| 命令                    | 用途                                                                                                          |
 | ---------------------- | ---------------------------------------------------------------------------------------------------------------------- |
-| `list`                 | List sessions. Default subcommand when none is given.                                                                  |
-| `search <keyword>`     | Find sessions whose contents match a keyword.                                                                          |
-| `context <session-id>` | Drill into one session: top-N hit turns + surrounding context. Pair with `--grep` for keyword anchoring.               |
-| `extract <session-id>` | Dump cleaned dialogue. Combine with `--phase` / `--grep` to slice.                                                     |
-| `projects`             | List active project `cwd` values with session counts. Use this to discover which `--cwd` to pass to other subcommands. |
+| `list`                 | 列出会话。未指定子命令时的默认行为。                                                                  |
+| `search <keyword>`     | 查找内容匹配关键词的会话。                                                                          |
+| `context <session-id>` | 深入查看某个会话：Top-N 命中轮次 + 周围上下文。配合 `--grep` 进行关键词锚定。               |
+| `extract <session-id>` | 导出清洗后的对话记录。结合 `--phase` / `--grep` 进行切片。                                                     |
+| `projects`             | 列出活跃项目的 `cwd` 值及其会话计数。用于发现应传递给其他子命令的 `--cwd`。 |
 
-## Flags (apply where meaningful)
+## 标志（酌情适用）
 
-| Flag                                          | Subcommands       | Meaning                                                                                                                                                    |
+| 标志                                           | 子命令               | 含义                                                                                                                                                    |
 | --------------------------------------------- | ----------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `--platform claude\|codex\|opencode\|pi\|all` | all               | Default `all`. OpenCode adapter is currently a stub on `0.6.0-beta.*` — see "Caveats" below.                                                               |
-| `--since YYYY-MM-DD`                          | list / search     | Inclusive lower date bound.                                                                                                                                |
-| `--until YYYY-MM-DD`                          | list / search     | Inclusive upper date bound.                                                                                                                                |
-| `--global`                                    | list / search     | Include sessions from every project on this machine. Default is the current project `cwd`.                                                                 |
-| `--cwd <path>`                                | list / search     | Force a specific project cwd instead of inferring from where you are.                                                                                      |
-| `--limit N`                                   | list / search     | Cap output rows. Default `50`.                                                                                                                             |
-| `--grep KW`                                   | extract / context | Filter turns by keyword. Multi-token AND when whitespace-separated.                                                                                        |
-| `--phase brainstorm\|implement\|all`          | extract           | Slice session by Cviauto task boundaries. `brainstorm` = `[task.py create, task.py start)`. `implement` = turns outside brainstorm windows. Default `all`. |
-| `--turns N`                                   | context           | Number of hit turns to return. Default `3`.                                                                                                                |
-| `--around N`                                  | context           | Surrounding turns to include per hit. Default `1`.                                                                                                         |
-| `--max-chars N`                               | context           | Total character budget. Default `6000` (~1500 tokens).                                                                                                     |
-| `--include-children`                          | search / context  | Merge OpenCode sub-agent sessions into their parent session.                                                                                               |
-| `--json`                                      | all               | Emit machine-parseable JSON instead of human-readable output.                                                                                              |
-
-## Common one-liners
+| `--platform claude\|codex\|opencode\|pi\|all` | 全部               | 默认 `all`。OpenCode 适配器在 `0.6.0-beta.*` 上目前为桩实现——见下方"注意事项"。                                                               |
+| `--since YYYY-MM-DD`                          | list / search     | 包含下界日期。                                                                                                                                |
+| `--until YYYY-MM-DD`                          | list / search     | 包含上界日期。                                                                                                                                |
+| `--global`                                    | list / search     | 包含本机上所有项目的会话。默认仅当前项目 `cwd`。                                                                 |
+| `--cwd <path>`                                | list / search     | 强制使用指定项目 cwd，而非根据当前位置推断。                                                                                      |
+| `--limit N`                                   | list / search     | 输出行数上限。默认 `50`。                                                                                                                             |
+| `--grep KW`                                   | extract / context | 按关键词筛选轮次。空格分隔表示多词 AND。                                                                                        |
+| `--phase brainstorm\|implement\|all`          | extract           | 按 Cviauto 任务边界切片会话。`brainstorm` = `[task.py create, task.py start)`。`implement` = 头脑风暴窗口之外的轮次。默认 `all`。 |
+| `--turns N`                                   | context           | 返回的命中轮次数量。默认 `3`。                                                                                                                |
+| `--around N`                                  | context           | 每个命中轮次包含的周围轮次数。默认 `1`。                                                                                                         |
+| `--max-chars N`                               | context           | 总字符预算。默认 `6000`（约 1500 tokens）。                                                                                                     |
+| `--include-children`                          | search / context  | 将 OpenCode 子 agent 会话合并到其父会话中。                                                                                               |
+| `--json`                                      | 全部               | 输出机器可解析的 JSON，而非人类可读输出。                                                                                              |
+
+## 常用一行命令
 
 ```bash
-# What past sessions discussed "deadlock" anywhere on this machine?
+# 本机上哪些过往会话讨论过 "deadlock"？
 cviauto mem search "deadlock" --global --limit 20
 
-# Inside a specific session, surface the top 5 turns that mention "lock contention"
-# plus 2 turns of surrounding context.
+# 在特定会话中，找出提及 "lock contention" 的前 5 轮，
+# 并附带每轮前后各 2 轮的上下文。
 cviauto mem context 5842592d --grep "lock contention" --turns 5 --around 2
 
-# Recover the brainstorm window for a session — useful when continuing a task
-# the user started a week ago.
+# 恢复某个会话的头脑风暴窗口——当需要继续用户一周前开始的任务时很有用。
 cviauto mem extract 5842592d --phase brainstorm
 
-# List every project this machine has Cviauto sessions for, with counts.
+# 列出本机所有有 Cviauto 会话的项目及其会话计数。
 cviauto mem projects
 ```
 
-## Output shapes
+## 输出形态
 
-- **Default human output** (no `--json`): wrapped to a terminal, with session ids highlighted and turn markers visible. Suitable to read inline but messy to paste into a markdown file.
-- **`--json`**: stable schema, safe to parse and process. When piping `mem` output into a follow-up step (e.g. summarizing for a Lessons section), prefer `--json`.
+- **默认人类可读输出**（无 `--json`）：适配终端宽度，会话 ID 高亮显示，轮次标记可见。适合内联阅读，但不适合粘贴到 markdown 文件中。
+- **`--json`**：稳定 schema，可安全解析和处理。当将 `mem` 输出通过管道传递给后续步骤（例如为经验教训章节做摘要）时，优先使用 `--json`。
 
-## Caveats
+## 注意事项
 
-- **OpenCode adapter is a stub on `0.6.0-beta.*`.** When `--platform` resolves to OpenCode (or `all` and OpenCode would be included), `mem` prints a one-line "reader unavailable" notice and continues with the other platforms. Don't promise OpenCode coverage in your reply until the adapter ships.
-- **`--phase` slicing depends on `task.py create` / `task.py start` invocations appearing in the recorded bash calls of the session.** Sessions where the user ran `task.py` from a different terminal — outside the recorded AI loop — will not have phase boundaries. `--phase all` is the safe fallback.
-- **`mem` indexes platform JSONL files directly.** If the user has cleared their Claude / Codex / Pi session storage, `mem` cannot recover what is no longer on disk.
-- **`mem` is read-only.** No remote sync, no edits to platform JSONL. Any write you do based on `mem` findings is your own follow-up call into the editing tools available to you.
+- **OpenCode 适配器在 `0.6.0-beta.*` 上为桩实现。** 当 `--platform` 解析为 OpenCode（或 `all` 且包含 OpenCode）时，`mem` 会打印一行"reader unavailable"通知并继续处理其他平台。在适配器正式发布之前，不要在回复中承诺 OpenCode 覆盖。
+- **`--phase` 切片依赖于会话记录的命令行调用中出现 `task.py create` / `task.py start`。** 如果用户在 AI 循环之外的其他终端中运行了 `task.py`，则这些会话不会有阶段边界。`--phase all` 是安全的回退方案。
+- **`mem` 直接索引平台的 JSONL 文件。** 如果用户清除了 Claude / Codex / Pi 的会话存储，`mem` 无法恢复磁盘上已不存在的数据。
+- **`mem` 是只读的。** 没有远程同步，不会编辑平台 JSONL。你基于 `mem` 发现所做的任何写入操作，都是你自己对可用编辑工具的后续调用。
 
-## When you need more than this reference
+## 当需要超出本参考的内容时
 
-Run `cviauto mem help` in the user's shell. The runtime help is authoritative and will be ahead of this reference during fast-moving beta releases.
+在用户的 shell 中运行 `cviauto mem help`。运行时帮助是权威的，在快速迭代的 beta 版本中会领先于本参考文档。