diff --git a/CATALOG.zh-CN.md b/CATALOG.zh-CN.md
index 3d32e80..9cdc37c 100644
--- a/CATALOG.zh-CN.md
+++ b/CATALOG.zh-CN.md
@@ -10,11 +10,11 @@
 | --- | --- |
 | 集合 | Personal Skills Collection |
 | 包数量 | 5 个第一方 Skill |
-| 当前状态 | v0.1.1 已发布；独立 `review-loop agent-skill` acceptance 仍为 BLOCKED |
+| 当前状态 | v0.1.1 已发布且可安装；独立 `review-loop agent-skill` 证据仍为 `BLOCKED` |
 | 稳定版本 | [v0.1.1](https://github.com/LightDevCoder/skills/releases/tag/v0.1.1) |
 | 安装权威 | [docs/INSTALLATION.zh-CN.md](docs/INSTALLATION.zh-CN.md) |
 | 发现检查 | [collection-discovery-tests.ps1](tests/collection-discovery-tests.ps1) |
-| 证据 | [v0.1.1 release evidence](docs/evidence/releases/v0.1.1/) |
+| 证据 | [v0.1.1 发布证据](docs/evidence/releases/v0.1.1/RELEASE_RECEIPT.zh-CN.md) |
 
 ## 已准入 Skill
 
@@ -30,7 +30,7 @@
 ### project-init
 
 - **作用：** 从最小 preset 初始化项目，保留既有指令并验证结果路径。
-- **调用：** User-invoked only。
+- **调用：** 仅 user-invoked。
 - **包：** [skills/project-init/](skills/project-init/)
 - **状态：** 第一方已准入。
 - **证据：** [package tests](skills/project-init/tests/)；[使用指南](docs/zh-CN/skills/project-init.md)。
@@ -39,7 +39,7 @@
 ### ask-light
 
 - **作用：** 从当前上下文推荐一个下一 Skill 或一个 bounded workflow recipe。
-- **调用：** User-invoked only；永不执行推荐结果。
+- **调用：** 仅 user-invoked；永不执行推荐结果。
 - **包：** [skills/ask-light/](skills/ask-light/)
 - **状态：** 第一方已准入；支持显式 `next` 和 `workflow` 模式。
 - **证据：** [scanner tests](skills/ask-light/tests/)；[使用指南](docs/zh-CN/skills/ask-light.md)。
@@ -48,7 +48,7 @@
 ### learn-anything
 
 - **作用：** 将证据充分的对话、笔记、workflow 或资料转成可复用 Agent Skill 方法。
-- **调用：** User-invoked only。
+- **调用：** 仅 user-invoked。
 - **包：** [skills/learn-anything/](skills/learn-anything/)
 - **状态：** 第一方已准入；保留 source-sufficiency 与 deterministic package-build 边界。
 - **证据：** [package contract](skills/learn-anything/SKILL.md)；[使用指南](docs/zh-CN/skills/learn-anything.md)。
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 1c3ac9f..c2dccf4 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -38,8 +38,11 @@ drafted.
   [INSTALLATION_VERIFICATION.md](docs/evidence/releases/v0.1.1/INSTALLATION_VERIFICATION.md).
 - Structural and package evidence:
   [TEST_SUMMARY.md](docs/evidence/releases/v0.1.1/TEST_SUMMARY.md).
-- Independent `review-loop agent-skill` acceptance remains `BLOCKED`; see
-  [release receipt](docs/evidence/releases/v0.1.1/RELEASE_RECEIPT.md).
+- The five-package collection remains installable and its collection-quality
+  checks passed. Independent evaluator evidence for the `review-loop
+  agent-skill` acceptance gate remains `BLOCKED`; this does not block ordinary
+  installation or use. See the [release receipt](docs/evidence/releases/v0.1.1/RELEASE_RECEIPT.md)
+  for the exact evidence boundary.
 
 ## 0.1.0 — 2026-07-23
 
diff --git a/CHANGELOG.zh-CN.md b/CHANGELOG.zh-CN.md
index 5aec210..55e1674 100644
--- a/CHANGELOG.zh-CN.md
+++ b/CHANGELOG.zh-CN.md
@@ -24,9 +24,11 @@
 - 合并后的 release commit 上 GitHub Actions `collection-quality`：`PASS`。
 - 整仓和单 Skill fresh install：使用 CLI `1.5.20`，均为 `PASS`。
 - GitHub release：https://github.com/LightDevCoder/skills/releases/tag/v0.1.1
-- 整仓与单 Skill fresh-install 目标记录：[INSTALLATION_VERIFICATION.md](docs/evidence/releases/v0.1.1/INSTALLATION_VERIFICATION.md)。
-- 结构与包测试证据：[TEST_SUMMARY.md](docs/evidence/releases/v0.1.1/TEST_SUMMARY.md)。
-- 独立 `review-loop agent-skill` acceptance 仍为 `BLOCKED`；见[发布收据](docs/evidence/releases/v0.1.1/RELEASE_RECEIPT.md)。
+- 整仓与单 Skill fresh-install 目标记录：[INSTALLATION_VERIFICATION.zh-CN.md](docs/evidence/releases/v0.1.1/INSTALLATION_VERIFICATION.zh-CN.md)。
+- 结构与包测试证据：[TEST_SUMMARY.zh-CN.md](docs/evidence/releases/v0.1.1/TEST_SUMMARY.zh-CN.md)。
+- 五个包组成的集合仍可安装，`collection-quality` 检查已通过。`review-loop
+  agent-skill` acceptance gate 的独立 evaluator 证据仍为 `BLOCKED`；这不影响
+  一般安装或使用。准确证据边界见[发布收据](docs/evidence/releases/v0.1.1/RELEASE_RECEIPT.zh-CN.md)。
 
 ## 0.1.0 — 2026-07-23
 
diff --git a/README.md b/README.md
index 6bdfb25..e357a7e 100644
--- a/README.md
+++ b/README.md
@@ -14,8 +14,13 @@ invocation boundary, and small enough to inspect before use.
 > is published from commit `c50f1ef`. The release record and fresh-install evidence
 > live in [docs/evidence/releases/v0.1.1/](docs/evidence/releases/v0.1.1/).
 >
-> Independent `review-loop agent-skill` acceptance remains `BLOCKED`; see the
-> receipt for the exact boundary.
+> **Release status:** The collection is published and usable. Installation and
+> `collection-quality` checks passed for all five first-party Skills. The
+> remaining release-acceptance limitation is the independent evaluator evidence
+> for the `review-loop agent-skill` gate: that evidence is `BLOCKED` because a
+> fresh independent evaluator record is not attached. This does not block
+> installation or ordinary use; see the [release receipt](docs/evidence/releases/v0.1.1/RELEASE_RECEIPT.md)
+> and [limitations](docs/evidence/releases/v0.1.1/LIMITATIONS.md) for the detailed boundary.
 
 ## Quick Start
 
@@ -57,6 +62,31 @@ result. Read [Quick Start](examples/quick-start/README.md), the [Skill user
 guides](docs/skills/), and [workflow recipes](docs/workflows/) for inputs,
 outputs, handoffs, and stopping boundaries.
 
+## External capabilities
+
+The five packages above are the core collection: installing this repository
+provides all five first-party Skills listed in the catalog.
+
+Optional workflow capabilities are external or third-party dependencies and are
+not included by default:
+
+- `grill-me` / `grilling` — `grill-me` is the user-facing entry point for a
+  one-session clarification interview; it starts the underlying model-invoked
+  `grilling` capability. Treat them as one capability, not two workflow steps.
+- `research` — investigate an external fact or practice when a local preset is
+  insufficient.
+- `to-spec` — turn an approved goal and constraints into a traceable
+  specification.
+- `to-tickets` — turn an approved specification into dependency-ordered
+  tickets.
+- `implement` — carry out one bounded, unblocked implementation ticket.
+- `code-review` — provide specialist findings for a fixed change.
+- `handoff` — preserve an accepted result or blocker for closeout or resumption.
+
+These capabilities may come from `mattpocock/skills` or another external
+source. This repository does not copy them or install them automatically;
+check their availability before selecting a workflow that names them.
+
 ## First-party catalog
 
 | Skill | Purpose | Invocation | Package |
diff --git a/README.zh-CN.md b/README.zh-CN.md
index f611c6a..d6823de 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -6,13 +6,18 @@
 
 `LightDevCoder/skills` 是公开的第一方 Agent Skills 集合，包含五个可以独立安装、独立发现、明确声明调用边界的 Skill。包内 `SKILL.md` 仍是行为权威；本 README 与用户指南负责说明使用方式。
 
-> **About：** Personal Skills Collection — Drive your creativity
+> **简介：** Personal Skills Collection — Drive your creativity
 
-> **Release：** [v0.1.1](https://github.com/LightDevCoder/skills/releases/tag/v0.1.1)
+> **发布：** [v0.1.1](https://github.com/LightDevCoder/skills/releases/tag/v0.1.1)
 > 已从 commit `c50f1ef` 发布。发布记录和 fresh-install 证据见
 > [docs/evidence/releases/v0.1.1/](docs/evidence/releases/v0.1.1/)。
 >
-> 独立 `review-loop agent-skill` acceptance 仍为 `BLOCKED`；准确边界见发布收据。
+> **发布状态：** 集合已发布且可使用。五个第一方 Skill 的安装与
+> `collection-quality` 检查均已通过。当前剩余的发布验收限制是
+> `review-loop agent-skill` 的独立 evaluator 证据：由于尚未附上 fresh
+> independent evaluator record，该项仍为 `BLOCKED`。这不影响安装或一般使用；
+> 详细边界见[发布收据](docs/evidence/releases/v0.1.1/RELEASE_RECEIPT.zh-CN.md)
+> 和[限制说明](docs/evidence/releases/v0.1.1/LIMITATIONS.zh-CN.md)。
 
 ## Quick Start
 
@@ -28,7 +33,7 @@ npx skills add LightDevCoder/skills#v0.1.1 --yes --copy --agent codex
 npx skills add LightDevCoder/skills#v0.1.1 --skill review-loop --yes --copy --agent codex
 ```
 
-刷新 Agent host，然后在其 Skill catalog 中确认发现结果。若 host 提供文件系统，检查已安装包的 `SKILL.md` 与 `agents/openai.yaml`；脱离 source checkout 后仍能发现，才是有意义的验证。CLI 版本、destination 和结果见 [INSTALLATION_VERIFICATION.md](docs/evidence/releases/v0.1.1/INSTALLATION_VERIFICATION.md)。
+刷新 Agent host，然后在其 Skill catalog 中确认发现结果。若 host 提供文件系统，检查已安装包的 `SKILL.md` 与 `agents/openai.yaml`；脱离 source checkout 后仍能发现，才是有意义的验证。CLI 版本、destination 和结果见 [INSTALLATION_VERIFICATION.zh-CN.md](docs/evidence/releases/v0.1.1/INSTALLATION_VERIFICATION.zh-CN.md)。
 
 第一次不知道下一步时，推荐显式调用 `$ask-light`：
 
@@ -39,21 +44,38 @@ $ask-light next
 三个最短示例：
 
 ```text
-$ask-light next       # 推荐下一 Skill，不执行它
+$ask-light next       # 推荐下一 Skill，不执行
 $project-init         # 初始化已确认的最小项目 preset
 $review-loop init     # 冻结已有验收标准的 baseline
 ```
 
-`ask-light` 只返回建议或一个有边界的 recipe，然后停止；不会执行、安装或自动串联。阅读 [Quick Start](examples/quick-start/README.zh-CN.md)、[Skill 使用指南](docs/zh-CN/skills/)、[workflow recipes](docs/zh-CN/workflows/) 了解输入、输出、handoff 和停止点。
+`ask-light` 只返回建议或一个有边界的 recipe，然后停止；不会执行、安装或自动串联。阅读 [Quick Start](examples/quick-start/README.zh-CN.md)、[Skill 使用指南](docs/zh-CN/skills/)、[工作流 recipes](docs/zh-CN/workflows/) 了解输入、输出、handoff 和停止点。
+
+## 外部能力（External Capabilities）
+
+上面的五个包组成 Core collection：安装本仓库后即可使用目录中的五个第一方 Skill。
+
+以下是可选的 workflow 能力，来自外部或第三方来源，不属于默认集合：
+
+- `grill-me` / `grilling`：`grill-me` 是一次会话澄清访谈的用户入口，会启动底层的 model-invoked `grilling` 能力。应把它们视为同一个能力，不要当成两个重复的工作流步骤。
+- `research`：本地 preset 不足时，用于调查外部事实或实践。
+- `to-spec`：把已确认的目标和约束整理成可追踪的 specification。
+- `to-tickets`：把已批准的 specification 整理成按依赖排序的 tickets。
+- `implement`：执行一个有边界且未被阻塞的 implementation ticket。
+- `code-review`：为固定变更提供 specialist findings。
+- `handoff`：为 closeout 或后续 resume 保存已接受结果或 blocker。
+
+这些能力可能来自 `mattpocock/skills` 或其他外部来源。本仓库不复制这些 Skill，
+也不会自动安装；选择包含它们的 workflow 前，请先确认当前 host 能看到对应能力。
 
 ## 第一方目录
 
 | Skill | 作用 | 调用方式 | 包路径 |
 | --- | --- | --- | --- |
 | [review-loop](skills/review-loop/SKILL.md) | 执行有边界的证据、修复和最终验收循环。 | Model-invoked；支持手动入口。 | skills/review-loop/ |
-| [project-init](skills/project-init/SKILL.md) | 从最小 preset 初始化已确认的软件、文稿、研究、知识、数据或 Skill-development 项目。 | User-invoked only。 | skills/project-init/ |
-| [ask-light](skills/ask-light/SKILL.md) | 检查 host 并推荐一个下一 Skill 或 bounded recipe，不执行建议。 | User-invoked only。 | skills/ask-light/ |
-| [learn-anything](skills/learn-anything/SKILL.md) | 从有足够证据的资料中提炼可复用 Agent Skill 方法。 | User-invoked only。 | skills/learn-anything/ |
+| [project-init](skills/project-init/SKILL.md) | 从最小 preset 初始化已确认的软件、文稿、研究、知识、数据或 Skill-development 项目。 | 仅 user-invoked。 | skills/project-init/ |
+| [ask-light](skills/ask-light/SKILL.md) | 检查 host 并推荐一个下一 Skill 或 bounded recipe，不执行建议。 | 仅 user-invoked。 | skills/ask-light/ |
+| [learn-anything](skills/learn-anything/SKILL.md) | 从有足够证据的资料中提炼可复用 Agent Skill 方法。 | 仅 user-invoked。 | skills/learn-anything/ |
 | [manuscript-ops](skills/manuscript-ops/SKILL.md) | 治理跨格式、批次、审查和 handoff 的可复现文稿工程。 | Model-invoked；支持手动入口。 | skills/manuscript-ops/ |
 
 完整目录见 [CATALOG.zh-CN.md](CATALOG.zh-CN.md)。组合示例是文档和验证资产，不是固定 pipeline，也不是自动编排器；退休的 `project-workflow` 不会重新引入。
diff --git a/docs/INSTALLATION.zh-CN.md b/docs/INSTALLATION.zh-CN.md
index c648f03..514fe26 100644
--- a/docs/INSTALLATION.zh-CN.md
+++ b/docs/INSTALLATION.zh-CN.md
@@ -2,7 +2,7 @@
 
 [English installation guide](INSTALLATION.md)
 
-公开第一方集合当前稳定版本是 [v0.1.1](https://github.com/LightDevCoder/skills/releases/tag/v0.1.1)，commit 为 `c50f1ef403a5f0bfe02e75d1aeff2c237556db63`。已发布 tag 的 fresh-install 证据见[release evidence](evidence/releases/v0.1.1/)。`skills/<name>/` 内的包契约仍是行为权威；本页只规定安装和验证证据。
+公开第一方集合当前稳定版本是 [v0.1.1](https://github.com/LightDevCoder/skills/releases/tag/v0.1.1)，commit 为 `c50f1ef403a5f0bfe02e75d1aeff2c237556db63`。已发布 tag 的 fresh-install 证据见[发布证据](evidence/releases/v0.1.1/RELEASE_RECEIPT.zh-CN.md)。`skills/<name>/` 内的包契约仍是行为权威；本页只规定安装和验证证据。
 
 ## Revision 语义
 
@@ -30,7 +30,7 @@ npx skills add LightDevCoder/skills#v0.1.1 --yes --copy --agent codex
 npx skills add LightDevCoder/skills#v0.1.1 --skill review-loop --yes --copy --agent codex
 ```
 
-第一条安装五个包，第二条选择同一 tag 下的完整单包。已验证的 CLI version、destination 类别、discovery 和 smoke result 见 [v0.1.1 安装记录](evidence/releases/v0.1.1/INSTALLATION_VERIFICATION.md)。
+第一条安装五个包，第二条选择同一 tag 下的完整单包。已验证的 CLI version、destination 类别、discovery 和 smoke result 见 [v0.1.1 安装记录](evidence/releases/v0.1.1/INSTALLATION_VERIFICATION.zh-CN.md)。
 
 ## 安装范围
 
diff --git a/docs/MAINTENANCE.zh-CN.md b/docs/MAINTENANCE.zh-CN.md
index 87fd966..b7bdfc7 100644
--- a/docs/MAINTENANCE.zh-CN.md
+++ b/docs/MAINTENANCE.zh-CN.md
@@ -14,10 +14,10 @@
 
 新增、更新、改名、弃用或移除时：
 
-1. 先执行 [Skill 准入](SKILL_ADMISSION.md) 的 reuse-before-invention 与 ownership gate。
+1. 先执行 [Skill 准入](SKILL_ADMISSION.zh-CN.md) 的 reuse-before-invention 与 ownership gate。
 2. 保留包边界、invocation direction、attribution 和必要资源。
 3. 收集 structural、fresh-install、behavioral、invocation、script 和 review evidence，并准确标注 evidence class。
-4. 执行 [review policy](REVIEW_POLICY.md) 的 review trigger。
+4. 执行[审查策略](REVIEW_POLICY.zh-CN.md)的 review trigger。
 5. 同步 README、目录、安装说明、治理链接、affected recipes、discovery tests、attribution 和 changelog。
 6. 未通过真实 release gate 前，不把版本、tag 或安装命令写成已验证。
 
diff --git a/docs/evidence/releases/v0.1.1/RELEASE_RECEIPT.zh-CN.md b/docs/evidence/releases/v0.1.1/RELEASE_RECEIPT.zh-CN.md
index c298fca..157b729 100644
--- a/docs/evidence/releases/v0.1.1/RELEASE_RECEIPT.zh-CN.md
+++ b/docs/evidence/releases/v0.1.1/RELEASE_RECEIPT.zh-CN.md
@@ -19,15 +19,15 @@ Actions 和 fresh-install 证据已核验；独立 `review-loop agent-skill` acc
 
 ## 证据
 
-- 结构与 discovery：[DISCOVERY_VERIFICATION.md](DISCOVERY_VERIFICATION.md)
-- 包与集合测试：[TEST_SUMMARY.md](TEST_SUMMARY.md)
-- Fresh install 与 host discovery：[INSTALLATION_VERIFICATION.md](INSTALLATION_VERIFICATION.md)
-- 限制和 evidence labels：[LIMITATIONS.md](LIMITATIONS.md)
-- [审查策略](../../../REVIEW_POLICY.md)
-- [准入契约](../../../SKILL_ADMISSION.md)
-
-| Fresh whole-repository install | `VERIFIED` | 见 [INSTALLATION_VERIFICATION.md](INSTALLATION_VERIFICATION.md)。 |
-| Fresh per-Skill install | `VERIFIED` | 见 [INSTALLATION_VERIFICATION.md](INSTALLATION_VERIFICATION.md)。 |
+- 结构与 discovery：[DISCOVERY_VERIFICATION.zh-CN.md](DISCOVERY_VERIFICATION.zh-CN.md)
+- 包与集合测试：[TEST_SUMMARY.zh-CN.md](TEST_SUMMARY.zh-CN.md)
+- Fresh install 与 host discovery：[INSTALLATION_VERIFICATION.zh-CN.md](INSTALLATION_VERIFICATION.zh-CN.md)
+- 限制和 evidence labels：[LIMITATIONS.zh-CN.md](LIMITATIONS.zh-CN.md)
+- [审查策略](../../../REVIEW_POLICY.zh-CN.md)
+- [准入契约](../../../SKILL_ADMISSION.zh-CN.md)
+
+| Fresh whole-repository install | `VERIFIED` | 见 [INSTALLATION_VERIFICATION.zh-CN.md](INSTALLATION_VERIFICATION.zh-CN.md)。 |
+| Fresh per-Skill install | `VERIFIED` | 见 [INSTALLATION_VERIFICATION.zh-CN.md](INSTALLATION_VERIFICATION.zh-CN.md)。 |
 | Independent `review-loop agent-skill` acceptance | `BLOCKED` | 等待 fresh independent evaluator 记录；同一上下文不是独立证据。 |
 | GitHub Actions | `VERIFIED` | 合并后的 release commit 上的 workflow 已通过。 |
 
diff --git a/docs/evidence/releases/v0.1.1/TEST_SUMMARY.zh-CN.md b/docs/evidence/releases/v0.1.1/TEST_SUMMARY.zh-CN.md
index 36b9103..22dc686 100644
--- a/docs/evidence/releases/v0.1.1/TEST_SUMMARY.zh-CN.md
+++ b/docs/evidence/releases/v0.1.1/TEST_SUMMARY.zh-CN.md
@@ -17,7 +17,7 @@
 | Quick Start | `powershell -File tests/quick-start-smoke-tests.ps1` | `PASS`；8 条断言。 |
 | Python 语法 | 只读 `ast.parse` 检查 | `PASS`；12 个 Python 文件解析通过且不写入字节码。 |
 | Python `compileall` | `python -m compileall -q skills tests` | 本地 `NOT PASSED`；沙箱拒绝写入现有受保护的 `__pycache__`，但合并 release commit `c50f1ef` 上的 GitHub Actions 同命令已通过。 |
-| Tagged fresh install | `npx skills add LightDevCoder/skills#v0.1.1 ...` 加 `npx skills list` | `PASS`；CLI `1.5.20`，整仓 destination 列出 5 个包，单 Skill destination 列出 `review-loop`，且两个 source checkout 都不存在。见[安装证据](INSTALLATION_VERIFICATION.md)。 |
+| Tagged fresh install | `npx skills add LightDevCoder/skills#v0.1.1 ...` 加 `npx skills list` | `PASS`；CLI `1.5.20`，整仓 destination 列出 5 个包，单 Skill destination 列出 `review-loop`，且两个 source checkout 都不存在。见[安装证据](INSTALLATION_VERIFICATION.zh-CN.md)。 |
 | Release-commit CI | GitHub Actions `collection-quality` | `PASS`；run `30189210521` 对应 `c50f1ef403a5f0bfe02e75d1aeff2c237556db63`。 |
 
 包测试只证明覆盖到的 contract 场景；collection discovery 只证明 cross-reference 和 metadata 一致。tagged installation 证据另有记录；这些证据都不能证明 independent acceptance 或模型介导的 runtime 行为。
diff --git a/docs/skills/manuscript-ops.md b/docs/skills/manuscript-ops.md
index 859ac8a..555f8ee 100644
--- a/docs/skills/manuscript-ops.md
+++ b/docs/skills/manuscript-ops.md
@@ -38,8 +38,10 @@ records, review evidence, and production QA records.
 ## Handoffs, success, and `BLOCKED`
 
 On a Project route, choose one discovery handoff: `grill-me` for one-session
-decisions or `wayfinder` for multi-session uncertainty, then stop. Continue
-only after the user explicitly resumes `manuscript-ops`. Before initialization,
+decisions or `wayfinder` for multi-session uncertainty, then stop. `grill-me`
+is the user-facing entry point; its underlying model-invoked capability is
+`grilling`, so it is one clarification capability rather than two user steps.
+Continue only after the user explicitly resumes `manuscript-ops`. Before initialization,
 the user must explicitly choose `project-init`; before review, an approved
 `review-loop` Charter is required. `BLOCKED` is correct for a missing root,
 missing dependency, unapproved brief, absent capability, missing evidence, or
diff --git a/docs/skills/project-init.md b/docs/skills/project-init.md
index 51dbbba..c7621f7 100644
--- a/docs/skills/project-init.md
+++ b/docs/skills/project-init.md
@@ -25,8 +25,9 @@ defaults to the current directory. Before writing, it reads root
 `AGENTS.md`/`CLAUDE.md`, README, manifests, project documents, and current
 status. It needs the project type, visible goal, outputs, collaboration mode,
 constraints, and required review level, either from the brief or from its
-short questions. `grilling` may help answer missing questions; it does not
-authorize additional writes.
+short questions. Use the external user-facing `grill-me` entry point when a
+question needs a clarification interview; its underlying model-invoked
+capability is `grilling`. This does not authorize additional writes.
 
 ```text
 $project-init
diff --git a/docs/workflows/recipes.md b/docs/workflows/recipes.md
index 3be6211..85de26d 100644
--- a/docs/workflows/recipes.md
+++ b/docs/workflows/recipes.md
@@ -18,6 +18,10 @@ authority for every package.
 - **Private modified third-party:** a package in `skills-3rdParty`; an absent
   private root is an availability gap, not an invitation to invent a fallback.
 
+`grill-me` is the user-facing entry point for one-session clarification. It
+starts the underlying model-invoked `grilling` capability; treat them as one
+external capability, not two separate user-facing workflow steps.
+
 Each row declares the handoff artifact and stop condition. `user-invoked` means
 the user must explicitly select the Skill; `model-invoked` means the host may
 call it under its package policy. Findings from a specialist never become the
diff --git a/docs/zh-CN/skills/ask-light.md b/docs/zh-CN/skills/ask-light.md
index d041d52..1f7eff6 100644
--- a/docs/zh-CN/skills/ask-light.md
+++ b/docs/zh-CN/skills/ask-light.md
@@ -1,6 +1,6 @@
 # `ask-light` 使用指南
 
-[English guide](../../skills/ask-light.md)
+[英文指南](../../skills/ask-light.md)
 
 行为与 scanner 输出契约见 [skills/ask-light/SKILL.md](../../../skills/ask-light/SKILL.md) 和 [discovery contract](../../../skills/ask-light/references/discovery-contract.md)。
 
diff --git a/docs/zh-CN/skills/learn-anything.md b/docs/zh-CN/skills/learn-anything.md
index c979b69..24dafcd 100644
--- a/docs/zh-CN/skills/learn-anything.md
+++ b/docs/zh-CN/skills/learn-anything.md
@@ -1,6 +1,6 @@
 # `learn-anything` 使用指南
 
-[English guide](../../skills/learn-anything.md)
+[英文指南](../../skills/learn-anything.md)
 
 唯一行为权威是 [skills/learn-anything/SKILL.md](../../../skills/learn-anything/SKILL.md)。
 
diff --git a/docs/zh-CN/skills/manuscript-ops.md b/docs/zh-CN/skills/manuscript-ops.md
index 333e6d7..02a63b6 100644
--- a/docs/zh-CN/skills/manuscript-ops.md
+++ b/docs/zh-CN/skills/manuscript-ops.md
@@ -1,6 +1,6 @@
 # `manuscript-ops` 使用指南
 
-[English guide](../../skills/manuscript-ops.md)
+[英文指南](../../skills/manuscript-ops.md)
 
 完整行为契约见 [skills/manuscript-ops/SKILL.md](../../../skills/manuscript-ops/SKILL.md)。
 
@@ -25,7 +25,7 @@ $manuscript-ops resume
 
 ## Handoff、成功和 `BLOCKED`
 
-Project route 先按需要选择一个 discovery handoff：单会话决策用 `grill-me`，多会话不确定性用 `wayfinder`，随后停止；只有用户显式 resume 才能继续。初始化前需用户显式选择 `project-init`，review 前需批准的 `review-loop` Charter。root、dependency、brief、capability、证据或真实渲染/round-trip proof 缺失时返回 `BLOCKED`，不能把语法有效当成视觉验收。
+Project route 先按需要选择一个 discovery handoff：单会话决策用 `grill-me`，多会话不确定性用 `wayfinder`，随后停止。`grill-me` 是用户入口，底层的 model-invoked 能力是 `grilling`；二者是同一个澄清能力，不是两个用户步骤。只有用户显式 resume 才能继续。初始化前需用户显式选择 `project-init`，review 前需批准的 `review-loop` Charter。root、dependency、brief、capability、证据或真实渲染/round-trip proof 缺失时返回 `BLOCKED`，不能把语法有效当成视觉验收。
 
 ## 组合和最终权威
 
diff --git a/docs/zh-CN/skills/project-init.md b/docs/zh-CN/skills/project-init.md
index 210bfa0..9855e60 100644
--- a/docs/zh-CN/skills/project-init.md
+++ b/docs/zh-CN/skills/project-init.md
@@ -1,6 +1,6 @@
 # `project-init` 使用指南
 
-[English guide](../../skills/project-init.md)
+[英文指南](../../skills/project-init.md)
 
 行为权威是 [skills/project-init/SKILL.md](../../../skills/project-init/SKILL.md)。
 
@@ -20,7 +20,7 @@ $project-init
 
 ## 前置条件、输入和输出
 
-默认目标是当前目录。写入前读取根部 `AGENTS.md`/`CLAUDE.md`、README、manifest、项目文档和当前状态。输入包括项目类型、用户目标、输出物、协作方式、约束和 review level；已有 brief 能回答时不重复询问。`grilling` 只能帮助澄清问题，不能授权额外写入。
+默认目标是当前目录。写入前读取根部 `AGENTS.md`/`CLAUDE.md`、README、manifest、项目文档和当前状态。输入包括项目类型、用户目标、输出物、协作方式、约束和 review level；已有 brief 能回答时不重复询问。需要澄清问题时使用外部的用户入口 `grill-me`；它启动底层 model-invoked 能力 `grilling`。这不能授权额外写入。
 
 输出包括 preset 或已确认的 fallback、唯一 instruction target、变更路径、能力可用性、验证结果和后续 Skill 建议；不得创建 tickets、implementation plan、final-review record 或竞争性的 specification。
 
diff --git a/docs/zh-CN/skills/review-loop.md b/docs/zh-CN/skills/review-loop.md
index 865ccc2..0bbc930 100644
--- a/docs/zh-CN/skills/review-loop.md
+++ b/docs/zh-CN/skills/review-loop.md
@@ -1,6 +1,6 @@
 # `review-loop` 使用指南
 
-[English guide](../../skills/review-loop.md)
+[英文指南](../../skills/review-loop.md)
 
 行为权威仍是 [skills/review-loop/SKILL.md](../../../skills/review-loop/SKILL.md)；本页只说明如何使用，不复制第二份契约。
 
@@ -36,4 +36,4 @@ $review-loop resume
 
 ## 安装与发现验证
 
-对于已发布的 v0.1.1，使用 `npx skills add LightDevCoder/skills#v0.1.1 --skill review-loop` 安装，刷新 host，在不依赖 source checkout 的情况下检查已发现的 `SKILL.md` 和 `agents/openai.yaml`。运行 [Profile tests](../../../skills/review-loop/tests/)；结果记录在 [安装证据](../../evidence/releases/v0.1.1/INSTALLATION_VERIFICATION.md)。
+对于已发布的 v0.1.1，使用 `npx skills add LightDevCoder/skills#v0.1.1 --skill review-loop` 安装，刷新 host，在不依赖 source checkout 的情况下检查已发现的 `SKILL.md` 和 `agents/openai.yaml`。运行 [Profile tests](../../../skills/review-loop/tests/)；结果记录在[安装证据](../../evidence/releases/v0.1.1/INSTALLATION_VERIFICATION.zh-CN.md)。
diff --git a/docs/zh-CN/workflows/README.md b/docs/zh-CN/workflows/README.md
index 6cbd527..592e220 100644
--- a/docs/zh-CN/workflows/README.md
+++ b/docs/zh-CN/workflows/README.md
@@ -1,12 +1,12 @@
 # 已验证组合示例
 
-[English workflow examples](../../workflows/README.md)
+[英文版 workflow examples](../../workflows/README.md)
 
 这里的文档用于展示 Skill 之间的安全组合、调用边界、停止点和证据。它们不是准入 gate、canonical workflow 或自动编排器，也不会自动调用其他 user-invoked Skill。
 
 ## 当前示例
 
 - [Ask Light 显式选择下一步](first-party-composition.md)
-- [Workflow recipes](recipes.md)
+- [工作流 recipes](recipes.md)
 
-完整的第一方组合示例见 [English version](../../workflows/first-party-composition.md)；当前五个包的 behavior authority 仍在各自 `SKILL.md`。
+完整的第一方组合示例见[英文版示例](../../workflows/first-party-composition.md)；当前五个包的 behavior authority 仍在各自 `SKILL.md`。外部 workflow 能力不属于本仓库默认安装内容，且不会由这些示例自动安装。
diff --git a/docs/zh-CN/workflows/first-party-composition.md b/docs/zh-CN/workflows/first-party-composition.md
index aaf8f31..ec58fc2 100644
--- a/docs/zh-CN/workflows/first-party-composition.md
+++ b/docs/zh-CN/workflows/first-party-composition.md
@@ -1,6 +1,6 @@
 # Ask Light 显式选择下一步
 
-[English example](../../workflows/first-party-composition.md)
+[英文版示例](../../workflows/first-party-composition.md)
 
 ## 场景
 
@@ -28,6 +28,6 @@ Agent 已有 goal、artifacts、blockers、project type、task kind、availabili
 - 五个包的 `SKILL.md`。
 - [ask-light discovery contract](../../../skills/ask-light/references/discovery-contract.md)。
 - [collection discovery test](../../../tests/collection-discovery-tests.ps1)。
-- [v0.1.1 release evidence](../../evidence/releases/v0.1.1/)。
+- [v0.1.1 发布证据](../../evidence/releases/v0.1.1/RELEASE_RECEIPT.zh-CN.md)。
 
-这是验证资产，不是 canonical workflow 或 admission requirement。
+这是验证资产，不是 canonical workflow 或准入要求。
diff --git a/docs/zh-CN/workflows/recipes.md b/docs/zh-CN/workflows/recipes.md
index d9bc8de..f899e15 100644
--- a/docs/zh-CN/workflows/recipes.md
+++ b/docs/zh-CN/workflows/recipes.md
@@ -1,22 +1,24 @@
-# Workflow Recipes
+# 工作流 Recipes
 
-[English recipes](../../workflows/recipes.md)
+[英文版 recipes](../../workflows/recipes.md)
 
 这些 recipe 是有边界的文档和验证资产，只描述显式 handoff；不会创建 canonical pipeline、永久 state machine 或自动多 Skill orchestrator。每个包的 `SKILL.md` 仍是行为权威。
 
 ## 来源与共同规则
 
-- **First-party：** 本仓库的 `review-loop`、`project-init`、`ask-light`、`learn-anything`、`manuscript-ops`。
-- **Matt upstream：** `mattpocock/skills` 中的 `to-spec`、`to-tickets`、`implement`、`code-review`、`handoff`、`diagnosing-bugs`、`grill-me`、`wayfinder`、`writing-great-skills`，或可见的 pinned third-party package。
-- **Private modified third-party：** `skills-3rdParty` 内的包；私有 root 不可见时必须报告 availability gap，不能编造 fallback。
+- **第一方（First-party）：** 本仓库的 `review-loop`、`project-init`、`ask-light`、`learn-anything`、`manuscript-ops`。
+- **Matt 上游（Matt upstream）：** `mattpocock/skills` 中的 `to-spec`、`to-tickets`、`implement`、`code-review`、`handoff`、`diagnosing-bugs`、`grill-me`、`wayfinder`、`writing-great-skills`，或可见的 pinned third-party package。
+- **私有第三方修改版（Private modified third-party）：** `skills-3rdParty` 内的包；私有 root 不可见时必须报告 availability gap，不能编造 fallback。
 
 每行都写明 handoff artifact 和 stop condition。`user-invoked` 必须由用户显式选择；`model-invoked` 仍受包自身 policy 约束。specialist findings 不能成为最终 verdict；需要验收时由 `review-loop` 拥有 `PASS`、`FAIL`、`BLOCKED`。
 
+`grill-me` 是一次会话澄清的用户入口，会启动底层的 model-invoked `grilling` 能力。二者属于同一个外部能力，不是两个需要用户分别选择的工作流步骤。
+
 ## 1. 软件项目
 
-**Entry condition：** 软件 feature/implementation 的目标、约束和验收方向已经明确。
+**入口条件：** 软件 feature/implementation 的目标、约束和验收方向已经明确。
 
-顺序为 `to-spec`（Matt upstream，user-invoked）→ `review-loop` specification（first-party，model-invoked）→ `to-tickets`（Matt upstream，user-invoked）→ `implement`（Matt upstream，user-invoked）→ `code-review`（Matt upstream，model-invoked，只提供 specialist findings）→ `review-loop` software（first-party，拥有最终 verdict）→ `handoff`（Matt upstream，user-invoked）。每一步的输入、输出、handoff 和 stop condition 见 [English recipe](../../workflows/recipes.md#1-software-feature)。
+顺序为 `to-spec`（Matt upstream，user-invoked）→ `review-loop` specification（first-party，model-invoked）→ `to-tickets`（Matt upstream，user-invoked）→ `implement`（Matt upstream，user-invoked）→ `code-review`（Matt upstream，model-invoked，只提供 specialist findings）→ `review-loop` software（first-party，拥有最终 verdict）→ `handoff`（Matt upstream，user-invoked）。每一步的输入、输出、handoff 和 stop condition 见[英文 recipe](../../workflows/recipes.md#1-software-feature)。
 
 缺少 acceptance authority、上游 Skill、批准 ticket、实现依赖或 independent evaluator 时 `BLOCKED`。证据包括 spec、ticket graph、commit、focused tests、specialist findings、review-loop state/verdict 和 handoff；到 `PASS`/`FAIL`/`BLOCKED` 停止。
 
@@ -26,7 +28,7 @@
 
 ## 3. 文稿项目
 
-顺序为 `manuscript-ops` → 按需选择 `grill-me`/`wayfinder` → `project-init` → `review-loop init` → manuscript production → `review-loop` manuscript Profile。Project route 选择 discovery handoff 后必须停；只有用户显式 `resume` 才能继续。root、dependency、brief、Charter、render/round-trip evidence 缺失时 `BLOCKED`，最终 verdict 归 `review-loop`。
+顺序为 `manuscript-ops` → 按需选择 `grill-me`/`wayfinder` → `project-init` → `review-loop init` → manuscript production → `review-loop` manuscript Profile。这里的 `grill-me` 是用户入口，底层 `grilling` 不作为第二个用户步骤单独选择。Project route 选择 discovery handoff 后必须停；只有用户显式 `resume` 才能继续。root、dependency、brief、Charter、render/round-trip evidence 缺失时 `BLOCKED`，最终 verdict 归 `review-loop`。
 
 ## 4. 从资料提炼 Skill
 
diff --git a/examples/quick-start/README.zh-CN.md b/examples/quick-start/README.zh-CN.md
index e5000b1..081d696 100644
--- a/examples/quick-start/README.zh-CN.md
+++ b/examples/quick-start/README.zh-CN.md
@@ -1,8 +1,10 @@
 # Quick Start 示例
 
-[English version](README.md)
+[英文版](README.md)
 
-这个小示例展示第一方集合的显式选择边界。它是文档 fixture，不是 workflow，也不是已经执行过命令的证明。
+这个小示例展示第一方集合的显式选择边界。它是文档 fixture，不是 workflow，也不是已经执行过命令的证明。理解本页流程不要求先阅读英文版的 `brief.md` 或 `AGENTS.md`；所需上下文已在下面说明。
+
+本示例的上下文是：目标是准备一份有来源支持、可检查的小型文档实验 brief；唯一提供的 artifact 是 `brief.md`，当前没有实现文件；用户尚未批准 specification、ticket graph 或 final acceptance source。第一步只是在 `$ask-light` 与 `$project-init` 之间做显式选择，不授权自动串联或发布。
 
 ## 1. 安装
 
@@ -20,7 +22,7 @@ npx skills add LightDevCoder/skills#v0.1.1 --skill ask-light
 
 ## 2. 查看示例
 
-阅读 [brief.md](brief.md) 和 [AGENTS.md](AGENTS.md)。它们只提供足够让 Agent 选择入口的上下文，不授权写业务代码，也不会静默串联 Skill。
+本页已经包含选择入口所需的上下文，不需要阅读英文文件才能继续。若要核对原始 fixture，可选阅读 [brief.md](brief.md) 和 [AGENTS.md](AGENTS.md)；它们只补充同一边界，不授权写业务代码，也不会静默串联 Skill。
 
 ## 3. 显式调用
 
@@ -30,7 +32,7 @@ $project-init
 $review-loop init using brief.md
 ```
 
-只选择与当前状态匹配的命令。预期结果是可检查的建议、最小初始化报告或 review Charter/state。下面是 Illustrative output / 示意输出，不代表本仓库已经运行：
+只选择与当前状态匹配的命令。预期结果是可检查的建议、最小初始化报告或 review Charter/state。以下是 Illustrative output（示意输出），不代表本仓库已经运行：
 
 ```text
 Status: RECOMMEND
@@ -39,4 +41,4 @@ Execution: recommendation only; nothing was invoked, installed, or orchestrated
 
 ## 4. 停止并 handoff
 
-`$ask-light` 后停止并等待用户选择；`$project-init` 后在 discovery/specification/implementation/final review 前停止；`$review-loop` 后在持久化的 `PASS`、`FAIL` 或 `BLOCKED` verdict 停止。stop after each handoff / 每个 handoff 后停止。更长的组合见 [workflow recipes](../../docs/zh-CN/workflows/recipes.md)，真实 release 验证见 [fresh-install evidence](../../docs/evidence/releases/v0.1.1/INSTALLATION_VERIFICATION.md)。
+`$ask-light` 后停止并等待用户选择；`$project-init` 后在 discovery/specification/implementation/final review 前停止；`$review-loop` 后在持久化的 `PASS`、`FAIL` 或 `BLOCKED` verdict 停止。每个 handoff 后都要停止并保留状态。更长的组合见[工作流 recipes](../../docs/zh-CN/workflows/recipes.md)，真实 release 验证见[安装证据](../../docs/evidence/releases/v0.1.1/INSTALLATION_VERIFICATION.zh-CN.md)。
diff --git a/skills/manuscript-ops/SKILL.md b/skills/manuscript-ops/SKILL.md
index f015195..8c3d004 100644
--- a/skills/manuscript-ops/SKILL.md
+++ b/skills/manuscript-ops/SKILL.md
@@ -5,6 +5,10 @@ description: Route and govern manuscript engineering from small notes and struct
 
 # Manuscript Ops
 
+For one-session clarification, `grill-me` is the external user-facing entry
+point and `grilling` is its underlying model-invoked capability. Treat them as
+one discovery handoff, not two separate user-facing steps.
+
 Treat the manuscript as a governed state machine, not a single editable file.
 Keep source authority, user decisions, reproducible generation, review evidence,
 and human gates visible throughout the work.
diff --git a/skills/manuscript-ops/references/handoffs.md b/skills/manuscript-ops/references/handoffs.md
index ab749f1..b96134c 100644
--- a/skills/manuscript-ops/references/handoffs.md
+++ b/skills/manuscript-ops/references/handoffs.md
@@ -18,7 +18,8 @@ contract as well. Do not use `--audit-all` in an ordinary manuscript handoff;
 it changes audit scope, not the selected workflow branch.
 
 Use `--strict-agent-skills` on a client that rejects non-standard frontmatter.
-The pinned `grill-me` and `wayfinder` contracts currently use
+The pinned `grill-me` user entry starts the underlying `grilling` capability;
+the `grill-me` and `wayfinder` contracts currently use
 `disable-model-invocation`; a strict client must return `BLOCKED` unless it has
 compatible releases or an explicit host extension.
 
@@ -109,8 +110,9 @@ $manuscript-ops resume from <exact-project-root>/.review-loop/state.md
 
 Install and refresh the agent between layers when necessary:
 
-1. Required discovery closure from `mattpocock/skills`: `grill-me`, `grilling`,
-   `wayfinder`, and `domain-modeling`.
+1. Required discovery closure from `mattpocock/skills`: `grill-me` (the user
+   entry), its underlying `grilling` capability, `wayfinder`, and
+   `domain-modeling`.
 2. Optional Wayfinder branches, before they are selected: `prototype` and
    `setup-matt-pocock-skills`.
 3. Independent acceptance from `LightDevCoder/Agent-Workflow`:
diff --git a/skills/project-init/SKILL.md b/skills/project-init/SKILL.md
index 78a0781..76c3178 100644
--- a/skills/project-init/SKILL.md
+++ b/skills/project-init/SKILL.md
@@ -32,8 +32,9 @@ Skill is a reportable capability gap, not a reason to invent a command.
 
 ### 2. Ask lightweight project questions
 
-Use `grilling` as a model-invoked capability when answers are not already
-explicit. Ask one short question at a time and capture six answers:
+Use the external user-facing `grill-me` entry point when answers are not
+already explicit. `grill-me` starts the underlying model-invoked `grilling`
+capability; treat this as one clarification capability. Ask one short question at a time and capture six answers:
 
 1. project type;
 2. user-visible goal;
@@ -109,6 +110,7 @@ confirmation decision if research was used.
 This Skill does not run `to-spec`, `to-tickets`, `implement`, `final review`,
 `review-loop`, `ask-light`, `learn-anything`, or any other user-invoked Skill.
 It does not manage tickets, perform implementation, establish acceptance, or
-become a permanent project workflow manager. `grilling` and `research` above
-are model-invoked capabilities permitted only for the stated questions and
-confirmed fallback; they do not authorize additional writes.
+become a permanent project workflow manager. `grill-me` (through its underlying
+`grilling` capability) and `research` above are external capabilities permitted
+only for the stated questions and confirmed fallback; they do not authorize
+additional writes.
diff --git a/skills/project-init/references/initialization-contract.md b/skills/project-init/references/initialization-contract.md
index 7d2c0e4..ca7b235 100644
--- a/skills/project-init/references/initialization-contract.md
+++ b/skills/project-init/references/initialization-contract.md
@@ -38,8 +38,10 @@ Record skipped checks and optional documents explicitly.
 
 ## Capability and invocation boundary
 
-`grilling` and `research` are model-invoked capabilities allowed by this
-initializer. The user remains in control of `to-spec`, `to-tickets`,
+`grill-me` is the user-facing entry point for the model-invoked `grilling`
+capability; together they provide the clarification interview allowed by this
+initializer. `research` is another model-invoked capability allowed for the
+confirmed fallback. The user remains in control of `to-spec`, `to-tickets`,
 `implement`, `review-loop`, `ask-light`, `learn-anything`, and every other
 user-invoked Skill. Project-init may recommend those names but never executes
 or orchestrates them.
diff --git a/skills/review-loop/references/attribution.md b/skills/review-loop/references/attribution.md
index b895e40..2661cb1 100644
--- a/skills/review-loop/references/attribution.md
+++ b/skills/review-loop/references/attribution.md
@@ -7,8 +7,9 @@ licensed projects:
   especially its execution gates, bounded agent packets, smoke-test evidence,
   snapshots, closeout, and advisory review gate.
 - [mattpocock/skills](https://github.com/mattpocock/skills), especially
-  `grill-me`, `grilling`, and `wayfinder` for the boundary between decision
-  discovery, planning, and execution.
+  `grill-me` as the user entry to its underlying `grilling` capability, and
+  `wayfinder` for the boundary between decision discovery, planning, and
+  execution.
 
 The audited projects are credited to their respective authors under MIT. No
 source text, code, visual asset, task-board implementation, or license text was