## 摘要 / Summary
补问、原话解释与真人确认分离；增加版本能力预检、sourceField/evidenceLinks、有限语义用例及正确工件依赖顺序。
Separate answers, interpretation and human confirmation; add capability
discovery, explicit source/evidence bindings, finite semantic checks and
artifact ordering.
发现描述覆盖“仅澄清”入口；有歧义的原话保持缺口，不把“不确定”塞入精确枚举或规范化值。按当前对话语言加载框架与固定事实门尾注。
当前请求中已唯一确定的值会写成类型化、待真人确认的 `node.value`；只有未知或仍有歧义的事实才保持 `needs_input`。
Discovery covers clarify-only requests. Ambiguous raw answers remain
unresolved, rather than becoming exact placeholder values. The framework
and fixed fact-gate footer follow the current conversation language.
Exact values uniquely supplied by the current request become typed,
human-reviewable `node.value` proposals; only genuinely unknown or
ambiguous facts remain `needs_input`.
应用/服务重启或重试 fork 后，入口必须在当前父轮重新加载 Skill，并在委派前用 ToolCatalog 核实阶段工具；子 Agent
不得突破未激活父级的能力上限。
After an app/service restart or retry fork, the entry Agent reloads the
Skill in the current parent turn and verifies stage tools before
delegation; a child never expands an unactivated parent ceiling.
新的 decision-grade `OptimizationSpec` 强制使用 v2，并完整声明 `semantic_contract`
中的 solve intent 及所有 objective/variable/constraint/data reference
的单位/维度；legacy v1 仅只读兼容。
New decision-grade `OptimizationSpec` artifacts use v2 and a complete
semantic contract for solve intent plus every material objective,
variable, constraint and data reference; legacy v1 remains read-only
compatibility.
## 验证 / Validation
- Scoped Skill/i18n/catalog check passes with zero errors. Existing
repository warnings remain.
- Publication safety check passed, including hidden working-tree files,
new paths, branch/commit metadata and collaboration text.
- 双语说明与 source hash 已同步，版本更新为 2.7.0；缺少新平台契约时保持普通澄清，不模拟缺失门禁。
- Bilingual bodies and source hashes are synchronized at version 2.7.0.
Older clients stay in plain-text clarification when capability discovery
fails.
## 状态 / Status
Runtime acceptance is still in progress; draft only. No customer data,
credentials, solver software or deployment settings are included.
真机验收仍在进行，本 PR 暂为草稿。保留外部求解器许可证、部署和费用披露；本变更不包含求解器、客户数据或凭据。
---------
Co-authored-by: yige <yige@yigedeMacBook-Neo.local>
## 背景 / Background
desirecore/desirecore#2248：真机测试中 code-intelligence 技能被绕过——模型未加载技能、未解锁
`Lsp`，直接用 Glob/Grep 文本检索回答语义导航问题，用户无从知道拿到的不是语义结果。
In real-device testing the skill was bypassed entirely: the model
answered semantic-navigation questions from Glob/Grep text matching
without loading the skill or unlocking `Lsp`, with no disclosure to the
user.
## 变更 / Changes
- **description（根级 + i18n 双语）改为命令式**：语义导航请求必须先加载本技能解锁隐藏的 `Lsp` 工具，禁止未尝试
`Lsp` 就用文本检索作答（配合主仓库的技能目录 provides.tools 附注，模型在决策点即可看到该指令）
- **L1 新增「硬性规则」**（双语）：`Lsp`
优先；限定允许回退的三种情形；任何回退到文本检索的回答必须向用户显式声明「结果来自文本匹配而非语义分析」及原因
- **L2 降级策略**同步引用硬性规则
- version 1.0.0 → 1.1.0；重算 i18n `source_hash`（`translated_by: human`
保持锁定）
## 校验 / Validation
- `uv run scripts/i18n/validate-i18n.py` → OK
- `uv run scripts/i18n/translate.py --check` → code-intelligence 两
locale 均无 stale
## 中文
- 将 `debug_port_closed` 的模型可见字段从 `launchCommand` 收紧为
`manualLaunchCommand`
- 明确 `requiredAction=wait_for_user_to_launch_browser` 与
`commandPolicy=display_only_never_execute`
- 中英 Skill 与 CDP 参考文档同步要求结束回合，禁止交给 Bash、PowerShell、终端或脚本执行
## English
- Rename the model-facing closed-port suggestion to
`manualLaunchCommand`
- Define `requiredAction=wait_for_user_to_launch_browser` and
`commandPolicy=display_only_never_execute`
- Keep the English/Chinese skill and CDP reference aligned: end the turn
and never pass the suggestion to an execution tool
## Validation
- i18n validator: pass
- translation freshness check: pass
- Windows real-device evidence: the previous contract correctly detected
`debug_port_closed` but attempted a Bash launch; approval was denied
before execution
## 中文
### 背景
L3-external 过去只用 curl 判断 9222，无法区分浏览器未安装、端口未开启、错误产品或伪 CDP
服务，也可能静默回落内置浏览器。
### 变更
- web-access 升级到 3.4.0，并要求先调用 BrowserExternalProbe
- 结构化处理未安装、端口关闭、多候选、产品不匹配、无效 CDP 与宿主不可用
- 显式浏览器不可自动替换；泛指 external 在多候选且无 ready 端口时先询问
- 所有 Playwright 配方使用 probe 返回端口和 DesireCore 隔离 Profile
- 纳入并修复 #93 的浏览器收尾规则与重复编号 finding
### 验证
- validate-i18n：通过
- translate --check：通过
- validate-i18n --online：通过
- source hash：sha256:1704b973e3a90e89
- 双语结构：31 个标题、20 个代码围栏
取代 #93；关联 desirecore/desirecore#2369。
## English
### Background
L3-external previously relied on curl against port 9222, which could not
distinguish a missing browser, a closed debug port, a different product,
or a fake CDP service, and could silently fall back to the built-in
browser.
### Changes
- Bump web-access to 3.4.0 and require BrowserExternalProbe before CDP
attach
- Handle missing installation, closed port, multiple candidates, product
mismatch, invalid CDP, and unavailable host as separate states
- Never replace an explicitly requested browser; ask when a generic
external request has multiple candidates and no ready endpoint
- Use the probe result port and a DesireCore-isolated profile in all
Playwright recipes
- Incorporate #93 browser wrap-up guidance and fix its duplicate
numbering review finding
### Validation
- i18n validation passed
- translation freshness check passed
- online validation passed
- source hash: sha256:1704b973e3a90e89
- bilingual structure: 31 headings and 20 code fences
Supersedes #93; related to desirecore/desirecore#2369.
---------
Co-authored-by: xieyuanxiang <124608760@qq.com>
## 中文
### 变更
- 将 manage-teams 升级到 1.3.0，并设置最低客户端版本 10.0.108
- 补齐 ManageTeam 全部 14 个 action 的用途、参数与风险边界
- 增加创建前检查、工作目录选择、Smart 成员路由、组织更新、头像、团队仓库、远程同步与失败恢复流程
- 明确远程操作必须经过 ManageTeam 的原因是供应链校验与审批，而不是假设 Agent 永远拿不到凭据
- 保持 disable-model-invocation: true，只在需要管理团队时按需加载
### 测试
- uv run --quiet scripts/i18n/test_validate_i18n.py
- uv run --quiet scripts/i18n/validate-i18n.py
- uv run --quiet scripts/i18n/translate.py --check
- git diff --check
## English
### Changes
- Upgrade manage-teams to 1.3.0 and require client 10.0.108
- Cover all 14 ManageTeam actions with their parameters and risk
boundaries
- Add preflight checks, workdir selection, Smart member routing,
organization updates, avatars, team repositories, remote
synchronization, and failure recovery
- Clarify that remote operations must use ManageTeam for supply-chain
validation and approval, not because Agents can never access credentials
- Keep disable-model-invocation: true so the Skill is loaded only when
team management is needed
### Tests
- uv run --quiet scripts/i18n/test_validate_i18n.py
- uv run --quiet scripts/i18n/validate-i18n.py
- uv run --quiet scripts/i18n/translate.py --check
- git diff --check
## 背景 / Background
v3.0（#85）以「它存在的每一条技术理由（无批量取文通道、evaluate 不可用、截图必须串行
activate）都已被内置浏览器覆盖」为由，删除了 Python Playwright 那一层。
**作为「内置浏览器不够用时的兜底」，这个判断是对的。**
但删除时顺带丢掉了一个完全不同的用例：用户想用**他自己那个**浏览器——他的登录态在他自己的 Chrome
里，他想亲眼看着操作、随时接管。这跟能力够不够无关，内置浏览器替代不了。
真实案例：用户要求「请你操作我本地机器的外部浏览器来完成一个示例报关过程」。技能里已无此路径，模型自己也查出「无独立的 Browser*
外部浏览器工具」，仍用内置浏览器做完全程，并以「本地受管浏览器」「已启动本地浏览器」描述——用户拿到的和要的不是一回事，却无从分辨。
v3.0 (#85) removed the Python Playwright layer on the grounds that every
technical reason it existed for is now covered by the built-in browser.
**As a fallback, that judgement was right.** But the deletion also took
a different use case with it: the user wanting *their own* browser —
their login state, their window, theirs to watch and take over. That has
nothing to do with capability, and the built-in browser cannot stand in
for it.
## 改动 / Changes
把 L3-external 作为**由用户意图触发的平级选择**恢复（**不再是 fallback**）：
- 恢复 `references/cdp-browser.md`（v3.0 删除，含 `connect_over_cdp` 模板与站点配方）
- 恢复 `Prerequisites: Chrome CDP Setup`，重新定位为「**仅 L3-external
需要**」，内置浏览器仍零前置条件
- 决策树的实时交互分支改为双路：用户点名外部 → L3-external；其余 → 内置（默认）
- 新增「两个浏览器，按用户意图选」对照表：是什么 / 登录态 / 用户能否看到 / 前置条件 / 是否默认
- 分层表加回 L3-external，并说明它**刻意不在默认排序里**——判据是用户点名，不是能力够不够
- 明确：CDP attach 时严禁 `browser.close()`（会关掉用户自己的 Chrome）
- 无论走哪条，措辞必须让用户能分辨实际用了哪个；禁止「本地浏览器」这类两边都像的说法
version 3.0.1 → 3.2.0
## 校验 / Validation
- `python3 scripts/i18n/validate-i18n.py` → OK: no i18n issues found
- `python3 scripts/i18n/translate.py --check` → web-access en-US
`human-locked, skipping`（无 source_hash 漂移）
- 双语同步；en-US 为 human-locked 翻译，已手工同步并按 `compute_source_hash` 重算对齐
## 公开信息边界 / Public information boundary
改动仅涉及浏览器能力边界的技术描述，无租户、客户或其他机密身份信息。
---------
Co-authored-by: Yige <a@wyr.me>
## 变更说明 / Summary
### 中文
- 在 `workforce-optimization` 的发现描述、`compatibility`、中英文市场摘要和正文中明确 MindOpt
是需要独立安装/部署并取得有效许可证的外部第三方求解器。
- 明确 `MindOptSolve` 只是受治理的 Connector/Adapter，不包含 MindOpt
求解器软件、许可证、算力托管、采购或运行费用。
- 增加运行前检查：必须确认 Connector ready、capabilities 可用且部署具备当前用途所需的有效许可证；仅注册 Tool
名称不能证明依赖可用。
- 增加安全降级：外部依赖不可用时仍可完成需求澄清和建模制品，但不得调用求解器、伪造 `SolveResult` 或宣称可行/最优/收益。
- 在 `AGENTS.md` 与 `CLAUDE.md` 中固化通用的第三方商业依赖披露规则。
- Skill 版本升级到 `2.3.3`，Market 版本升级到 `1.2.24`。
MindOpt 官方文档说明运行前必须取得有效许可证，并同时提供商业许可和社区许可；适用范围与采购要求以官方条款为准：
https://opt.aliyun.com/doc/mindopt/latest/cn/html/installation/license.html
### English
- Discloses in discovery metadata, `compatibility`, localized
marketplace text, and runtime instructions that MindOpt is separately
installed/deployed third-party solver software requiring a valid
applicable license.
- Clarifies that `MindOptSolve` is only the governed connector/adapter
and does not bundle the solver, license, hosted compute, procurement, or
operating costs.
- Adds a preflight gate for connector readiness, required capabilities,
and applicable licensing.
- Defines safe degraded behavior: requirement and model artifacts may
still be produced, but no solver call or fabricated solution claim is
allowed.
- Adds a generic third-party dependency disclosure rule to both
repository instruction entrypoints.
- Bumps the Skill to `2.3.3` and the Market to `1.2.24`.
The official MindOpt documentation states that a valid license is
required and documents both commercial and community licenses;
eligibility and purchasing remain governed by those official terms:
https://opt.aliyun.com/doc/latest/en/html/installation/license.html
## 验证 / Validation
- `uv run --quiet scripts/i18n/test_validate_i18n.py` — 8 passed
- `uv run --quiet scripts/i18n/validate-i18n.py` — no issues
- `uv run --quiet scripts/i18n/translate.py --check` — current; human
translation hash aligned
- `git diff --check`
- Public-worktree customer-identity/path scan — 0 matches
## Summary / 摘要
Normalize the Configure Compute, Using Services, and Register Services
source SVG icons to pure white.
将“配置算力”、“使用服务”和“注册服务”的源 SVG 图标统一为纯白。
## Version / 版本
- Market: `1.2.16` → `1.2.17`
- Each affected skill: `1.0.2` → `1.0.3`
## Validation / 验证
- `uv run scripts/i18n/validate-i18n.py`
- `uv run scripts/i18n/translate.py --check`
- Parsed all three SVGs and asserted their only hex color is `#FFFFFF`
- `git diff --check`
## 摘要 / Summary
### 中文
在去除机械数字上限（#58）后，进一步删掉技能里追问/展示数量的**软性倾向措辞**——create
的「一次不要问太多以免用户负担」、discover 的「避免一次刷屏过多」。数量与节奏完全交由执行 Agent
自主判断，不带任何倾向暗示。create 2.5.4 / discover 2.6.4，manifest 1.2.15，中英双份同步、重算
source_hash（validate-i18n 通过）。
### English
After removing the mechanical numeric caps (#58), further drop the soft
directional hints on ask/display count — create's "don't ask too many so
as not to burden the user" and discover's "avoid flooding the screen".
Count and pacing are left entirely to the executing Agent's judgment
with no bias. create 2.5.4 / discover 2.6.4, manifest 1.2.15, both
locales synced, hashes recomputed (validate-i18n passes).
## 摘要 / Summary
### 中文
去除技能里束缚执行 Agent 自主判断的**机械数字策略**：create 需求收集的「每轮最多问 2 个」、discover
排序的「最多展示 5 个候选」。改为交由 Agent 按情况自主把握追问节奏与展示数量，保留「别让用户负担 /
别一次刷屏」的原则意图——把控制权交还给判断力更强的执行者，而非用固定上限约束。create 2.5.3 / discover
2.6.3，manifest 1.2.14，中英双份同步、重算 source_hash（validate-i18n 通过）。
### English
Remove mechanical numeric limits that constrain the executing Agent's
judgment: create's "at most 2 questions per turn" and discover's "show
at most 5 candidates". Both become "the Agent decides the pacing/count
by situation", keeping the principle intent (don't burden the user /
don't flood the screen) while handing control back to the more capable
executor instead of a fixed cap. create 2.5.3 / discover 2.6.3, manifest
1.2.14, both locales synced, hashes recomputed (validate-i18n passes).
## 摘要 / Summary
### 中文
#56 的复盘修正。上一轮"强改写压缩"把四技能 L1
的**技术属性、使用场景与交互示范当套话一刀切**，造成实质信息丢失（承诺"意图全保留"但未做到）。本 PR 补回：
- **create**：`创建仓库符合 AgentFS v2 规范、git
管理版本（可治理/可追溯）`定位；`基础创建`形态（name+description，description 自动填充 persona
L0）；需求收集的**引导问题示例**（"起什么名字？/主要负责什么？"…）；企业部署/开发者原型使用场景。
- **update**：`agent 目录 git 管理版本、历史可追溯`定位 + 使用场景。
- **discover**：使用场景（浏览/新用户/找替代）+ `语义匹配而非关键词搜索`。
- **delete**：使用场景（清理/测试/释放存储）。
根因：L1 混着实质技术属性与营销套话、使用场景是触发判据、引导问题是交互示范，不该按"只留独有信息"一刀切。补回后仍保留结构性压缩（zh
正文合计仍降 ~64%）。版本 create 2.5.2 / update 3.1.3 / delete 2.5.2 / discover
2.6.2，manifest 1.2.13，中英双份同步、重算 source_hash（validate-i18n 通过）。
### English
Post-mortem fix for #56. The previous aggressive compression treated the
skills' L1 technical attributes, use cases, and interaction demos as
boilerplate and cut them in a blanket way, dropping substantive
information (the "all intent preserved" claim wasn't fully met). This PR
restores: create's AgentFS-v2 / git-version-management positioning, the
"basic create" form (name+description auto-filling persona L0), the
requirement-gathering prompt questions, and enterprise/developer use
cases; update's git-versioned/traceable positioning and use cases;
discover's use cases and "semantic match, not keyword search"; delete's
use cases. Root cause: L1 mixed real technical attributes with marketing
boilerplate, use cases are trigger cues, and prompt questions are
interaction demos — none should have been blanket-cut. Structural
compression is retained (zh bodies still ~64% smaller). Versions bumped,
manifest 1.2.13, both locales synced, source hashes recomputed
(validate-i18n passes).
## 摘要 / Summary
### 中文
market#52 的修正:update-agent
附录示例使用了错误的字段名(`communicationStyle`/`must`),照示例调用会被 ManageAgent 的 Ajv
校验(additionalProperties: false)直接拒绝;`personality` 示例应为字符串数组。同时把 `get`
的返回示例对齐真实输出格式(`## persona.md` / `## principles.md` 段落含分层 markdown 原文,对应
desirecore#1230),并在附录固定列出结构化字段名清单。update-agent 3.1.1,manifest 1.2.11。
### English
Correction to market#52: the update-agent appendix examples used wrong
field names (`communicationStyle`/`must`) that ManageAgent's Ajv
validation (additionalProperties: false) would reject outright;
`personality` must be a string array. The `get` response example is
aligned with the actual output format (`## persona.md` / `##
principles.md` sections, per desirecore#1230), and the appendix now
lists the fixed structured field names. update-agent 3.1.1, manifest
1.2.11.
## Summary / 摘要
Add inline SVG icons to all 20 external pointer skills, so their cards
no longer fall back to an empty icon. The market catalog version is
bumped from `1.2.8` to `1.2.9`.
为全部 20 个外部 pointer skill 补齐内联 SVG 图标，市场卡片不再显示为空；市场版本由 `1.2.8` 升至
`1.2.9`。
## Compatibility / 兼容性
Depends on desirecore/desirecore#1177, which permits the `icon` field in
strict pointer-entry validation and forwards it through the offline
list/detail responses. That PR must merge first.
## Skill → icon screenshot / Skill 与图标截图
The preview labels every card with its display name and id.
Covered skills: `agent-reach`, `ai-news-radar`, `amap-jsapi-skill`,
`dingtalk-api`, `flyai-skill`, `follow-builders`,
`ian-xiaohei-illustrations`, `karpathy-guidelines`, `khazix-skills`,
`larksuite-cli`, `last30days`, `luckin-my-coffee`, `mattpocock-skills`,
`minimax-image-gen`, `minimax-tts`, `mt-paotui-for-client`,
`netease-skills`, `taste-skill`, `wechatpay-skills`, and `wecom-cli`.
## Validation / 验证
- `uv run scripts/i18n/validate-i18n.py`
- `uv run scripts/i18n/translate.py --check`
- Parsed all 20 `entry.json` icons as SVG XML
- `git diff --check`
- Rendered the committed preview asset locally
## Summary / 摘要
Complete the two pointer entries added in #46 with `latestVersion` and
`i18n` blocks.
补全 #46 新增的两个 pointer 条目的 `latestVersion` 与 `i18n` 字段。
## Why / 原因
- **latestVersion**: `karpathy-guidelines` upstream `SKILL.md` has no
root-level `version`, so the client records `0.0.0` on install and the
update check (`0.0.0 == 0.0.0`)永远判定已最新——updates would be silently
skipped forever. Registering `latestVersion` here enables the
client-side fallback (shipping separately in the desirecore repo).
`karpathy-guidelines` 上游无根级 version，客户端装出来是 0.0.0 且更新判定永远跳过；在市场登记
latestVersion 配合客户端 fallback 修复。
- **i18n**: per ADR-038, market list localization must work offline from
`entry.json` alone. Both entries previously lacked `i18n`, so the list
shortDesc would render empty.
按 ADR-038 列表本地化需离线可用，此前两条目缺 i18n，列表简介为空。
## Changes / 变更
- `skills/karpathy-guidelines/entry.json`: `latestVersion: 1.0.0` +
zh-CN/en-US `i18n`
- `skills/last30days/entry.json`: `latestVersion: 3.11.1`（与上游一致）+
zh-CN/en-US `i18n`
## Testing / 测试
- Both files validated against `marketSkillEntrySchema` (Ajv, desirecore
repo) — VALID.
- [x] I have read and agree to the CLA
## 变更 / Changes
update-agent 技能:纯改名场景改为用 **Edit 工具同时更新两个文件**——`agent.json` 的 `name` 字段 与
`persona.md` 的首行标题(`# 名称`),避免两者脱节;并强调不实际编辑文件不得声称已改名。
The update-agent skill now instructs: for a pure display-name change,
use the **Edit tool to update both files** — the `name` field in
`agent.json` and the first-line title heading (`# Name`) in `persona.md`
— so the display name and persona title never fall out of sync. Also
emphasizes never claiming a rename is done without actually editing the
files.
## 背景 / Context
此前改名只改了 `agent.json` 的 name,`persona.md`
标题残留旧名(显示名与人格文档脱节);且模型有时只口头声称完成而不真正落盘。本改动通过技能引导修正这两点。
Previously renaming only touched `agent.json`'s name while
`persona.md`'s title kept the old name (desync), and the model would
sometimes claim completion without actually writing. This skill guidance
fixes both.
## 改动范围 / Scope
- `skills/update-agent/SKILL.md`(+3)
- `skills/update-agent/SKILL.zh-CN.md`(+3)
- 纯文档/技能引导改动,version 保持 3.0.4 不变
Co-authored-by: 张馨元 <zhangxy@iynss.com>
