ake
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAKE 使用帮助与入口路由
AKE Usage Help and Entry Routing
A. Skill 日常命令(在对话中使用)
A. Daily Skill Commands (used in conversations)
| 命令 | 功能 |
|---|---|
| 显示使用帮助(本页) |
| 显示使用帮助(与 |
| 查看当前安装和版本状态(只读,不联网) |
| 检查并更新 AKE(由用户明确发起,走确定性 CLI 流程) |
宿主只把 token 交给本 Skill,后面的 、、 是自然语言,不是宿主结构化参数路由。遇到歧义、或更新可能覆盖本地定制时,先询问用户,不要替用户决定。
/akestatusupdatehelp| Command | Function |
|---|---|
| Display usage help (this page) |
| Display usage help (identical to |
| View the current installation and version status (read-only, no network access) |
| Check for and install AKE updates (explicitly initiated by the user through the deterministic CLI workflow) |
The host passes only the token to this Skill. The following , , and are natural-language inputs, not structured parameter routes handled by the host. In case of ambiguity, or if an update may overwrite local customizations, ask the user first; do not decide on their behalf.
/akestatusupdatehelpB. CLI 安装与项目初始化(在终端使用)
B. CLI Installation and Project Initialization (used in a terminal)
| 命令 | 功能 |
|---|---|
| 安装/更新到用户级 Skills 目录(Vercel Skills CLI) |
| 初始化当前工作目录 |
| 初始化指定目录 |
| 查看安装状态,同时保留原有知识统计 |
| 检查并更新已安装的 Skill(参数以 |
说明: 指 AKE 源码或项目内附带的 CLI( 或 )。Skill 的安装与链接由上面的 Vercel Skills CLI 负责; 不会推进已固定到某个 commit 的安装,因此更新请用 。
akenode scripts/ake.mjs …node .ake/tools/scripts/ake.mjs …npx skills updateake update| Command | Function |
|---|---|
| Install/update into the user-level Skills directory (Vercel Skills CLI) |
| Initialize the current working directory |
| Initialize a specified directory |
| View installation status while retaining existing knowledge statistics |
| Check for and update the installed Skill (refer to |
Note: refers to the AKE source code or the project-bundled CLI ( or ). Skill installation and linking are handled by the Vercel Skills CLI above. Because does not advance an installation pinned to a specific commit, use to update it.
akenode scripts/ake.mjs …node .ake/tools/scripts/ake.mjs …npx skills updateake updateC. 知识管理能力
C. Knowledge Management Capabilities
- 自动检索:任务开始、涉及实现/排障/架构/风险变更时,先检索四类知识(Agent Notes、Defensive Patterns、Postmortems、Cookbooks)。
- 自动评估沉淀:实质任务完成并经用户确认后,评估本次是否有可复用知识值得沉淀。
- 手动评估当前 Session:直接要求 AKE 评估这段工作是否值得整理(不要求先跑完自动流程)。
- 手动整理指定经验:明确指定「把某段经验整理成候选」,AKE 只按你的指定范围整理。
- 查看候选:(查看全部候选及状态)。
node .ake/tools/scripts/ake.mjs candidate list - 检查审核状态:/
node .ake/tools/scripts/ake.mjs candidate show <id>。candidate check <id> - 发布授权流程:候选经独立 reviewer 审核后,需用户明确授权才 并
approve <id> --by <human> --confirm;未授权时保持未发布。publish <id>
- Automatic Retrieval: At the start of tasks involving implementation, troubleshooting, architecture, or risk-related changes, first retrieve the four knowledge categories: Agent Notes, Defensive Patterns, Postmortems, and Cookbooks.
- Automatic Capture Assessment: After a substantive task is complete and confirmed by the user, assess whether the task produced reusable knowledge worth capturing.
- Manual Assessment of the Current Session: Directly ask AKE to assess whether the current work is worth organizing, without first running the automatic workflow.
- Manual Organization of a Specified Experience: Explicitly request that a particular experience be organized into a candidate; AKE will organize only the scope you specify.
- View Candidates: to view all candidates and their statuses.
node .ake/tools/scripts/ake.mjs candidate list - Check Review Status: /
node .ake/tools/scripts/ake.mjs candidate show <id>.candidate check <id> - Publishing Authorization Workflow: After an independent reviewer has reviewed a candidate, explicit user authorization is required before running and
approve <id> --by <human> --confirm. Without authorization, the candidate remains unpublished.publish <id>
路由规则
Routing Rules
- 或
/ake:只输出本帮助。无参数/ake help不解释为知识沉淀任务、不扫描当前 Session、不自动检索、不创建候选。/ake - :执行
/ake status(只读)。若当前目录没有 AKE 项目,如实报告错误,不改用其他项目。ake status - :执行确定性 CLI 更新流程,顺序如下:
/ake update- 若本 Skill 目录内存在 且支持
resources/ake-source/scripts/ake.mjs→ 用它执行;update - 否则,若当前处于 AKE 官方源码 checkout(为官方仓库、
origin无未提交改动)→ 用skills/ake;node <checkout>/scripts/ake.mjs update - 两者都不满足 → 停止并说明原因,不得由模型自行拼 shell、Git、复制或清理命令。
- 若本 Skill 目录内存在
- 更新成功后提示:DSH 每次加载/注入 Skill 时读取磁盘,本 Session 已注入的旧内容不会自动刷新;请在新消息中重新调用 ,若仍使用旧内容则新开 Session。无需重启整个 DSH。
/ake - 任何会覆盖用户定制、或无法确认安装目标的情况,先询问用户。
- or
/ake: Output only this help page. A no-argument/ake helpmust not be interpreted as a knowledge-capture task, must not scan the current Session, must not perform automatic retrieval, and must not create a candidate./ake - : Execute
/ake status(read-only). If the current directory does not contain an AKE project, report the error truthfully; do not fall back to another project.ake status - : Execute the deterministic CLI update workflow in the following order:
/ake update- If exists within this Skill directory and supports
resources/ake-source/scripts/ake.mjs→ use it to execute the update;update - Otherwise, if the current directory is an official AKE source checkout (points to the official repository and
originhas no uncommitted changes) → useskills/ake;node <checkout>/scripts/ake.mjs update - If neither condition is satisfied → stop and explain why. The model must not construct its own shell, Git, copy, or cleanup commands.
- If
- After a successful update, notify the user: DSH reads from disk whenever it loads/injects a Skill, and old content already injected in this Session will not refresh automatically. Invoke again in a new message; if the old content is still being used, start a new Session. There is no need to restart the entire DSH.
/ake - Before performing anything that may overwrite user customizations or when the installation target cannot be confirmed, ask the user first.
示例
Examples
- → 只显示本帮助(不检索、不沉淀)。
/ake - 在项目目录执行 → 初始化当前目录;换到别处初始化才用
ake init。ake init --dir <project> - 查看版本/安装/更新状态;需要更新时
/ake status(自动备份、校验、失败回滚)。/ake update
- → displays only this help page, with no retrieval or capture.
/ake - Run in a project directory → initializes the current directory; run
ake initonly when initializing a directory elsewhere.ake init --dir <project> - Use to view version, installation, and update status; use
/ake statuswhen an update is needed (automatic backup, verification, and rollback on failure)./ake update
安装、初始化与日常使用的区别
Differences Between Installation, Initialization, and Daily Use
- 安装:把 Skill 放进用户级 Skills 目录,每台机器/每个用户一次。
- 初始化:为某个 Git 项目建立 (知识目录、配置、项目内 CLI),每个项目一次。
.ake/ - 日常使用:以具体请求调用(例如 ),或由 AKE 按任务阶段自动检索/沉淀;单独输入
/ake 评估这段经验是否值得沉淀只显示帮助,不触发检索或沉淀。日常使用不重复安装或初始化。/ake
- Installation: Places the Skill in the user-level Skills directory; performed once per machine/user.
- Initialization: Establishes for a Git project, including the knowledge directory, configuration, and project-local CLI; performed once per project.
.ake/ - Daily use: Invoke AKE with a specific request, such as , or allow AKE to retrieve/capture knowledge automatically according to the task phase. Entering
/ake assess whether this experience is worth capturingby itself only displays the help page and does not trigger retrieval or capture. Daily use does not repeat installation or initialization./ake
AKE knowledge operations
AKE knowledge operations
先确定目标项目的绝对路径,并使用 Skill 加载器提供的 本 Skill base directory 绝对路径;不得从当前工作目录、目标项目或 AKE 源码 checkout 推导 Skill 路径。若加载环境未提供该绝对路径,先请用户提供/确认已安装 Skill 的位置,不要猜路径。
First determine the absolute path of the target project and use the absolute path to the current Skill base directory provided by the Skill loader. The Skill path must not be inferred from the current working directory, target project, or AKE source checkout. If the loading environment does not provide this absolute path, first ask the user to provide or confirm the installed Skill location; do not guess the path.
项目初始化(按需)
Project Initialization (as needed)
首次检查用下面的 对目标做只读预检;不要把继承 环境的普通 shell 结果当作授权依据。Bootstrap 清理全部 环境变量后再检查:目标可以是独立 Git 工作树根目录,也可以是已有父级工作树中的项目子目录;它只在用户给定的确切目录初始化,不向上迁移、不创建嵌套 Git 仓库,也不运行 。若结果明确为非 Git 工作树,询问用户是否先选择/初始化 Git 项目;只有用户确认且目录已由用户建立为有效工作树后才重试。缺少 Git、bare 仓库或其他 Git 检查错误时,不得推测可新建,停止并报告原因。检查失败时零写。
bootstrap.mjs --dry-runGIT_*gitGIT_*git init如果目标中 与 都是现有文件,视为已初始化:不要重复运行 bootstrap、不要复制或升级配置/CLI。bootstrap 仅安全读取 config 版本与随附 bundle 的 package 元数据并报告是否不同;它不会执行项目 CLI,且不能由 config 版本证明 CLI 本身的版本。无法判断时明确报告未知。旧版或版本未知的项目 CLI 在任何写操作前,要求用户自行运行只读 ,确认返回的 精确等于目标绝对路径;Agent 不自动执行现有项目 CLI,也不在未确认前执行写命令。若项目根错误,先备份并让用户人工审阅当前官方 AKE 版本的迁移/合并方案;不要自动复制、升级或覆盖项目 CLI、配置、知识文件。确认后才可使用该项目自己的 CLI。
.ake/config.json.ake/tools/scripts/ake.mjsnode <绝对目标路径>/.ake/tools/scripts/ake.mjs status --jsonproject若缺任一文件,使用本 Skill 随附的离线资源执行器,不依赖 AKE 源码 checkout 或调用时的工作目录。先展示计划:
bash
node <本 Skill base directory 的绝对路径>/bootstrap.mjs --dir <绝对目标路径> --dry-rundry-run 若报告任何 ,停止并报告冲突路径;不要应用部分计划。无冲突后再应用:
conflictbash
node <本 Skill base directory 的绝对路径>/bootstrap.mjs --dir <绝对目标路径>bootstrap 从本 Skill 的 离线资源调用原有 AKE 初始化器。若资源不完整,它会列出确切缺失文件且不写项目文件;按 README 中的官方 Skill 安装说明从 AKE 源码 checkout 恢复/更新 Skill,再重试。初始化不安装任何全局 Skill,也不升级已有项目 CLI。
resources/ake-source/程序可测试的行为包括 Git 根校验、dry-run、冲突拒绝、离线初始化和既有 CLI/config 保留;“非 Git 时询问用户”是本 Skill 对 Agent 的软指令,不能由脚本或自动化测试证明真实 Agent 会遵循。不要把提示规则描述成安全边界。
For the first check, use the following command to perform a read-only preflight check against the target. Do not treat results from an ordinary shell process that inherits environment variables as authorization. The bootstrap clears all environment variables before checking. The target may be either the root of a standalone Git worktree or a project subdirectory within an existing parent worktree. It initializes only the exact directory specified by the user; it does not migrate upward, create a nested Git repository, or run . If the result clearly indicates that the target is not a Git worktree, ask the user whether to select or initialize a Git project first. Retry only after the user confirms and the directory has been established by the user as a valid worktree. If Git is missing or the check reports a bare repository or another Git error, do not infer that a new repository can be created; stop and report the reason. A failed check must result in zero writes.
bootstrap.mjs --dry-rungitGIT_*GIT_*git initIf both and are existing files in the target, treat the project as initialized. Do not run bootstrap again or copy or upgrade the configuration/CLI. Bootstrap only safely reads the configuration version and the bundled package metadata and reports whether they differ. It does not execute the project CLI, and the configuration version cannot prove the version of the CLI itself. If the version cannot be determined, explicitly report it as unknown. For an old or unknown-version project CLI, before any write operation ask the user to run the read-only command and confirm that the returned exactly equals the target absolute path. The Agent does not automatically execute the existing project CLI or any write command before confirmation. If the project root is incorrect, first create a backup and have the user manually review the migration/merge plan against the current official AKE version. Do not automatically copy, upgrade, or overwrite project CLI files, configuration, or knowledge files. Only after confirmation may the project’s own CLI be used.
.ake/config.json.ake/tools/scripts/ake.mjsnode <absolute target path>/.ake/tools/scripts/ake.mjs status --jsonprojectIf either file is missing, use the offline resource executor bundled with this Skill, without depending on an AKE source checkout or the working directory used at invocation time. First present the plan:
bash
node <absolute path of this Skill base directory>/bootstrap.mjs --dir <absolute target path> --dry-runIf the dry run reports any , stop and report the conflicting paths; do not apply a partial plan. If there are no conflicts, apply the plan:
conflictbash
node <absolute path of this Skill base directory>/bootstrap.mjs --dir <absolute target path>Bootstrap invokes the original AKE initializer from the offline resources under . If those resources are incomplete, it lists the exact missing files and does not write project files. Restore or update the Skill from the AKE source checkout according to the official Skill installation instructions in the README, then retry. Initialization does not install any global Skill or upgrade an existing project CLI.
resources/ake-source/Program-testable behaviors include Git root validation, dry-run, conflict rejection, offline initialization, and preservation of an existing CLI/configuration. “Ask the user when the target is not a Git repository” is a soft instruction for the Agent and cannot be proven by a script or automated test. Do not describe prompt-based rules as a security boundary.
任务前:用户可见通知与按需检索
Before the Task: User-Visible Notification and On-Demand Retrieval
- 当任务首次进入 AKE 触发阶段(相关工程知识检索或任务后沉淀)时,在首个 AKE CLI 操作前给用户一条简短通知;同一阶段连续进行的多次搜索/候选命令合并在这条通知中,不逐条重复通知。
- Agent Teams 由 Lead/任务 owner 统一发用户通知;成员只将检索/候选结果汇报给 Lead,不各自重复通知用户。
- 在触发的检索阶段,先说明「我会检索 AKE 项目知识并按相关性使用」,再按模块/技术、症状、操作构造具体关键词执行 。只在触发相关任务时检索,不要求无关任务做空搜索。
node .ake/tools/scripts/ake.mjs search <terms> - 搜索默认覆盖四类知识根:Agent Notes、Defensive Patterns、Postmortems、Cookbooks;结果须展示/说明类别标签。需要时使用 ,并可用
--include-candidates/--type缩小结果。--limit - 命中后只读查看相关文档;判断其 scope、status、verified、证据和当前代码是否仍适用,不把命中视为自动指令。最终报告指出检索词、命中文档/类别及适用性;没有命中只表示“未找到”,不表示知识不存在。
- When a task first enters an AKE trigger phase, whether relevant engineering knowledge retrieval or post-task capture, provide the user with a brief notification before the first AKE CLI operation. Combine multiple consecutive search/candidate commands within the same phase under this notification instead of repeating it for every command.
- For Agent Teams, the Lead/task owner sends the user notification centrally. Members report retrieval/candidate results to the Lead and do not each send separate notifications to the user.
- During a triggered retrieval phase, first state, “I will retrieve AKE project knowledge and use it according to relevance.” Then construct specific keywords based on the module/technology, symptom, or operation and execute . Retrieve knowledge only when the task is relevant; do not perform empty searches for unrelated tasks.
node .ake/tools/scripts/ake.mjs search <terms> - Searches cover the four knowledge roots by default: Agent Notes, Defensive Patterns, Postmortems, and Cookbooks. Results must display or explain their category labels. Use when needed, and narrow results with
--include-candidates/--type.--limit - After a match, read the relevant documents read-only. Assess their scope, status, state, evidence, and whether they still apply to the current code. Do not treat a match as an automatic instruction. The final report must identify the search terms, matched documents/categories, and their applicability. No matches means only “not found,” not that the knowledge does not exist.
verified
任务后:判断是否值得沉淀
After the Task: Assess Whether Knowledge Is Worth Capturing
- Agent Note:有可复用的设计/实现决策、重要取舍或变更依据。按生命周期写入 。
.agents/notes/{proposed,implemented,rejected}/{class}/ - Defensive Pattern:可重复的规则/防错检查,写入 。
docs/defensive-patterns/ - Postmortem:已发生的故障、影响、时间线、根因与护栏,写入 。
docs/postmortem/ - Cookbook:可复用的操作步骤及验证方式,写入 。
docs/cookbook/
只把有据、可复用的新知识写成候选。普通问答、琐碎改动、没有稳定经验或已被现有文档覆盖时,报告「AKE · 本次无新增知识」。若已发现可能有价值的新知识但核心证据不足,不要误报“无新增知识”:不创建候选,明确标注“潜在知识待补证据”,说明缺少什么以及如何验证。不得编造 scope、evidence、验证日期、会话/事件标识或解决状态。先搜索正式知识及候选,优先修订真正对应的现有目标。候选应对应实际有价值的结果,并用与核心主张相关的 A/B 级证据支持;可追溯证据可以是当前会话中可核对的直接观察,无需额外持久化产物或 ID。按主张选择合适验证;不得声称未执行的测试/检查已运行,也不要求每个候选都必须有实际测试。写明适用范围和验证条件。创建或更新前通知用户「AKE · 准备沉淀为 <类别>:<简要主题>」。使用 或 、 和 ;逐项核对格式、目标、链接、重复项、范围、证据、内容哈希和目标哈希。
candidate newcandidate revisecandidate submitcandidate check- Agent Note: A reusable design/implementation decision, important trade-off, or rationale for a change. Write it to according to its lifecycle.
.agents/notes/{proposed,implemented,rejected}/{class}/ - Defensive Pattern: A repeatable rule or defensive check. Write it to .
docs/defensive-patterns/ - Postmortem: An incident that has occurred, including its impact, timeline, root cause, and safeguards. Write it to .
docs/postmortem/ - Cookbook: Reusable operational steps and validation methods. Write it to .
docs/cookbook/
Create candidates only for evidence-based, reusable new knowledge. For ordinary Q&A, trivial changes, work with no stable lessons, or results already covered by existing documentation, report . If potentially valuable new knowledge has been identified but core evidence is insufficient, do not incorrectly report “No new knowledge this time.” Do not create a candidate. Instead, explicitly report “Potential knowledge awaiting evidence,” explain what is missing, and describe how it can be validated. Never fabricate scope, evidence, validation dates, session/event identifiers, or resolution status. Search established knowledge and candidates before creating or revising a target, and prefer revising the genuinely corresponding existing target. Each candidate must correspond to an actually valuable result and be supported by A- or B-level evidence relevant to its core claim. Traceable evidence may consist of direct observations that can be verified within the current session; no additional persisted artifact or ID is required. Select validation appropriate to the claim. Do not claim that tests or checks were run when they were not, and do not require every candidate to have an actual test. State the applicable scope and validation conditions. Before creating or updating a candidate, notify the user: . Use or , , and ; verify the format, target, links, duplicates, scope, evidence, content hash, and target hash item by item.
AKE · No new knowledge this timeAKE · Preparing to capture as <category>: <brief topic>candidate newcandidate revisecandidate submitcandidate check独立审核与发布授权
Independent Review and Publishing Authorization
-
Agent Teams:优先由未参与候选生成、且适合该领域的独立 reviewer 检查。以真实 reviewer 名称运行;不得伪装身份。发出一次请求后,等待该 reviewer 的实际审核结果;派单成功、工具接受或沉默都不是审核完成。若当前轮次无法等待实际结果,暂停并如实告知用户/Lead,不自行假称已审核。
review <id> --reviewer ... --verdict <approve|request-changes|reject> --notes ... -
Single Session:有可用独立子代理时,交由未参与生成的 reviewer 审核并等待其实际结果;没有可用 reviewer 时,说明独立审核不可用并暂停,等待安排 reviewer。作者自检可作为补充记录,但不得声称独立,也不得替代所需的独立审核。
-
Reviewer 报告使用、
PASS、PASS WITH LIMITATIONS标签;现有 CLI verdict 保持BLOCK:approve|request-changes|reject映射PASS;approve若核心主张有据且限制已明确写入候选,也映射PASS WITH LIMITATIONS;若需先补充/明确限制,则映射approve。request-changes按问题是否可修复映射BLOCK或request-changes。不要将新标签作为 CLI verdict。reject -
证据等级针对候选的核心主张,而非元数据完整度。A(强直接证据) = 与主张相关的源代码/差异、实际测试日志、可复现结果,或有意义的前后对比;不相关的代码或测试不能支撑该主张。B(当前上下文中的可用证据) = 与主张相关的当前运行/系统状态、实际浏览器检查、此 Session Agent 的直接验证、用户对其意图/验收的确认,或可读取的配置、安装脚本、系统状态。B 不要求持久化材料、独立证据文件、session/event ID,也不要求把会话内直接观察再包装成独立佐证;按主张判断关联性和局限。C(核心证据缺失) = 核心主张没有基本相关证据、证据与主张不匹配,或被现有证据反驳。A/B 可支持相关核心主张;C 对核心主张须标,并按可修复性映射
BLOCK/request-changes。缺少 session ID、事件号、独立证据文件或不相关主题本身不降级证据等级,也不构成 BLOCK;不得为了满足字段制造证据。reject -
若潜在知识有价值但因 C 级证据不足不能形成候选,报告“潜在知识待补证据”及具体缺口/验证路径,不能说“无新增知识”。仅用于确实没有新的、可复用结果。
AKE · 本次无新增知识 -
收到后最多自动修订一次,再交由独立 reviewer 实际复核一次;第二次仍未通过就暂停并报告,不循环。CLI 记录 verdict 时保留原有候选状态和绑定门禁。
request-changes -
Reviewer 通过后,向用户报告候选及限制并等待用户明确授权发布。不得默认自动授权,不得预先运行或
approve --confirm。收到明确授权后,使用现有 CLIpublish记录授权,再运行approve <id> --by <human> --confirm;publish <id>是声明,不是身份认证。用户未授权时保持未发布,并说明候选 ID、状态和等待原因。--by -
内容修改或观察到漂移后,必须按现有门禁重新提交并重新审核;发布仍须保留绑定校验、漂移检测、账本和 unknown-result reconcile。Skill/AGENTS 是软约束,普通文件工具可绕过,不是安全边界。
-
合成回归例(不是已观察事实):假设本 Session Agent 实际检查 Tampermonkey 目标页面的按钮文字与背景/边框、/
::before伪元素层叠、真实计算样式和下拉交互,且用户确认这些观察;其他页面/菜单主题未检查并已作为限制写明。此即时上下文证据属 B,不要求持久化截图、独立证据文件或 session/event ID;预期::after,映射 CLIPASS WITH LIMITATIONS。不能仅因缺少标识/持久化文件或其他主题未验证而 BLOCK。若同一候选对这些核心主张实际没有基本证据(C),则应approve,按可修复性映射BLOCK/request-changes。此例为合成测试向量,不是实际浏览器检查或 Tampermonkey 行为验收。reject
-
Agent Teams: Prefer an independent reviewer who did not participate in generating the candidate and has suitable domain expertise. Runusing the reviewer’s real name. Do not impersonate another identity. After sending a review request, wait for the reviewer’s actual result. Successful dispatch, tool acceptance, or silence does not mean the review is complete. If the actual result cannot be awaited in the current turn, pause and truthfully inform the user/Lead; do not claim that a review occurred.
review <id> --reviewer ... --verdict <approve|request-changes|reject> --notes ... -
Single Session: If an independent subagent is available, assign the review to a reviewer who did not participate in generation and wait for the actual result. If no independent reviewer is available, explain that independent review is unavailable and pause until a reviewer is arranged. The author’s self-check may be recorded as supplementary evidence, but it must not be claimed as independent or used as a substitute for the required independent review.
-
Reviewer reports use the,
PASS, andPASS WITH LIMITATIONSlabels. Existing CLI verdicts remainBLOCK:approve|request-changes|rejectmaps toPASS;approvemaps toPASS WITH LIMITATIONSif the core claim is supported and all limitations are explicitly recorded in the candidate, or toapproveif limitations must first be supplemented or clarified;request-changesmaps toBLOCKorrequest-changesdepending on whether the issues are fixable. Do not use the new labels as CLI verdicts.reject -
Evidence grades apply to the candidate’s core claim, not to metadata completeness. A (strong direct evidence) means source code/diffs related to the claim, actual test logs, reproducible results, or meaningful before/after comparisons; unrelated code or tests cannot support the claim. B (usable evidence in the current context) means current runtime/system state related to the claim, an actual browser inspection, direct verification by the Session Agent, user confirmation of intent/acceptance, or readable configuration, installation scripts, or system state. B does not require persisted materials, independent evidence files, or session/event IDs, nor does it require turning direct session observations into separate independent corroboration; assess relevance and limitations according to the claim. C (core evidence missing) means the core claim has no fundamentally relevant evidence, the evidence does not match the claim, or existing evidence contradicts it. A/B evidence can support a relevant core claim. A C-grade core claim must be markedand mapped to
BLOCK/request-changesaccording to whether it is fixable. The absence of a session ID, event number, independent evidence file, or a relevant topic does not itself lower the evidence grade or constitute areject; never fabricate evidence to satisfy fields.BLOCK -
If potentially valuable knowledge cannot form a candidate because it has C-level evidence, report “Potential knowledge awaiting evidence,” including the specific gaps and validation path. Do not say “No new knowledge this time.” The messageis used only when there is genuinely no new, reusable result.
AKE · No new knowledge this time -
After receiving, automatically revise the candidate at most once and then have the independent reviewer perform one actual re-review. If it still fails on the second review, pause and report the result; do not continue looping. When the CLI records a verdict, preserve the existing candidate status and binding gates.
request-changes -
After the reviewer passes, report the candidate and its limitations to the user and wait for explicit authorization to publish. Do not grant automatic authorization by default, and do not runor
approve --confirmin advance. After receiving explicit authorization, use the existing CLI commandpublishto record the authorization, then runapprove <id> --by <human> --confirm. Thepublish <id>value is a declaration, not identity authentication. If the user has not authorized publication, keep the candidate unpublished and explain its ID, status, and the reason for waiting.--by -
After content is modified or drift is observed, resubmit and re-review the candidate under the existing gates. Publishing must continue to preserve binding validation, drift detection, the ledger, and unknown-result reconciliation. Skill/AGENTS are soft constraints that ordinary file tools can bypass and are not security boundaries.
-
Synthetic regression example, not an observed fact: Suppose the Session Agent actually inspected the button text, background/border,/
::beforepseudo-element stacking, actual computed styles, and dropdown interactions on the target Tampermonkey page, and the user confirmed those observations; other pages/menu themes were not inspected and were recorded as limitations. Such immediate-context evidence is B-level and does not require persisted screenshots, independent evidence files, or session/event IDs. The expected result is::after, mapped to the CLI verdictPASS WITH LIMITATIONS. It must not be markedapprovemerely because identifiers or persisted files are missing or other themes remain unverified. If the same candidate actually has no fundamental evidence for these core claims, its grade is C, and it must be markedBLOCKand mapped toBLOCK/request-changesaccording to whether it is fixable. This example is a synthetic test vector, not an actual browser inspection or acceptance of Tampermonkey behavior.reject
触发路由与连续执行能力边界
Trigger Routing and Boundaries of Continuous Execution
- 按阶段应用触发并只执行当前阶段适用的步骤:任务前触发只做检索与适用性判断,不启动候选捕获;任务后触发先评估沉淀价值和证据。用户显式调用 时按其请求的阶段执行,不受自动完成语句条件限制。仅在任务后评估确认有据、可复用且未被覆盖的结果时,才继续查重、创建/修订候选和请求独立 reviewer;无价值则报告「AKE · 本次无新增知识」,证据不足则报告“潜在知识待补证据”,不得强制建候选。
/ake - 当前阶段的所有适用步骤一次连续执行,不要在检索、适用性判断、价值/证据评估、查重或合格候选的准备/提交/reviewer 请求之间额外询问“是否继续”。只在必须取得实际 reviewer 回复或用户发布授权时等待;无法等待 reviewer 的真实结果时如实报告,不伪造结果。现有 candidate/submit/review/approve/publish 权限、安全、验证和状态门槛不因连续执行而放宽。
- 自动完成语句路由的条件仅适用于这一个额外的自动信号:此前确有实质工程任务(实现、调试、测试、架构或风险变更),本 Skill 已加载,且用户随后明确说「验证 ok」「测试通过」「没问题了」「验收通过」等。该条件不限制显式 调用或既有适用知识触发。普通问答、解释、无工程产出的对话不因完成语句路由自动进入候选流程;完成确认也不等于发布授权。
/ake - 以上消息判断是模型软约束,不是宿主硬触发。普通语言消息不能保证自动加载本 Skill;显式 可通过宿主机制注入,但不得声称 AKE 能观察所有消息或保证检测任意完成语句。无法确认 Skill 已加载时如实说明。
/ake
- Apply triggers by phase and execute only the steps applicable to the current phase. A pre-task trigger performs retrieval and applicability assessment only; it does not initiate candidate capture. A post-task trigger first assesses capture value and evidence. When the user explicitly invokes , execute the phase requested by the user without being constrained by the conditions for automatic completion phrases. Continue to duplicate checking, candidate creation/revision, and independent-review requests only when the post-task assessment confirms that the result is evidence-based, reusable, and not already covered. If there is no value, report
/ake; if evidence is insufficient, report “Potential knowledge awaiting evidence.” Never force candidate creation.AKE · No new knowledge this time - Execute all applicable steps in the current phase as one continuous run. Do not ask “Should I continue?” between retrieval, applicability assessment, value/evidence assessment, duplicate checking, or qualified-candidate preparation/submission/reviewer requests. Wait only when an actual reviewer response or user publishing authorization is required. If an actual reviewer result cannot be awaited, report that honestly rather than fabricating a result. Existing permissions, security, validation, and status gates for candidate/submit/review/approve/publish are not relaxed by continuous execution.
- Automatic completion-phrase routing applies only to this one additional automatic signal: a substantive engineering task previously occurred, such as implementation, debugging, testing, architecture, or a risk-related change; this Skill was loaded; and the user subsequently explicitly says “validation OK,” “tests passed,” “no issues,” “acceptance passed,” or similar. This condition does not limit explicit invocations or existing applicable knowledge triggers. Ordinary Q&A, explanations, and conversations with no engineering output do not automatically enter the candidate workflow because of a completion phrase. Completion confirmation also does not constitute publishing authorization.
/ake - These message rules are model-level soft constraints, not host-level hard triggers. Ordinary-language messages cannot guarantee automatic loading of this Skill. Explicit may inject it through the host mechanism, but AKE must not claim that it observes every message or guarantees detection of arbitrary completion phrases. If it cannot confirm that the Skill was loaded, say so truthfully.
/ake
常用命令
Common Commands
node .ake/tools/scripts/ake.mjs candidate new --kind <note|defensive-pattern|postmortem|cookbook> --title <title> --author <actual-name> --target <path> --body <file>node .ake/tools/scripts/ake.mjs candidate submit <id>node .ake/tools/scripts/ake.mjs candidate check <id>- ;CLI verdict 不接受 PASS 标签
node .ake/tools/scripts/ake.mjs review <id> --reviewer <actual-reviewer> --verdict <approve|request-changes|reject> --notes <evidence> - 仅在用户明确授权发布后:,随后
node .ake/tools/scripts/ake.mjs approve <id> --by <human> --confirmpublish <id>
node .ake/tools/scripts/ake.mjs candidate new --kind <note|defensive-pattern|postmortem|cookbook> --title <title> --author <actual-name> --target <path> --body <file>node .ake/tools/scripts/ake.mjs candidate submit <id>node .ake/tools/scripts/ake.mjs candidate check <id>- ; the CLI verdict does not accept PASS labels
node .ake/tools/scripts/ake.mjs review <id> --reviewer <actual-reviewer> --verdict <approve|request-changes|reject> --notes <evidence> - Only after explicit user authorization to publish: , followed by
node .ake/tools/scripts/ake.mjs approve <id> --by <human> --confirmpublish <id>
用户可见最终报告
User-Visible Final Report
任务结束时简要填写,不隐去未验证项:
text
AKE 知识流程
- 检索:<关键词>;命中 <类别/文档及适用性>,或未找到
- 沉淀:<Agent Note | Defensive Pattern | Postmortem | Cookbook + 标题/目标>;若潜在知识待补证据,写明证据缺口/验证路径;仅确无可复用结果时写「AKE · 本次无新增知识」
- 检查/审核:<candidate check 结果;独立 reviewer 实际结果,或独立审核不可用并暂停>
- 授权/发布:<用户明确授权后发布,或未授权/未完成审核而保持未发布及原因;候选状态>
- 验证:<实际运行的命令与结果>
- 风险/未验证:<剩余事项>At the end of the task, briefly complete the following report without omitting unverified items:
text
AKE Knowledge Workflow
- Retrieval: <keywords>; matched <category/document and applicability>, or not found
- Capture: <Agent Note | Defensive Pattern | Postmortem | Cookbook + title/target>; if potential knowledge is awaiting evidence, specify the evidence gaps/validation path; write “AKE · No new knowledge this time” only when there is genuinely no new reusable result
- Check/Review: <candidate check result; independent reviewer’s actual result, or independent review unavailable and paused>
- Authorization/Publishing: <published after explicit user authorization, or left unpublished because authorization/review was incomplete, with the reason; candidate status>
- Verification: <commands actually run and their results>
- Risks/Unverified: <remaining items>边界
Boundaries
AKE 是流程和工具层,不是安全边界。普通文件/shell 工具可绕过流程;身份无法验证,自动授权标记不证明人类授权或审核者真实独立。发布仅对经 CLI 处理的候选执行绑定、格式、目标与漂移检查。
AKE is a process and tooling layer, not a security boundary. Ordinary file/shell tools can bypass the workflow; identities cannot be verified, and automatic authorization markers do not prove human authorization or genuine reviewer independence. Publishing applies only to candidates processed through the CLI and performs binding, format, target, and drift checks.