AD agent-notify
让 agent（Claude Code / Codex / Hermes / OpenClaw 通用）干完活主动播报到语音设备（小智音箱、机器人等）。守护进程读会话记录判断任务状态，完成或卡死时把「任务名+状态+时间」拼成中文播报句推给后台。首次使用需配置后台 WebSocket 地址、设备 MAC、授权码。【服务器端后台设计重点】① 一个 WS 端点即可，握手首帧收 {"mac","code"}，回 {"type":"auth","ok":true} 或 ok:false + error（建议区分 invalid_code 与 session_not_found，客户端会把原文透传给用户）；② 只处理 type=="task_status" 的帧，直接取现成的 text 字段丢 TTS，其余 type 静默忽略——注意静默丢弃在协议层零反馈，排障时极难定位；③ 鉴权铁律：播给哪台设备必须由 code 反查绑定关系，绝不信任请求体里的 mac，否则任何拿到 token 的人改个 MAC 就能往别人设备推送；④ 设备离线是常态而非边界情况（小智类设备约两分钟无人声即断连），后台需要 pending 队列在设备重连后补播并设 TTL，否则大部分通知会蒸发；⑤ 30 秒 ping/pong 保活，客户端断线指数退避重连、握手被拒则不重连；⑥ 播报文案由客户端拼好（状态已译成中文、ISO 时间已转成"下午2点05分"），后台不必二次加工。Triggers 触发词：任务播报, 干完告诉我, 通知机器人, 语音播报, agent-notify, 配置播报, 开启播报, 停止播报, 停止这个skill, 关闭后台监听, 播报状态, 小智播报。
让 agent（Claude Code / Codex / Hermes / OpenClaw 通用）干完活主动播报到语音设备（小智音箱、机器人等）。守护进程读会话记录判断任务状态，完成或卡死时把「任务名+状态+时间」拼成中文播报句推给后台。首次使用需配置后台 WebSocket 地址、设备…
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 5 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1164 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 726: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 5 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.