AC notify-hub
让 Agent 的产出自动送到你眼前：选股扫描、监控告警、日报周报，一键推送到飞书/企业微信/钉钉/Slack/Telegram/邮件群。 This skill should be used when the user wants to send a message — text, structured card, or file — to one or more destinations across Feishu (飞书), WeCom (企业微信), DingTalk (钉钉), Slack, Telegram, or email, especially when the same content should be broadcast to multiple channels at once. 同一张卡片自动降级渲染： 飞书完整卡片、企微/钉钉转文本对齐、Slack 转 blocks、邮件转 HTML 表格，支持 --dry-run 零配置预览。 It only handles the "dispatch" step; the content is defined by the caller, so it pairs with any report/alerts/reminder workflow. Trigger when the user asks to 推送/发送/通知/广播 到 飞书/企业微信/钉钉/Slack/Telegram/邮件、 统一通知、多通道推送、群消息自动化、定时提醒、选股结果推送、监控告警推送、日报推送.
As a process C 57/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice
How to improve
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Exfiltration
exfil-webhook-urlreferences/channels-schema.md:13Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation table row; the skill's own vendor host)| Slack | `slack` | `https://hooks.slack.com/services/{T}/{B}/{X}` | `url` | 无（URL 即鉴权） |tablevendor-host -
low Exfiltration
exfil-webhook-urlreferences/channels-schema.md:14Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation table row; the skill's own vendor host)| Telegram | `telegram` | `https://api.telegram.org/bot{token}/{method}` | `token`, `chat_id` | 无（token 在 URL） |tablevendor-host -
low Exfiltration
exfil-webhook-urlscripts/channels/telegram.py:20Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host; quoted — discussed, not commanded)return f"https://api.telegram.org/bot{token}/{method}"vendor-hostquoted
Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 796 tokens
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 679: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 2)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.