BF llm-daily-digest
生成一份当日 LLM / 大模型领域的中文资讯简报。采集来源包括：**8 家头部厂商官方博客**（海外：OpenAI / Anthropic / Google DeepMind / Meta AI / xAI / Mistral；国内：DeepSeek / 通义千问 Qwen —— 最高优先级一手源）、GitHub Trending、arXiv（cs.CL / cs.AI / cs.LG / cs.CV）、Hugging Face、Papers With Code、Hacker News、X/Twitter、以及机器之心、量子位等中文媒体；覆盖四类内容：厂商官方发布、新开源项目、新论文、行业资讯/事件。只要用户说"跑一下今天的 AI 日报""生成大模型日报""今日大模型简报""总结一下今天 AI 动态""给我一份 LLM 快报""今天 AI 圈发生了啥""AI 圈今天有啥""看看今天大模型那边啥情况"，或被 cron 定时任务触发（触发消息中包含"日报""digest""brief"等关键字），都应使用此 skill。即使用户没说"日报"两个字，但表达出"整理今天 LLM 相关的项目/论文/新闻"意图的也应触发（例如"今天 HuggingFace 上有啥好东西""今天有什么 AI 新论文值得看""OpenAI / Anthropic / DeepSeek / Qwen 今天有啥新动态"）。产出是一份结构化 Markdown 文件，标题为 `🗣️ 今天 AI 圈发生了啥 · YYYY-MM-DD`，保存到 `~/.openclaw/workspace/digests/YYYY-MM-DD.md`，并在会话里附上文件路径和本日最值得看的 3 条精选。
As a process F 33/100 · Will not run — References files that are not bundled: url, hn-url, src-url
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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: 3. 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") - warning
missing-refreference to a missing file: url - warning
missing-refreference to a missing file: hn-url - warning
missing-refreference to a missing file: src-url
Process rating: all ten parameters 33/100
- 0Tools and files. 3 referenced file(s) missing: url, hn-url, src-url
- 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
- 30Running it twice. 4 mutating operations with no state check
- 100Steps. 139 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3758 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -224 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 14 example trigger phrases
- +3Description length 736: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 139 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.