BD multi-ai-feed
多平台AI信息源 — 一个 Skill 同时查询快手、公众号、B站、视频号、小红书五大平台的 AI 爆款内容，可指定单平台、多平台或全部平台。按各平台主指标（点赞/互动）筛选热门，智能聚类话题后生成一份统一的多平台 HTML 日报，含跨平台总览、跨平台话题对比、封面图、互动数据与平台筛选 Tab。同步对每平台 TOP 话题执行 AI 情报调查，采用多引擎搜索与交叉验证，输出带可信度标注的结构化调查报告。支持自定义关键词定向查询与每日订阅。⚠️快手/B站数据每日15:00更新前一天内容，公众号/视频号/小红书每日16:00更新，目标日期无数据时必须先告知用户并等待确认后才能调用接口，禁止自动获取。当用户需要多平台AI日报、跨平台AI热点、全网AI爆款，或AI快手日报、快手爆款、AI公众号日报、公众号爆款、AI-B站日报、B站爆款、AI视频号日报、视频号AI热点、AI小红书日报、小红书AI热点、各平台AI情报或自定义关键词查询时使用。
多平台AI信息源 — 一个 Skill 同时查询快手、公众号、B站、视频号、小红书五大平台的 AI 爆款内容，可指定单平台、多平台或全部平台。按各平台主指标（点赞/互动）筛选热门，智能聚类话题后生成一份统一的多平台 HTML 日报，含跨平台总览、跨平台话题对比、封面图、互动数据与平台筛选 Tab。同步对每平台…
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Dangerous commands
cmd-persistencescripts/feed_core.py:1734Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)f'(crontab -l 2>/dev/null | grep -v "{PLIST_LABEL}"; 'code literal -
low Dangerous commands
cmd-shell-rcscripts/feed_core.py:406Writes to a shell startup file (string literal in code, not executed)print(f" macOS/Linux (zsh): echo 'export {ENV_KEY}=ak_你的密钥' >> ~/.zshrc && source ~/.zshrc")code literal -
low Dangerous commands
cmd-shell-rcscripts/feed_core.py:407Writes to a shell startup file (detector / deny-list definition; string literal in code, not executed)print(f" macOS/Linux (bash): echo 'export {ENV_KEY}=ak_你的密钥' >> ~/.bashrc && source ~/.bashrc")detectorcode literal -
low Dangerous commands
cmd-cron-mentionscripts/feed_core.py:1734Mentions editing / listing crontab (string literal in code, not executed)f'(crontab -l 2>/dev/null | grep -v "{PLIST_LABEL}"; 'code literal -
low Dangerous commands
cmd-cron-mentionscripts/feed_core.py:1771Mentions editing / listing crontab (string literal in code, not executed)f'crontab -l 2>/dev/null | grep -v "{script_path}" | crontab -',code literal -
low Dangerous commands
cmd-cron-mentionscripts/feed_core.py:1777Mentions editing / listing crontab (string literal in code, not executed)warn("自动移除 crontab 失败，请手动执行: crontab -e")code literal -
low Dangerous commands
cmd-cron-mentionscripts/feed_core.py:1801Mentions editing / listing crontab (string literal in code, not executed)out = subprocess.run("crontab -l 2>/dev/null", shell=True, capture_output=True).stdout.decode()code literal
Files scanned: 12. 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 (bash) that frontmatter does not declare
- 100Steps. 29 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2865 tokens
- 100Running it twice. No mutating operations
- low 13 top-level sections: this looks like several domains in one skill
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
- -218 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 421: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.