BD mp2rss
Mp2rss CLI Skill —— 微信公众号 / X（Twitter）账号转 RSS 订阅与内容管理。 **当以下情况使用此 Skill**： (1) 用户要订阅 / 取消订阅 / 列出 / 搜索**微信公众号**：「订阅这个公众号 https://mp.weixin.qq.com/s/...」「我订阅了哪些公众号」「列一下我的公众号 RSS」「搜一下我订阅的财经类公众号」「取消订阅那个号」「把 <公众号名> 从订阅里删了」 (2) 用户要查**公众号历史文章**：「<公众号名> 最近发了什么」「拉一下 <公众号名> 的文章」「<公众号名> 的历史文章」 (3) 用户要操作 **X（Twitter）账号**：「我订阅了哪些 X 账号」「@elonmusk 最近发了啥」「拉一下某个 X 号的推文 / 长文」（注：X 的订阅 / 取消订阅仅在 Web 控制台，CLI 只能列出已订阅与拉内容） (4) 用户要管理**登录态**：「登录公众号 RSS 服务」「登出 mp2rss」「我的 Feed Key 是什么」「我在 mp2rss 里登录了吗」 (5) 用户要**安装 / 配置 Mp2rss CLI**：「装 mp2rss」「升级 mp2rss」「mp2rss 配置在哪里」
As a process D 45/100 · 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:97Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/areyoubugcoder/mp2rss-cli/main/scripts/install.sh | sh
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostreferences/install.md:27Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/areyoubugcoder/mp2rss-cli/main/scripts/install.sh | sh
Files scanned: 10. 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 45/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1720 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (10 tags): a typed call is more reliable
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
- -219 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 546: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.