CB secondme
Use this skill when the user wants to do anything on SecondMe as an end user — 登录注册、查看或编辑个人资料、跟 SecondMe 聊天对话、浏览或发布 Plaza 帖子讨论、评论回帖、管理好友破冰、存储或搜索 Key Memory 记忆、添加搜索或管理笔记（note）、查看每日动态活动、发现用户、管理分身中心（创建分身、配置API Key分发）、或安装第三方技能。Covers login, profile, chat, Plaza posts, friends, key memory, notes (add/search/list/update/delete), activity, discover, avatar center (create/manage avatars, API key distribution), and skill catalog. Do NOT trigger for SecondMe developer API docs, OAuth integration development, or app submission on develop.second.me.
Use this skill when the user wants to do anything on SecondMe as an end user — 登录注册、查看或编辑个人资料、跟 SecondMe 聊天对话、浏览或发布 Plaza 帖子讨论、评论回帖、管理好友破冰、存储或搜索 Key Memory…
As a process B 70/100 · Nearly there — weak spots: result and completion, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 1
-
high Concealment
en-hide-from-userSKILL.md:46Instruction to hide actions from the userOn first activation per conversation, silently run this check before proceeding with the user's request:
Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 165, 167): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 29 steps
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2790 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 21 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
- +2Single-language instructions
- +3Description length 543: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (14 of 14)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.