BD fork-latte-skill
报名/登记信息收集 agent（中转服务模式）。触发词：「ping」。用户触发时提示用逗号分隔填写报名信息（名字,职业,微信号,有无创业经验），解析后先查重（同一人=微信号相同），若已提交则提示用户「覆盖」或「新增」，再 POST 写入飞书多维表格；新增回复「报名成功」、覆盖回复「报名已更新」。飞书凭证仅存于中转服务端，客户端零敏感信息。需中转服务 endpoint 配置在 relay-server/config.json。
报名/登记信息收集 agent（中转服务模式）。触发词：「ping」。用户触发时提示用逗号分隔填写报名信息（名字,职业,微信号,有无创业经验），解析后先查重（同一人=微信号相同），若已提交则提示用户「覆盖」或「新增」，再 POST…
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Secrets in code
secret-high-entropy-tokenrelay-server/config.example.json:1High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded){"endpoint":"http://loca…000/api/signup","api_key":"jcc_…Z68"}fixturequoted -
low Secrets in code
secret-high-entropy-tokenrelay-server/config.json:1High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded){"endpoint":"http://loca…000/api/signup","api_key":"jcc_…Z68"}quoted -
low Exfiltration
read-dotenvrelay-server/README.md:18Reads a .env filecp .env.example .env
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:22High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- `api_key` = `jcc_…Z68`
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:34High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- `api_key` = `jcc_…Z68`
quoted
Files scanned: 9. 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 43/100
- 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
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 34 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1363 tokens
- low The response is described with custom markup (3 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 214: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.