BD bidding-due-diligence
招投标尽职调查助手（投资/合作/并购前的轻尽调）。当用户给出一个公司主体，想在投资、并购、合作、签约前做尽职调查、核实经营实态时，必须使用此SKILL：企业尽调、轻尽调、投资标的初筛、经营实态核验（中标合同流水是否活跃）、订单走势分析（逐年增长还是萎缩）、客户结构与大客户依赖度、履约能力评估、公开涉诉与行政处罚检索。基于全网招投标数据输出报告：经营实态用真实发生的中标合同流水说话、客户关系是真实合同关系、风险信息逐条附来源链接。支持单公司深度报告与双公司对比。即使用户没有提到「尽调」，只要想在投钱或合作前搞清楚一家公司的真实经营状况，都应使用本SKILL。注意边界：若用户给出一个具体的招标项目做该不该投的决策分析，使用 zlbx-bid-decision SKILL；若用户想主动挖掘商机/销售线索，使用 zlbx-opportunity-radar SKILL；若用户只是搜索/查询招中标公告数据，使用 zlbx-bidding SKILL。
招投标尽职调查助手（投资/合作/并购前的轻尽调）。当用户给出一个公司主体，想在投资、并购、合作、签约前做尽职调查、核实经营实态时，必须使用此SKILL：企业尽调、轻尽调、投资标的初筛、经营实态核验（中标合同流水是否活跃）、订单走势分析（逐年增长还是萎缩）、客户结构与大客户依赖度、履约能力评估、公开涉诉与行政处罚检索。…
As a process D 46/100 · 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Exfiltration
net-credential-usereferences/auto-register.md:215Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)**如果当前 api_key 来自 `$ZLBX_API_KEY`**：跳过 SID 流程，提示用户访问 `https://ai.zhiliaobiaoxun.com/?ch=s126` 手动登录充值。
quoted -
low Obfuscation
obf-base64-blobscripts/render_report.py:93Long base64-looking blob (quoted — discussed, not commanded)_LOGO_B64 = "iVBO…B5x
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/render_report.py:93High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)_LOGO_B64 = "iVBO…B5x
quoted
Files scanned: 7. 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 (web) that frontmatter does not declare
- 100Steps. 40 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1987 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 426: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.