AB brightdata-research
Use when the user asks to batch-search candidates, verify public web evidence, dedupe results, and organize them into Feishu/Lark docs. Use especially for requests like "继续搜更多并追加到飞书", "帮我批量找一批候选并整理到飞书", "搜索+抓取+汇总+落文档/落表", "帮我调研一批XX平台", "扩展候选池", even if the user does not explicitly name this skill. Also use when the user says "检查飞书文档里有没有重复" or "去重" in the context of a research document — this skill covers dedup-and-cleanup as a sub-workflow. Do NOT use for: single-page summaries, one-off Q&A, pure code tasks, or tasks that don't involve batch research + structured output.
As a process B 69/100 · Nearly there — weak spots: result and completion, progress reporting
How to improve
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 69/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 80 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1259 tokens
- 100Running it twice. No mutating operations
- medium 9 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 577: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 80 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.