AB infoseek-en
Deep web information search and archival skill for comprehensive research on persons, organizations, or products. Uses multiple search engines (Baidu, Tavily, Multi-Search-Engine) plus browser-based content extraction. Features URL-normalized deduplication with SQLite database, structured file storage with complete metadata, ad/content filtering, and customizable output formats (md/json/txt/csv/xlsx/html/docx). Automatically creates organized folders per subject. Enforces strict deletion policy (recycle bin only, user confirmation required). Use when: user needs comprehensive information gathering, background research, due diligence, media monitoring, competitive intelligence, or building information archives about specific subjects. Triggers: infoseek, deep search, information gathering, background check, media monitoring, archive search, research person, research company, competitive analysis, dossier building.
As a process B 67/100 · Nearly there — weak spots: when it triggers, consistency, running it twice
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 3. 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 67/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 17 mutating operations with no state check
- 40Consistency. Frontmatter name (infoseek-en) differs from the folder (infoseek)
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 44 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 1679 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 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)
- +3Description length 926: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 21 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.