AC search
Search the web via the Bright Data CLI — `bdata search` for Google/Bing/Yandex SERP, `bdata discover` for intent-ranked semantic results. Use when the user wants SERP results, needs URLs to feed into scraping, or wants semantic web discovery with optional page content. Hands off to `scrape` once target URLs are chosen, and to `data-feeds` when the user wants structured data from a known platform. Requires the Bright Data CLI; proactively guides install + login if missing.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 5. 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 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (search) differs from the folder (brightdata-search)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 27 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 1351 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (5 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
- +1No license
- +2Single-language instructions
- +3Description length 476: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.