AC brd-browser-debug
Debug Bright Data Scraping Browser sessions using the Browser Sessions API. Use this skill when the user encounters a Bright Data browser session error, puppeteer stack trace, failed scraper run, or asks about session bandwidth, duration, captchas, or connection issues. Also use when a Bright Data scraper produces unexpected results such as empty data, 0 items found, missing products, or fewer results than expected — session data can reveal whether the issue is network/proxy-side (blocks, captchas, redirects, timeouts) or client-side (selectors, extraction logic). Triggers on phrases like 'why did my session fail', 'debug my bright data session', 'check my scraping browser sessions', 'how much bandwidth did my scraper use', 'got 0 results', 'found 0', 'scraper returned empty', 'scraper not working', 'script didn't work', or when a Bright Data error code or brd.superproxy.io stack trace appears in the conversation. Requires BRIGHTDATA_API_KEY environment variable.
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: 2. 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
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (brd-browser-debug) differs from the folder (brightdata-brd-browser-debug)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 37 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 1709 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (4 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)
- +3Description length 977: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.