BC apify-blocked-scrape-triage
Diagnose and recover a scrape that is blocked, throttled, or served empty or partial content, in cost order, before paying for a heavier Actor. Use when a run returns 0 items, when a site answers 403, 429 or a challenge page, when the HTML comes back empty or truncated, when a request fails with no response at all, when the page shows data in a browser that the Actor does not see, or when a scraper that worked yesterday suddenly returns nothing. Triggers - "I'm getting blocked", "403 from the site", "429 rate limited", "Cloudflare challenge", "scraper returns empty results", "connection reset", "page loads in my browser but not in the Actor", "do I need residential proxies", "should I switch to a browser", "my scraper broke overnight". Escalates in cost order - a cheaper published source first, then reachability, request rate and IP spread, request fidelity, session tokens, the site's own internal API, browser last.
Diagnose and recover a scrape that is blocked, throttled, or served empty or partial content, in cost order, before paying for a heavier Actor.
As a process C 62/100 · Has gaps — weak spots: result and completion, when it triggers, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
- warning
body-longSKILL.md body ≈ 11764 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "author_url"
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 40Execution cost. Instruction body is 11764 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 51 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 929: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Structure: 16 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.