AF search-harvester
ScrapeBox-style candidate discovery for link building and outreach. Rotates Tor exit nodes (and optionally public HTTP proxies) so the server's datacenter IP never touches the search engine, harvests candidate URLs from multiple engines (DuckDuckGo html, Marginalia), dedupes, triages liveness/barriers, and exports a scored candidate list. Use when the user says "find more places to submit", "find directories", "scrape search results", "get candidate websites like scrapebox", "search for link building opportunities" — or whenever direct search from the server IP gets captcha/bot-blocked (Google, Brave, DuckDuckGo, Bing all block datacenter IPs).
ScrapeBox-style candidate discovery for link building and outreach.
As a process F 44/100 · Will not run — References files that are not bundled: scripts/search-harvester.py
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/search-harvester.py
Process rating: all ten parameters 44/100
- 0Tools and files. 1 referenced file(s) missing: scripts/search-harvester.py
- 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 (search-harvester) differs from the folder (scraper-skill-main)
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 25 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2081 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 13 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 652: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (6 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.