AF search-harvester
Candidate discovery for link building and outreach. Harvests candidate URLs from DuckDuckGo HTML and Marginalia through a local privacy-preserving Tor circuit (server IP never contacts the engine), then dedupes, triages liveness/anti-bot barriers, and exports a scored candidate list. DISCOVERY ONLY — this skill never submits forms, posts listings, or performs any state-changing action on third-party sites. Use ONLY when the user explicitly asks to find directories, submission platforms, blogs, or link-building candidates (e.g. "find more places to submit", "find directories", "get candidate websites like scrapebox", "search for link building opportunities"). Requires explicit user confirmation before routing any query through Tor; never for generic web search, never for sensitive/personal queries.
Candidate discovery for link building and outreach.
As a process F 45/100 · Will not run — References files that are not bundled: references/clawhub-publishing.md
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/clawhub-publishing.md
Process rating: all ten parameters 45/100
- 0Tools and files. 1 referenced file(s) missing: references/clawhub-publishing.md
- 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. 9 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 4761 tokens
- 85Steps. 41 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 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
- +3Description length 808: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 14 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (5 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.