BC apify-link-prospecting-outreach
Find sites ranking for target keywords, score every prospect with Ahrefs domain authority and page-level traffic, identify the strongest pitch angle per row ("links to competitor", "mentions brand without linking", "top-3 SERP", "resource page", "outdated content"), generate brand-voice-matched outreach emails using an outreach-type-aware template (unlinked-mention claim, competitor-link replacement, resource-page inclusion, outdated-content replacement, topical niche-edit), and propose a concrete in-article link placement as three artifacts — the verbatim source sentence, the same sentence rewritten with the link spliced in, or a fully-drafted new insertion if no natural fit exists. Use when user asks to find link building opportunities, prospect link partners, recover unlinked brand mentions, replace competitor links, build a tiered outreach list, or run cold email outreach for SEO link building.
Find sites ranking for target keywords, score every prospect with Ahrefs domain authority and page-level traffic, identify the strongest pitch angle per row…
As a process C 51/100 · Has gaps — References files that are not bundled: campaign.json.example, URL
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10236 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: campaign.json.example - warning
missing-refreference to a missing file: URL - note
frontmatter-keyunknown frontmatter key "author_url" - note
edit-residuethe text marks something as outdated (lines 235): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 51/100
- 0Tools and files. 2 referenced file(s) missing: campaign.json.example, URL
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 24 mutating operations with no state check
- 40Execution cost. Instruction body is 10236 tokens: crowds the task out of the window
- 60Steps. 67 steps, 5 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 9 branches, has a failure section
- 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 The skill ranks results itself: that belongs to the system behind the tool, not the model
- low The response is described with custom markup (10 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 911: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 15 headings
- +3Step-by-step instructions: 67 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 7 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.