AB apify-influencer-brand-collabs
Discover Instagram brand–creator partnerships by chaining Apify Actors. Use when the user asks who collabs with a brand, which brands a creator has done paid posts for, wants to audit an influencer's branded-content history, or wants to scope a brand's sponsorship roster. **Triggers:** - "who collabs with [brand] on Instagram?" - "what brands has [creator] done sponsored posts for?" - "find paid partnerships / branded content for [handle]" - "audit [influencer]'s brand deals" - "show me [brand]'s influencer roster" Works in either direction — brand → creators or creator → brands — and detects direction from the data, so don't ask the user to declare it. Requires Apify MCP tools.
Discover Instagram brand–creator partnerships by chaining Apify Actors.
As a process B 71/100 · Nearly there — weak spots: result and completion
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
- note
frontmatter-keyunknown frontmatter key "author_url"
Process rating: all ten parameters 71/100
- 0Result and completion. Does not say what the result is
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 23 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1511 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 689: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.