AB apify-buying-signal-detection
Set up a recurring buying-signal detection pipeline that finds companies showing buying intent across three signal types — job postings (hiring for the persona), fundraising events (recent raises), and LinkedIn content (pain-point posts, hiring announcements) — then aggregates results into a deduplicated leads.csv with the signal source, evidence URL, and detection timestamp per row. Split-schedule architecture — Apify Actor Tasks pull raw data on their own cadence, a Claude-side aggregation task normalizes, deduplicates against a blacklist, and appends new leads with a weekly-idempotent guard. Use when the user says "find companies with buying signals", "detect intent signals for outbound", "set up a weekly lead pipeline", "monitor hiring signals for lead gen", "track startup funding leads", "find LinkedIn buying signals", "schedule Apify Actors for prospecting", "build a signals-based lead list", or "set up buying-intent monitoring for my ICP".
Set up a recurring buying-signal detection pipeline that finds companies showing buying intent across three signal types — job postings (hiring for the…
As a process B 68/100 · 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: 10. 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 68/100
- 0Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4773 tokens
- 85Steps. 37 steps, 3 vague phrases
- 100Failures and branches. 3 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
- 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 960: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 17 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.