AB prospecting
When the user wants to find, qualify, and build a list of prospects to reach out to, across B2B SaaS, general B2B, or local small businesses. Also use when the user mentions "prospecting," "build a prospect list," "find leads," "lead list," "outbound list," "target account list," "ICP-fit accounts," "find local businesses," "find my first customers," "design partners," "signal-based outbound," "buying signals," "intent data," "job change alerts," "waterfall enrichment," "Clay table," "lookalike accounts," "catch-all emails," "account tiering," or "research this account before I reach out." Always verify emails before they reach a sequence, and never scrape LinkedIn. Define audiences in Sales Navigator and pull contacts from licensed data. Covers list building, signals, enrichment, verification, and account research. For the outreach itself (copy, sending setup, LinkedIn, cadences, replies), see cold-email. For researching competitors, see competitor-profiling.
When the user wants to find, qualify, and build a list of prospects to reach out to, across B2B SaaS, general B2B, or local small businesses.
As a process B 68/100 · Nearly there — weak spots: running it twice, progress reporting
How to improve
- 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: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 9): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 68/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 6 branches
- 70Execution cost. Instruction body is 4751 tokens
- 85Steps. 64 steps, 3 vague phrases
- 100Consistency. Name and required fields are in place
- 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
- low No test case covers injection arriving through data
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 974: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 20 example trigger phrases
- +4Structure: 22 headings
- +3Step-by-step instructions: 64 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.