AB eric-b2b-lead-generation
B2B Lead Generation Assistant. Activated when users say 'I want to sell XXX', 'Help me find customers', 'Analyze competitors', or 'Discover opportunities'. Automatically identifies competitors, discovers potential customers through connection mining, scores and enriches leads, and generates personalized BD materials. Supports 6-phase standardized workflow: Config Generation → Information Collection → Lead Scoring → Data Enrichment → BD Material Generation → Output Delivery.
As a process B 68/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
body-longSKILL.md body ≈ 8878 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 40Execution cost. Instruction body is 8878 tokens: crowds the task out of the window
- 65Failures and branches. 3 branches
- 100Tools and files. No external tools needed
- 100Steps. 118 steps
- 100Result and completion. Output format and completion criterion are stated
- 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 12 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -257 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 478: enough signal without eating the budget
- +4Structure: 72 headings
- +3Step-by-step instructions: 118 items
- +3Output format is stated explicitly
- +4Has examples (48 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.