BB flashrev-ai-enrich
Use this skill when an AI agent needs to enrich a CSV lead list through the flashrev-ai-enrich npm CLI. Triggers on list enrichment, filling missing company or person fields, verifying or unlocking emails and phones, finding CEOs, executives, LinkedIn posts, matching companies or people to FlashRev IDs, Google search/news/maps lookups, scraping a page, or running an LLM over each row. Agents must run with `FLASHREV_ENRICH_AI_MODE=1`, call `schema --json`, use only live `funcName` values, and invoke each command with explicit `--capability FUNC_NAME --map ... --output ...`. For broad person enrich requests, run a profile + contact pipeline when supported; for contact-only requests, run only the requested contact capability. Avoid `--prompt` unless explicitly requested. Dry-run and sample preview are required before live runs unless already authorized.
Triggers on list enrichment, filling missing company or person fields, verifying or unlocking emails and phones, finding CEOs, executives, LinkedIn posts…
As a process B 69/100 · Nearly there — weak spots: result and completion, running it twice
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6569 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 69/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 12 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6569 tokens
- 85Steps. 75 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 7 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 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 862: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +4Structure: 21 headings
- +3Step-by-step instructions: 75 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.