AC outclaw-research
Deeply research a specific person or organisation for B2B outreach. Pulls from every outreach-relevant tool in the user's inventory (Leadbay/LeadClaw, LinkedIn, Twitter/X, web search, company pages, podcasts, news) and writes a persistent profile into the OutClaw knowledge base. Also useful for discovery ("find me a promising lead at <company>" via Leadbay). Triggers on: 'research <person|company>', 'look up <person>', 'who is <person>', 'find <person>'s email|linkedin|phone|company', 'tell me about <company|person>', 'enrich <person>', 'pull a lead', 'surface a prospect'. Normally invoked by the outclaw orchestrator.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 4921 tokens
- 85Steps. 58 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 15 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
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (26 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 625: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 58 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.