AC market-research
Conducts market research and industry analysis by searching for reports, news, trends, and market data. Use when the user mentions 'market research,' 'industry analysis,' 'market size,' 'market trends,' 'TAM,' 'total addressable market,' 'market landscape,' 'industry report,' 'market opportunity,' 'market sizing,' 'SAM,' 'SOM,' 'industry overview,' or 'how big is the market.' This skill uses web search to gather and synthesize market intelligence -- for company-specific research, see exa-company-research; for competitor analysis, see competitive-intelligence. Triggers on market and industry analysis intent, not individual company research. See competitive-intelligence for competitor-focused analysis, see content-strategy for content market research.
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, consistency, progress reporting
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (market-research) differs from the folder (abm-market-research)
- 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
- 70Failures and branches. 4 branches
- 100Steps. 33 steps
- 100Execution cost. Instruction body is 1567 tokens
- 100Running it twice. No mutating operations
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)
- +1No license
- +2Single-language instructions
- +3Description length 759: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 33 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.