AC Market Radar
Industry hotspot and competitor monitoring across 5 dimensions. Use when user (in Chinese) asks to monitor an industry (监测...行业) and provides competitor URLs. Systematically browses international English sources using agent-browser, runs a 5-dimension scan (brand activity, visual identity, brand positioning, content hotspots, strategic signals) on each competitor, then delivers a structured Chinese daily-brief with brand alerts and role-based action recommendations via Telegram.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "read_when"
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (Market Radar) differs from the folder (market-radar)
- 50When it triggers. No condition that starts the skill
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 55 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 1934 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)
- +3Output format is not stated: the model decides each time
- -226 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 483: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 55 items
- +4Has examples (13 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.