AD aky-public-opinion
Professional-grade Chinese social media sentiment analysis report writer for government and enterprise use. Generates structured public opinion analysis reports covering risk assessment, communication data analysis, and actionable countermeasures. Supports 5 daily report types and 5 special event types including International Pressure, Diplomatic Sensitivity, and Ethnic/Ideological analysis. Enhanced with multi-tool international media collection: X.com trending (x-news-daily), headless browser scraping (agent-browser), built-in browser automation (browser-automation), web_fetch, and web_search for comprehensive international media information gathering and cross-validation. Use when the user asks: write a sentiment analysis report, analyze public opinion risk, do sentiment assessment, monthly sentiment summary, or any event requiring international public opinion tracking.
Professional-grade Chinese social media sentiment analysis report writer for government and enterprise use.
As a process D 45/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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: 5. 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 45/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (aky-public-opinion) differs from the folder (aky-publicopinion)
- 60Tools and files. Uses tools (web, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 74 steps, 1 vague phrases
- 100Execution cost. Instruction body is 3626 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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)
- +3Description length 885: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 33 headings
- +3Step-by-step instructions: 74 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.