AD find-china-cdc-health-report
Locate, verify, optionally download, and extract five official China CDC report types: China influenza weekly reports, acute respiratory infectious-disease sentinel weekly reports, national COVID-19 monthly updates, global infectious-disease event risk assessments, and China key-infectious-disease/public-health-emergency risk assessments. Use for a named report type plus week, month, issue, publication/reference date, latest, official PDF, report content, table, chart, summary, or comparison. Do not use for medical advice, prediction, third-party reports, or unregistered sources.
Locate, verify, optionally download, and extract five official China CDC report types: China influenza weekly reports, acute respiratory infectious-disease…
As a process D 47/100 · Unfinished process — 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Secrets in code
secret-high-entropy-tokenreferences/output-schema.md:17High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"report_id": "infl…917",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/report-schema.md:8High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"report_id": "infl…917",
quoted
Files scanned: 21. 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 47/100
- 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
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (find-china-cdc-health-report) differs from the folder (cdc-data)
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 44 steps
- 100Execution cost. Instruction body is 1837 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 586: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 44 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (9 of 10)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.