AF paper-analysis-evidence
structured academic paper analysis from local paper files or paper urls, adapted from a dify scheme a workflow. use when the user asks to analyze pdf/docx/text/html academic papers, extract title/task/background/problem/method/datasets/baselines/metrics/results/ablations/limitations/contributions, cite evidence spans, verify consistency against the original paper, or export paper analysis reports. supports chinese or english outputs and saves downloaded inputs, intermediate files, generated json, markdown, html, and docx reports under the ubuntu desktop.
As a process F 52/100 · Will not run — References files that are not bundled: references/dify_scheme_a_source.yml
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/dify_scheme_a_source.yml
Process rating: all ten parameters 52/100
- 0Tools and files. 1 referenced file(s) missing: references/dify_scheme_a_source.yml
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (paper-analysis-evidence) differs from the folder (paper-summary-json)
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 35 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 1338 tokens
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 560: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.