CD pubmed-verifier
Reference checker for AI-fabricated citations: batch-verify PMIDs against PubMed and catch the hallucination existence checks miss — a REAL PMID pointing to a DIFFERENT paper. Five-state citation verification (correct / mismatch / partial / invalid / unknown), citation-context parsing, Crossref DOI cross-check, retraction detection (capped at partial), correct-PMID suggestion, arXiv ID verification, plain-text reference list parsing, formatted reference lists (GB/T 7714 / Vancouver / APA / AMA), OpenAlex DOI fallback for non-Crossref registries, Chinese-reference title search, CSV/JSON claims, HTML/JSON/text reports. Four data sources: NCBI, Europe PMC fallback, Crossref, OpenAlex. Network failures are honestly reported as unverified, never as "not found". Zero dependencies, runs fully local. Triggers: verify PMIDs, check citations, citation audit, reference check, PMID check, batch verify references, AI hallucination detection, verify DOI, DOI check, citation formatting, reference formatter, GB/T 7714.
Reference checker for AI-fabricated citations: batch-verify PMIDs against PubMed and catch the hallucination existence checks miss — a REAL PMID pointing to a…
As a process D 46/100 · Unfinished process — References files that are not bundled: examples/refs.sample.bib, examples/refs.sample.ris
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10648 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: examples/refs.sample.bib - warning
missing-refreference to a missing file: examples/refs.sample.ris
Process rating: all ten parameters 46/100
- 0Tools and files. 2 referenced file(s) missing: examples/refs.sample.bib, examples/refs.sample.ris
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 10 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 40Execution cost. Instruction body is 10648 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Steps. 101 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 38 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 1018: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -216 emoji in the instructions: noise for the model
- +2Single-language instructions
- +4Structure: 40 headings
- +3Step-by-step instructions: 101 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.