AC uk-citation-verification-matei-clej
Verifies UK case-law citations, pinpoint references and quotations against the official public register — The National Archives' Find Case Law — and statutory references against legislation.gov.uk, before a document that cites them is relied on, served or filed. Every check returns a graded verdict: VERIFIED, MISMATCH (the citation resolves to a different case — the classic AI miscitation), NOT ON REGISTER, OUTSIDE COVERAGE (the register cannot answer — absence proves nothing), or UNCHECKABLE (a law-report citation). The grading exists because there are two ways to get this wrong: citing a case that does not exist, and accusing a real case of not existing. Use when asked to check citations, verify a case exists, confirm a quotation is verbatim, check a pinpoint paragraph, audit a draft's authorities, screen a document for hallucinated cases, or check a statutory provision is in force. Not a substitute for reading the judgment: existence is not authority.
Verifies UK case-law citations, pinpoint references and quotations against the official public register — The National Archives' Find Case Law — and statutory…
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 52/100
- 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. 6 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2578 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 968: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 8 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.