AA research-claim-ledger
Build source-backed research claim ledgers from drafts, literature matrices, notes, citation lists, PDFs, source packets, or reviewer comments. Use when the user needs to audit factual, numerical, causal, comparative, novelty, policy, or citation-dependent claims; find unsupported or overclaimed statements; prepare a supervisor/coauthor/shareable evidence receipt; repair a manuscript before submission; triage a literature review; or turn academic sources into a traceable claim-to-source table without running a full research-paper pipeline.
As a process A 80/100 · Runs to the end — weak spots: inputs and preconditions, progress reporting
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: 3. 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 80/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 6 branches
- 100Tools and files. No external tools needed
- 100Steps. 52 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1867 tokens
- 100Running it twice. Mutating operations check current state
- high The skill tells the model to perform an irreversible action with no human approval
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)
- +1No license
- +2Single-language instructions
- +3Description length 545: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 52 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.