AB retraction-watcher
Automatically scan document reference lists and check against Retraction.
As a process B 78/100 · Nearly there — no weak spots found
How to improve
For the model run — optional
- 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
- note
frontmatter-keyunknown frontmatter key "skill-author"
Process rating: all ten parameters 78/100
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 60 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2799 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 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 73: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 19 headings
- +3Step-by-step instructions: 60 items
- +3Output format is stated explicitly
- +4Has examples (5 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: 91.
External checks
ClawHub: clean
The skill does what it claims: it checks academic references against external retraction databases, but users should avoid confidential documents and untrusted PDFs unless the dependency risks are addressed.
LLM: benign (high) · VirusTotal: · 29 May 2026