AB cite-holmes
Cite Holmes — deep research that interrogates its own sources (Verified Deep Research). Calibrates scope first (asks 3-5 sharp questions), plans sub-questions, searches iteratively across sources and languages, then machine-verifies every citation (five states: verified/partial/unverified/unreachable/invalid) before a confidence-graded report ships. Never outputs unverified references; treats fabricated DOIs, dead links and missing sources as first-class catch targets. Use whenever the user asks to "deep research", "look into", "investigate", "compare A vs B", "fact check", "verify this claim", "is it true that...", "check these references", "are these citations real", wants a research report with sources, or needs reliable multi-source answers — even if they never say the word "research".
Cite Holmes — deep research that interrogates its own sources (Verified Deep Research).
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, running it twice, 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: 9. 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 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 11 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1136 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
- +4Description does not say when NOT to use the skill (false activations)
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +3Description length 800: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 11 items
- +3Output format is stated explicitly
- +4Has examples (1 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: 100.