AB research
Default entry point for any research request — a hybrid router that classifies the question deterministically and either delegates to a specialist research skill (pulse for trends/sentiment, grants for NIH funding, litreview for academic literature, syllabus for course reading, patent for prior-art + IP landscape, dossier for entity research, deepread for evidence-first reading of supplied documents) or runs its own plan-decompose-multi-source-search-synthesize-cite fallback workflow when no specialist matches. Always surfaces the routing decision so users can override. Use when the user makes any research request that doesn't obviously match a more-specific specialist skill (e.g., "research [topic]", "look into [topic]", "what do we know about [topic]", "investigate [topic]", "find me information on [topic]", "do some research on [topic]", "I need to understand [topic]"). Output is a markdown briefing (default) or .docx document (on request) with full citations and an audit log.
Default entry point for any research request — a hybrid router that classifies the question deterministically and either delegates to a specialist research…
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions
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: 7. 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 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (web) 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
- 70Execution cost. Instruction body is 4057 tokens
- 100Steps. 47 steps
- 100Failures and branches. 7 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 994: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 22 headings
- +3Step-by-step instructions: 47 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.