AC research-agent
Deep research and analysis agent for any topic. Use when the user wants to research a topic, analyze competitors, evaluate technologies, compare tools, investigate trends, do market research, or get a comprehensive analysis of anything. Triggers on phrases like "research", "investigate", "analyze", "compare", "what is", "tell me about", "look into", "deep dive", "competitor analysis", "market research", "technology evaluation", "find alternatives", "landscape analysis", "pros and cons", "should I use". Produces structured research reports with sources.
As a process C 59/100 · Has gaps — weak spots: inputs and preconditions, consistency, 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 59/100
- 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
- 40Consistency. Frontmatter name (research-agent) differs from the folder (deep-research-agent)
- 55Failures and branches. 1 branches
- 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
- 100Steps. 48 steps
- 100Execution cost. Instruction body is 1325 tokens
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)
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +5Description quotes 15 example trigger phrases
- +3Description length 558: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 48 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.