AB parallect
Deep research using Parallect.ai. Queries multiple AI research providers (Perplexity, Gemini, OpenAI, Grok, Anthropic) in parallel, then synthesizes results into a unified report with cross-referenced citations and conflict resolution. Use when the user wants to research a topic, investigate a question, or needs comprehensive analysis with citations. Also triggers when the user says things like "look this up", "research this", "find out about", "deep dive on", or "what do we know about". Do NOT use for simple factual questions you can answer from memory -- only for topics requiring sourced, multi-perspective analysis.
As a process B 70/100 · Nearly there — weak spots: result and completion, inputs and preconditions, consistency
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 70/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (parallect) differs from the folder (parallect-ai-deep-research)
- 100Tools and files. No external tools needed
- 100Steps. 53 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 15 branches, has a failure section
- 100Execution cost. Instruction body is 2934 tokens
- 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
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 625: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 53 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.