BC discovery-engine
Automatically discover novel, statistically validated patterns in tabular data. Find insights you'd otherwise miss, far faster and cheaper than doing it yourself (or prompting an agent to do it). Disco systematically searches for feature interactions, subgroup effects, and conditional relationships you wouldn't think to look for, validates each on hold-out data with FDR-corrected p-values, and checks every finding against academic literature for novelty. Returns structured patterns with conditions, effect sizes, citations, and novelty scores.
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 19. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 11937 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 17 mutating operations with no state check
- 40Execution cost. Instruction body is 11937 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 100Steps. 81 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 22 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 22 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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +3Description length 548: enough signal without eating the budget
- +4Structure: 48 headings
- +3Step-by-step instructions: 81 items
- +4Has examples (33 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.