AC powerdrill-data-analysis
This skill should be used when the user wants to analyze, explore, visualize, or query data using Powerdrill. Covers listing, creating, and deleting datasets; uploading local files as data sources; creating analysis sessions; running natural-language data analysis queries; and retrieving charts, tables, and insights. Triggers on requests like "analyze my data", "query my dataset", "upload this file for analysis", "list my datasets", "create a dataset", "visualize sales trends", "continue my previous analysis", "delete this dataset", or any data exploration task mentioning Powerdrill.
As a process C 62/100 · Has gaps — weak spots: result and completion, consistency, running it twice
The same skill appears in 1 more place: ClawHub
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: 4. 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 62/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 19 mutating operations with no state check
- 40Consistency. Frontmatter name (powerdrill-data-analysis) differs from the folder (powerdrill-data-analysis-skill)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 22 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 2418 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 590: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (18 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.