AC cm-dagster-pipeline-analyzer
Analyze Dagster pipelines and software-defined assets for quality, scheduling, partitioning, IO managers, resource configuration, and observability. Checks asset dependencies, freshness policies, group structure, sensor/schedule configuration, and operational best practices. Use when asked to review Dagster code, audit asset graphs, check Dagster best practices, analyze partition strategies, review IO managers, or optimize Dagster deployments. Triggers on "dagster", "software-defined assets", "dagster assets", "dagster pipeline", "dagster schedule", "dagster sensor", "dagster partition", "io manager", "dagster resources", "dagster ops", "dagster jobs", "asset graph".
As a process C 60/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, 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: 2. 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 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (cm-dagster-pipeline-analyzer) differs from the folder (dagster-pipeline-analyzer)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 11 steps
- 100Execution cost. Instruction body is 1655 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)
- +1No license
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +3Description length 675: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 11 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.