CtrlK
BlogDocsLog inGet started
Tessl Logo

evilissimo/transformational-programming

Decompose problems into pipelines of data transformations. Refactors loops into map/filter/reduce chains, converts nested/OO logic into composable function sequences, designs multi-step data transformation pipelines. Trigger on: "transformational programming", "data pipeline", "function pipeline", "pipe operator", "|>", "stream processing", "chained transformations", "Unix pipes", "dataflow", "decompose into steps", "write this as a pipeline", "compose functions", "chain of transformations", or restructuring imperative/OO code into data transforms. NOT for ETL infrastructure or stream processing frameworks (Kafka, Flink) — focuses on code-level function composition and transformation design patterns.

94

1.19x
Quality

97%

Does it follow best practices?

Impact

85%

1.19x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-1/

{
  "context": "Tests whether the agent structures its pipeline decomposition response according to the prescribed output format: a '## Transformation Analysis' heading, a '### Data Flow' section with arrow notation, a '### Step breakdown' table, a '### Implementation' section, and a '### Error handling' section.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Transformation Analysis heading",
      "description": "pipeline_analysis.md contains a heading that starts with '## Transformation Analysis:' followed by a name",
      "max_score": 12
    },
    {
      "name": "Data Flow section",
      "description": "pipeline_analysis.md contains a '### Data Flow' section heading",
      "max_score": 10
    },
    {
      "name": "Arrow notation in Data Flow",
      "description": "The Data Flow section uses → (arrow) notation to show the transformation chain, e.g. 'input → step1 → step2 → ... → output'",
      "max_score": 14
    },
    {
      "name": "Step breakdown section",
      "description": "pipeline_analysis.md contains a '### Step breakdown' section heading",
      "max_score": 10
    },
    {
      "name": "Step breakdown as markdown table",
      "description": "The Step breakdown section contains a markdown table with columns 'Step' and 'What it does' (or equivalent headers in a pipe-table format)",
      "max_score": 14
    },
    {
      "name": "Implementation section",
      "description": "pipeline_analysis.md contains a '### Implementation' section heading (optionally followed by a language name)",
      "max_score": 10
    },
    {
      "name": "Error handling section",
      "description": "pipeline_analysis.md contains a '### Error handling' section heading",
      "max_score": 10
    },
    {
      "name": "Input-output function framing",
      "description": "The analysis frames the overall program as a function from a specific input to a specific output (e.g. 'raw sensor records → per-floor averages')",
      "max_score": 10
    },
    {
      "name": "Single-responsibility steps",
      "description": "Each step listed in the breakdown does exactly one named transformation (read, filter, parse, group, aggregate, etc.) rather than combining multiple concerns",
      "max_score": 10
    }
  ]
}

evals

scenario-1

criteria.json

task.md

SKILL.md

tile.json