Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

typedef-ai

@typedef-ai source repo

5 published skills

  1. ▌
    Fenic Mechanics · typedef-ai bundle
    Use when writing, editing, or debugging code that uses fenic (the `fenic` Python library, imported as `import fenic as fc`) — the semantic-DataFrame engine with LLM operators (semantic.map/extract/classify/predicate/reduce, embeddings), jq/markdown/transcript processing, chunking, and fuzzy matching. Covers fenic's import & namespace structure, semantic-operator calling conventions, model/session config, and known silent-failure traps. NOT for plain PySpark, pandas, or Polars code.
    0
    installs
  2. ▌
    Update Fenic Skill · typedef-ai
    Use when fenic has been upgraded to a new version and the `fenic-mechanics` skill needs refreshing, or when explicitly asked to regenerate/update the fenic API reference. Regenerates the version-stamped reference from the installed fenic, surfaces the API deltas, and flags which hand-authored judgment sections to re-review.
    0
    installs
  3. ▌
    Setup · typedef-ai
    Install or verify the ade-bench harness, the Python project that actually runs the benchmark tasks this plugin generates. Use when ade-bench isn't yet on the user's machine, when a generated task fails because the harness is missing, or when the user explicitly asks to set up ade-bench. Also invoked automatically by plan-tasks and create-task when they detect ade-bench is missing.
    0
    installs
  4. ▌
    Plan Tasks · typedef-ai
    Interactively plan and generate ADE-Bench benchmark tasks from a dbt project. Explores the codebase with the user in a pair-planning loop — understanding the domain, reasoning about what makes good benchmarks, and building up a task plan incrementally. Use when you want high-quality, tailored benchmark tasks for your own dbt project.
    0
    installs
  5. ▌
    Create Task · typedef-ai
    Scan a dbt project and generate ADE-Bench benchmark tasks. Analyzes models, proposes bug-injection scenarios by difficulty, and outputs complete task scaffolding (task.yaml, patches, setup/solution scripts, test SQL). Use when you want to benchmark AI agents against your own dbt project and data.
    0
    installs