story-film-eval

Run and interpret the story-film suite's weak-model, continuity, adapter, style, and prompt-injection evaluation cases. Use when developing or regression-testing the skill package itself.

SKILL.md

GitHub

Story Film Eval

This is a developer skill. It is not part of creative production routing.

Workflow

  1. Read ../../references/EVALS.md and ../../evals/README.md.
  2. Run static validation first:
python scripts/run_evals.py
  1. For a live model or harness, use --runner with a command that accepts the case prompt on stdin and operates inside the case workspace.
  2. Inspect failed checks by case ID. Change one skill rule at a time when possible.
  3. Re-run the same cases plus the full static suite.
  4. Add a regression case whenever a real failure teaches a reusable lesson.

Done

The changed skill improves the target cases without regressing unrelated suites, and the new behavior has a durable regression case when appropriate.

Related in other

limits-colimits

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context polluti...

by parcadei
3,392

ddttom-allaboutv2-claude-skills-block-collection-and-party

The Block Collection and Block Party are repositories for existing AEM blocks, build tools, code snippets, integration p...

by mattnigh
20

nodnarbnitram-claude-code-extensions-claude-skills-esphome-confi

This skill should be used when the user asks to "create an esphome config", "set up an esp32 device", "configure esphome...

by mattnigh
20