rendercv/scripts/rendercv_skill/evals/promptfooconfig.yaml at main - rendercv - Gitea: Git with a cup of tea

mirror/rendercv

mirror of https://github.com/rendercv/rendercv.git synced 2026-04-18 14:04:08 -04:00

Files

Sina Atalay 021c9fbde3 Add RenderCV skill with eval framework and auto-generated docs/llms.txt

- Add SKILL.md for AI agents: YAML schema reference, entry type field
  tables, design samples per theme, CLI reference, and important patterns
  (YAML quoting, phone validation, bullet characters)
- Add Jinja2 template and generate.py that auto-generates SKILL.md and
  docs/llms.txt from live Pydantic models and sample generators
- Add promptfoo eval suite (15 tests across 4 files): cv_generation,
  pdf_parsing, design, and cli_workflow
- Add deterministic grader that validates LLM output through RenderCV's
  own pydantic pipeline (not jsonschema)

2026-03-20 20:15:09 +03:00

17 lines

339 B

YAML

Raw Permalink Blame History

 description: RenderCV Skill Evaluation
 providers:
   - id: anthropic:messages:claude-sonnet-4-6
     config:
       temperature: 0.0
       max_tokens: 4096
 prompts:
   - file://prompts/skill_chat.js
 tests:
   - file://tests/cv_generation.yaml
   - file://tests/design.yaml
   - file://tests/cli_workflow.yaml
   - file://tests/pdf_parsing.yaml