Files
claude-skills-reference/eval/skills/cto-advisor.yaml
Leo 75fa9de2bb feat: add promptfoo eval pipeline for skill quality testing
- Add eval/ directory with 10 pilot skill eval configs
- Add GitHub Action (skill-eval.yml) for automated eval on PR
- Add generate-eval-config.py script for bootstrapping new evals
- Add reusable assertion helpers (skill-quality.js)
- Add eval README with setup and usage docs

Skills covered: copywriting, cto-advisor, seo-audit, content-strategy,
aws-solution-architect, agile-product-owner, senior-frontend,
senior-security, mcp-server-builder, launch-strategy

CI integration:
- Triggers on PR to dev when SKILL.md files change
- Detects which skills changed and runs only those evals
- Posts results as PR comments (non-blocking)
- Uploads full results as artifacts

No existing files modified.
2026-03-12 05:39:24 +01:00

54 lines
2.3 KiB
YAML

# Eval: cto-advisor
# Source: c-level-advisor/cto-advisor/SKILL.md
# Run: npx promptfoo@latest eval -c eval/skills/cto-advisor.yaml
description: "Evaluate CTO advisor skill — technical leadership guidance"
prompts:
- |
You are an expert AI assistant. You have the following skill loaded:
---BEGIN SKILL---
{{skill_content}}
---END SKILL---
Now complete this task: {{task}}
providers:
- id: anthropic:messages:claude-sonnet-4-6
config:
max_tokens: 4096
temperature: 0.7
tests:
- vars:
skill_content: file://../../c-level-advisor/cto-advisor/SKILL.md
task: "We're a 15-person startup with a monolithic Django app serving 50K users. Response times are growing. Should we move to microservices or optimize the monolith? We have 4 backend engineers."
assert:
- type: llm-rubric
value: "Response provides a clear recommendation with reasoning, not just listing pros and cons"
- type: llm-rubric
value: "Response considers team size (4 engineers) as a factor in the architecture decision"
- type: llm-rubric
value: "Response includes concrete next steps or an action plan"
- vars:
skill_content: file://../../c-level-advisor/cto-advisor/SKILL.md
task: "Our tech debt is slowing us down. Engineering velocity dropped 30% over 6 months. The CEO wants new features but we can barely maintain what we have. How do I make the case for a tech debt sprint to the board?"
assert:
- type: llm-rubric
value: "Response frames tech debt in business terms the board would understand, not just technical jargon"
- type: llm-rubric
value: "Response includes a strategy for balancing tech debt work with feature delivery"
- type: llm-rubric
value: "Response provides specific metrics or frameworks to measure tech debt impact"
- vars:
skill_content: file://../../c-level-advisor/cto-advisor/SKILL.md
task: "I'm hiring my first VP of Engineering. I'm a technical founder who has been CTO and lead dev. What should I look for, and how do I avoid hiring someone who will clash with me?"
assert:
- type: llm-rubric
value: "Response addresses the founder-VP dynamic specifically, not generic hiring advice"
- type: llm-rubric
value: "Response includes qualities to look for and red flags to watch for"