75fa9de2bb
- 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.
42 lines
1.6 KiB
YAML
42 lines
1.6 KiB
YAML
# Eval: content-strategy
|
|
# Source: marketing-skill/content-strategy/SKILL.md
|
|
|
|
description: "Evaluate content strategy skill"
|
|
|
|
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://../../marketing-skill/content-strategy/SKILL.md
|
|
task: "Build a 3-month content strategy for a developer tools startup that just launched. We have zero blog posts and a small Twitter following of 500. Our product is an open-source database migration tool."
|
|
assert:
|
|
- type: llm-rubric
|
|
value: "Response includes a phased plan with specific content types, topics, and publishing cadence"
|
|
- type: llm-rubric
|
|
value: "Strategy addresses developer audience specifically with appropriate channels (dev blogs, GitHub, HN)"
|
|
- type: llm-rubric
|
|
value: "Response includes measurable goals or KPIs for the content program"
|
|
|
|
- vars:
|
|
skill_content: file://../../marketing-skill/content-strategy/SKILL.md
|
|
task: "We have 50 blog posts but traffic has plateaued at 10K monthly visits. What should we do to 3x our organic traffic in 6 months?"
|
|
assert:
|
|
- type: llm-rubric
|
|
value: "Response diagnoses potential issues with existing content before prescribing new content"
|
|
- type: llm-rubric
|
|
value: "Response includes specific tactics like content refresh, internal linking, or topic clusters"
|