eval-engineering
by langchain-ai13 days ago1.1kIteratively inspect an agent repository and optional user-provided traces, interview the user, and create, run, and audit Harbor evals one at a time. Use for agent evals, Harbor tasks, benchmark cases, verifier design, or controlled agent environments.
Install
Show step-by-stepHide step-by-step
Open your terminal
- Mac: Press β Space, type "Terminal", press Enter
- Windows: Press Win R, type "cmd", press Enter
Paste the command above and press Enter
Use the Copy command button, then paste in your terminal (Mac: βV, Windows: Ctrl V).
Restart Claude Code
Close and reopen Claude Code, or start a new session, so it picks up the new skill.
Where it lives
Comments
"New version of the eval-engineering skill released, thanks for everyone's feedback on the first version. npx skills add --skill eval-engineering updates: - now..."
"Open Questions to friends here: 1. Do you do evals? 2. What are friction point for building evals you actually trust? 3. What open tooling do you feel like..."
"democratizing high quality evals & environments for your specific use-cases is a huge win for Open Intelligence. so weβre sharing skills & workflows that plug..."
Related skills
comfyui
Generate images, video, and audio with ComfyUI β install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.
hyperframes
Render MP4/WebM videos from HTML compositions.
claude-api
Reference for the Claude API / Anthropic SDK β model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER β read BEFORE opening the target file; don't skip because it "looks like a one-liner" β whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) β never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named β don't Read the file).
paddleocr-text-recognition
Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox coordinates. Strong accuracy for CJK, small print, and handwritten text. Trigger terms: OCR, ζεθ―ε«, εΎη转ζε, ζͺεΎθ―ε, ζεεΎδΈζε, ζ«ζθ―ε, θ―ε, ηΊ―ζε, plain text extraction, εζ , ζ£ζ΅ζ‘, bbox, bounding box, image to text, screenshot, photo scan, recognize text.