Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
HomeCompare › design-context-extract vs langchain-eval-harness

design-context-extract vs langchain-eval-harness

Two General Claude Code skills, side by side. Pick the right skill for your workflow with a side-by-side look at metadata, sample code, and install commands.

Side-by-side

Namedesign-context-extractlangchain-eval-harness
DescriptionExtract design DNA from existing app screenshots or live URLs using Google Stitch. Produces color palettes, typography specs, spacing tokens, and component patterns as design-tokens.json or Tailwind config. Use when…Build reproducible evaluation pipelines for LangChain 1.0 chains and LangGraph 1.0 agents — golden datasets, LangSmith evaluate(), ragas RAG metrics, deepeval LLM-as-judge, agent trajectory analysis, and CI gating on…
CategoryGeneralGeneral
Sub-categorydesign-creativegeneral-misc
Tagstype:auditai:llm type:debug
AuthorOrchestKitJeremy Longshore <[email protected]>
LicenseMITMIT
Install/add-skill design-context-extract/add-skill langchain-eval-harness

Tag overlap

Shared

Only in design-context-extract type:audit

Only in langchain-eval-harness ai:llm, type:debug

Sample code from each SKILL.md

design-context-extract

/ork:design-context-extract /tmp/screenshot.png       # From screenshot
/ork:design-context-extract https://example.com        # From live URL
/ork:design-context-extract current project            # Scan project's existing styles

langchain-eval-harness

# evals/golden_set/v2026.04.jsonl
{"id": "gs-0001", "input": "Refund policy for SKU ABC-42?", "expected": "30 days with receipt", "contexts": ["policy_v3.md"], "tags": ["refund"], "difficulty": "easy", "dataset_version": "2026.04"}
{"id": "gs-0002", "input": "Return policy for opened software?", "expected": "No, opened software is final sale", "contexts": ["policy_v3.md#returns"], "tags": ["refund"], "difficulty": "medium", "dataset_version": "2026.04"}

When to choose each

design-context-extract — Extract design DNA from existing app screenshots or live URLs using Google Stitch. Produces color palettes, typography specs, spacing tokens, and component patterns as design-tokens.json or Tailwind config. Use when…

langchain-eval-harness — Build reproducible evaluation pipelines for LangChain 1.0 chains and LangGraph 1.0 agents — golden datasets, LangSmith evaluate(), ragas RAG metrics, deepeval LLM-as-judge, agent trajectory analysis, and CI gating on…

Both are free to install. If you're unsure, install both — Claude Code skills are isolated by filename and only collide if their trigger phrases overlap (rare). The richest signal is the SKILL.md body itself — open both skill pages and read the first paragraph of each.

Open design-context-extract → Open langchain-eval-harness →

Other comparisons in this category

See all Claude Code skill comparisons · Browse all General skills · Top 100