Skip to content
anyai.fyi

output-eval-dataset-design

Skill from growthxai/output

Design & Media No risky patterns found curated design

Install

npx skills add growthxai/output --skill output-eval-dataset-design

Runs the open skills CLI and installs the skill for your agent (Claude Code, Codex, Cursor …). Alternatively copy the skill folder into .claude/skills/ or upload it in Claude.ai under Settings → Skills.

As a Claude Code plugin

/plugin marketplace add anthropics/claude-plugins-official /plugin install outputai@outputai

This skill is part of the plugin “outputai”. In Claude Code the plugin installs it together with the plugin’s other skills, commands and hooks.

What does the output-eval-dataset-design skill do?

Design diverse eval datasets using dimension-based variation. Use when bootstrapping eval datasets, when real traces are sparse, or when existing datasets miss edge cases.

Description from the SKILL.md in the source repository.

Questions about output-eval-dataset-design

What does the output-eval-dataset-design skill do?

Design diverse eval datasets using dimension-based variation. Use when bootstrapping eval datasets, when real traces are sparse, or when existing datasets miss edge cases.

How do I install output-eval-dataset-design?

In a terminal: npx skills add growthxai/output --skill output-eval-dataset-design. The skills CLI asks which agents to install it for. In Claude.ai you can upload the skill folder as a ZIP under Settings → Skills.

Which agents can use output-eval-dataset-design?

Skills use the open SKILL.md format, which Claude Code, Claude.ai, the Claude API, OpenAI Codex, Cursor, Gemini CLI and other agents support.

Is output-eval-dataset-design safe to use?

Our automatic check found no risky patterns (piped shell scripts, hidden characters, secret access, prompt overrides). It is not a full audit – read the SKILL.md and any scripts before installing.

More skills from growthxai/output

output-eval-error-analysis
growthxai/output

Systematically review workflow traces to identify failure modes before building evaluators. Use when starting an eval project, after significant pipeline changes, or when production quality drops.

Research & Web curated
No risky patterns found
output-migrate
growthxai/output

Upgrade a project between versions of the Output framework. Use when the user asks to upgrade, migrate, or move to a newer Output version.

Other curated
No risky patterns found
output-meta-project-context
growthxai/output

Comprehensive guide to Output.ai Framework for building durable, LLM-powered workflows orchestrated by Temporal. Covers project structure, workflow patterns, steps, LLM integration, HTTP clients, CLI commands, and the full inventory of available agents …

Agents & Workflows curated
Worth a look
output-meta-pre-flight
growthxai/output

Pre-flight validation checks for Output SDK workflow operations. Ensures conventions are followed, requirements are gathered, and quality gates are passed before workflow execution.

Development curated
No risky patterns found
output-meta-post-flight
growthxai/output

Post-flight validation for Output SDK workflow operations. Systematic verification of step completion, convention compliance, quality validation, and deliverable verification.

Development curated
No risky patterns found
output-eval-validate-judge
growthxai/output

Validate LLM judges against human labels using TPR/TNR metrics and train/dev/test splits. Use after writing a judge prompt to verify it agrees with human judgment.

Testing & QA curated
No risky patterns found
output-eval-judge-prompt
growthxai/output

Design effective LLM judge .prompt files for evaluators. Use when creating judgeVerdict/judgeScore/judgeLabel prompts, or when existing judges produce unreliable results.

Design & Media curated
No risky patterns found
output-error-try-catch
growthxai/output

Handle errors caught in Output workflows without losing failure context. Use when adding workflow try/catch logic, fallbacks, partial-failure handling, custom Error classes, or typed checks for errors thrown by steps and evaluators.

Other curated
No risky patterns found

Related skills in Design & Media

hyperframes
heygen-com/hyperframes

Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays.

Design & Media 1560k installs curated
Worth a look
media-use
heygen-com/hyperframes

Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free …

Design & Media 1469k installs curated
Worth a look
design-mobile-apps
designed-by-ai/skills

Design mobile app screens with Sleek, edit Sleek projects, and implement their designs in React Native or HTML.

Design & Media 1467k installs
No risky patterns found
grill-with-docs
mattpocock/skills

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Design & Media 1336k installs curated
No risky patterns found
ai-video-generation
101-skills/superpowers

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI.

Design & Media 1039k installs
No risky patterns found
ai-image-generation
101-skills/superpowers

Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI.

Design & Media 1036k installs
No risky patterns found
ai-avatar-video
101-skills/superpowers

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro.

Design & Media 1036k installs
No risky patterns found
codebase-design
mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable …

Design & Media 963k installs curated
No risky patterns found