ai-evaluation
Systematic evaluation (evals) for LLM and AI products.
Skill by sunnypatneedi
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sunnypatneedi-ai-evaluation
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, testing, ml
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ai-evaluation
What's inside
- Skill name
ai-evaluation- Description
- Systematic evaluation (evals) for LLM and AI products. Design test cases, measure accuracy/quality, track regressions, benchmark models, and build continuous evaluation pipelines. Distinct from traditional software testing with probabilistic outputs.
- License
- NOASSERTION
- Instructions
- 465 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from sunnypatneedi/claude-starter-kit
- 0.472score
ask-questions
sunnypatneedi
Clarify requirements before implementing.
SkillDFreshness: D★ 11Claude Code +9 - 0.472score
multi-agent-orchestrator
sunnypatneedi
Marketing multi-agent orchestration system for complex, parallelizable campaigns.
SkillDFreshness: D★ 11Claude Code +9 - 0.469score
skill-improver
sunnypatneedi
Review feedback from skill retrospectives and update skill files to improve with use.
SkillDFreshness: D★ 11Claude Code +9 - 0.469score
performance-optimization
sunnypatneedi
Optimize frontend and backend performance through profiling, caching strategies, database optimization, code splitting, and Core Web Vitals improvements.
SkillDFreshness: D★ 11Claude Code +9 - 0.469score
ugc-content-creator
sunnypatneedi
Create short-form video content for TikTok, Instagram Reels, and YouTube Shorts.
SkillDFreshness: D★ 11Claude Code +9 - 0.469score
copywriter
sunnypatneedi
Master storytelling frameworks, video scripts (15s/30s/60s), social media captions, segment-specific messaging, and persuasive CTAs.
SkillDFreshness: D★ 11Claude Code +9 - 0.469score
social-media-ops
sunnypatneedi
Daily social media operations including account setup, warming protocols, posting calendars, community engagement, performance tracking, and crisis management…
SkillDFreshness: D★ 11Claude Code +9 - 0.469score
product-market-fit
sunnypatneedi
Measure and diagnose product-market fit using retention cohorts, user surveys, engagement metrics, and qualitative signals.
SkillDFreshness: D★ 11Claude Code +9 - 0.469score
north-star-metrics
sunnypatneedi
Define and align organization around a single North Star Metric (NSM) that captures product value, drives growth, and focuses team efforts.
SkillDFreshness: D★ 11Claude Code +9 - 0.469score
retention-engagement
sunnypatneedi
Build habit-forming products using Hook Model (trigger-action-reward-investment), cohort analysis, feature adoption tracking, and re-engagement strategies.
SkillDFreshness: D★ 11Claude Code +9 - 0.466score
systems-decompose
sunnypatneedi
Decompose a feature into system components before implementation
SkillDFreshness: D★ 11Claude Code +9 - 0.466score
weekly-review
sunnypatneedi
Guide a comprehensive weekly reflection and planning session
SkillDFreshness: D★ 11Claude Code +9
Signals
- Stars
- 11
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jan 23, 2026 (9 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- NOASSERTION
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sunnypatneedi
- 0.472score
multi-agent-orchestrator
sunnypatneedi
Marketing multi-agent orchestration system for complex, parallelizable campaigns.
SkillDFreshness: D★ 11Claude Code +9 - 0.472score
ask-questions
sunnypatneedi
Clarify requirements before implementing.
SkillDFreshness: D★ 11Claude Code +9 - 0.469score
retention-engagement
sunnypatneedi
Build habit-forming products using Hook Model (trigger-action-reward-investment), cohort analysis, feature adoption tracking, and re-engagement strategies.
SkillDFreshness: D★ 11Claude Code +9 - 0.469score
copywriter
sunnypatneedi
Master storytelling frameworks, video scripts (15s/30s/60s), social media captions, segment-specific messaging, and persuasive CTAs.
SkillDFreshness: D★ 11Claude Code +9 - 0.469score
product-market-fit
sunnypatneedi
Measure and diagnose product-market fit using retention cohorts, user surveys, engagement metrics, and qualitative signals.
SkillDFreshness: D★ 11Claude Code +9 - 0.469score
north-star-metrics
sunnypatneedi
Define and align organization around a single North Star Metric (NSM) that captures product value, drives growth, and focuses team efforts.
SkillDFreshness: D★ 11Claude Code +9
Cite this page
ai-evaluation skill. Agent Mart. https://agentmart.dev/skills/sunnypatneedi-ai-evaluation (last updated 2026-10-24)