Browse And Evaluate

by MoizIbnYousaf

Browse And Evaluate is an Automation skill for Claude Code, published by MoizIbnYousaf in ai-agent-skills.

1.1K stars131 forkson MoizIbnYousaf/ai-agent-skillsAdded 2026/09/03Repository updated 2026/08/17

View source on GitHub Download repo ZIP

agent-skillsai-agentsclaude-codeclicodexcursordeveloper-toolsmcpproductivity

Install in seconds

Install Browse And Evaluate

Copy Browse And Evaluate into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/MoizIbnYousaf/ai-agent-skills/tree/main/skills/browse-and-evaluate ~/.claude/skills/browse-and-evaluate

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/MoizIbnYousaf/ai-agent-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/browse-and-evaluate/SKILL.md in MoizIbnYousaf/ai-agent-skills
Installs to: ~/.claude/skills/browse-and-evaluate
Collection: One of 18 skills cataloged from this repository
Category: Automation — 2226 skills

What Browse And Evaluate does

Browse And Evaluate helps you search, compare, preview, and dry-run installs from the ai-agent-skills catalog. Use it when you want to choose a skill carefully without loading too much output or installing by mistake.

Browse And Evaluate is cataloged under Automation on DirSkills. Browse And Evaluate comes from a repository tagged agent-skills, ai-agents, claude-code, cli and codex.

Documentation

README

Excerpt

Always use --fields on list/search/info to keep output small. Default: --fields name,tier,workArea,description.
Always use --dry-run before installing anything.
Never install more than 3 skills at once without explicit user confirmation.
Prefer --format json in non-interactive pipelines. The CLI defaults to JSON when stdout is not a TTY.
Use --limit when browsing large catalogs. Start with --limit 10.

Workflow

Search or browse the catalog.

npx ai-agent-skills search <query> --fields name,tier,workArea,description --limit 10

Get details on a candidate.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Browse And Evaluate

What else does MoizIbnYousaf publish alongside Browse And Evaluate?
Browse And Evaluate is one of 18 skills that DirSkills catalogs from MoizIbnYousaf/ai-agent-skills, the repository it ships in. Its siblings there include Add an Upstream Skill, Ask Questions If Underspecified and Audit Library Health. Each one is a separate skill with its own page in this directory, installs the same way Browse And Evaluate does, and is maintained by MoizIbnYousaf in that same repository. The rest of the collection is listed on the MoizIbnYousaf/ai-agent-skills page.
How does Browse And Evaluate compare to other Automation skills?
Browse And Evaluate ranks #761 by stars among the 2226 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Browse And Evaluate against them. Open each page to compare what they document and how they install.