browse-and-evaluate

Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable skill body with executable commands, clear sequencing, and a dry-run validation checkpoint for a batch/install operation. The only gap is an explicit error-recovery loop after the dry-run step.

Suggestions

Add a short feedback loop after the dry-run step — e.g. "If the dry-run shows unexpected skills or unreachable sources, adjust the command and re-run before installing."

Optionally note how to inspect a collection's member list during the preview/dry-run step to reinforce the collection-install gotcha inline in the workflow.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — a one-line goal, tight guardrail bullets, executable commands, and gotchas that convey only non-obvious operational knowledge (prompt-injection sanitization, collection pulls, upstream fetch). No padding or explanation of concepts Claude already knows.	5 / 5
Actionability	Fully executable copy-paste-ready `npx ai-agent-skills` commands cover the common flow (search, info, preview, dry-run, install) with appropriate placeholders, and gotchas give concrete checks to run.	5 / 5
Workflow Clarity	A clear 5-step sequence with an explicit validation checkpoint (step 4 dry-run before step 5 install) and a batch-operation guardrail ("Never install more than 3 skills at once without confirmation"), but it lacks an explicit error-recovery feedback loop (what to do when dry-run output looks wrong).	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with well-organized sections (Goal, Guardrails, Workflow, Gotchas) and no need for external references; per the simple-skill guidance this scores 5 on structure alone.	5 / 5
	Total	19 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concise description that clearly states both capability and trigger context with concrete operational guidance. Minor room to broaden trigger-term synonyms (browse/search) and separate capability claims from guardrails.

Suggestions

Add common synonyms users might say — e.g. "search or browse the catalog" — to broaden trigger-term coverage.

Move the "--fields / --dry-run" operational guidance so the first sentence stays focused on capabilities, keeping the what/when trigger crisp.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — "find, compare, and evaluate skills before installing" — plus operational specifics like "--fields" and "--dry-run", but the second sentence leans toward guardrails rather than expanding capability coverage, so it stops short of a 5.	4 / 5
Completeness	Explicitly answers both what (find, compare, evaluate, install skills) and when ("Use when exploring the ai-agent-skills catalog...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("find, compare, and evaluate skills", "installing") but omits common synonyms like browse/search that the body itself uses, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — browsing/evaluating the ai-agent-skills catalog before install — with distinct triggers and minimal overlap risk with unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: MoizIbnYousaf/ai-agent-skills
Path: skills/browse-and-evaluate/SKILL.md
Commit: 1159592

Reviewed: 19 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.