CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-lookup

Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.

86

0.97x
Quality

Does it follow best practices?

Impact

80%

0.97x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

An actionable, well-organized skill body with concrete tool calls and exact file paths, plus a clear sequenced install workflow with verification steps. The main weakness is redundancy across sections and the absence of an error-recovery feedback loop for the verification step.

Suggestions

Consolidate the overlapping install instructions from the Workflow and How to Install sections into a single authoritative sequence to remove redundancy.

Add a brief feedback loop after the SKILL.md verification step (e.g. "If frontmatter is missing or malformed, re-fetch the skill before proceeding") to close the validation gap.

Merge the per-tool parameter documentation in Available Tools, How to Search, and How to Get into one reference block so each tool's usage lives in one place.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but the Workflow, Available Tools, How to Search/Get/Install, and Guidelines sections repeat overlapping information (e.g. install steps appear in both Workflow and How to Install), so it could be tightened.

2 / 3

Actionability

Provides concrete, copy-paste-ready tool calls with parameters (search_skills({"query":...}), get_skill({"id":...})) and exact install paths like .claude/skills/{slug}/SKILL.md, matching the fully-executable anchor.

3 / 3

Workflow Clarity

The install sequence is clearly numbered with explicit verification steps ("verify the SKILL.md exists", "Read back SKILL.md to verify the frontmatter is intact"), but there is no feedback loop describing what to do if verification fails, leaving a validation gap that caps the score at 2.

2 / 3

Progressive Disclosure

A single-purpose skill organized into clear sections (Workflow, Example, Available Tools, How to..., Guidelines) with no external bundle files and no nested references, which satisfies the simple-skill allowance for a top score without external references.

3 / 3

Total

10

/

12

Passed

Description

100%

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 concise, third-person description that names concrete actions, gives explicit "Use when..." triggers with natural language, and occupies a clearly distinct niche. It hits the top anchor on every dimension with no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools" — matching the anchor for several specific concrete actions.

3 / 3

Completeness

Explicitly states what ("Search, retrieve, and install...") and when ("Use when the user asks to find skills..."), satisfying both halves of the completeness anchor.

3 / 3

Trigger Term Quality

Natural user-facing phrases like "find skills", "browse skill catalogs", "install a skill for Claude", and "extend Claude's capabilities" give good coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The niche is scoped to the prompts.chat registry via MCP tools with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
f/awesome-chatgpt-prompts
Reviewed

Table of Contents

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.