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.
82
78%
Does it follow best practices?
Impact
80%
0.97xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/claude/prompts.chat/skills/skill-lookup/SKILL.mdQuality
Discovery
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.
This is a well-crafted skill description that clearly communicates what the skill does (search, retrieve, install skills from a specific registry) and when to use it (with an explicit 'Use when' clause covering multiple trigger scenarios). The description is concise, uses third person voice, and includes distinctive terms that minimize conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Search, retrieve, and install Agent Skills' and specifies the source 'prompts.chat registry using MCP tools'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (search, retrieve, install Agent Skills from prompts.chat registry using MCP tools) and 'when' (explicit 'Use when' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'find skills', 'browse skill catalogs', 'install a skill for Claude', 'extend Claude's capabilities', 'reusable AI agent components'. These cover multiple natural phrasings a user might use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific references to 'prompts.chat registry', 'MCP tools', and 'Agent Skills'. This is a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable structure for guiding Claude through searching and installing skills from a registry, with clear section organization and a logical workflow. However, it suffers from some redundancy between the overview workflow and the detailed how-to sections, and the actionability is weakened by the lack of concrete file-writing code or error handling in the installation process.
Suggestions
Add concrete file-writing commands or code snippets in the 'How to Install a Skill' section (e.g., showing the actual tool calls or bash commands to create directories and write files)
Add an error recovery step to the install workflow — e.g., what to do if file writing fails or if the skill has missing files
Consolidate the redundant content between the top-level 'Workflow' section and the three 'How to...' sections to reduce token usage
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but has some redundancy — the workflow steps are repeated in more detail in the 'How to Install a Skill' section, and the tool parameter descriptions could be more compact. Some sections like 'How to Get a Skill' restate what the tool returns, which Claude could infer. | 2 / 3 |
Actionability | The skill provides concrete MCP tool calls with parameter names and an example, but the examples are incomplete — they show function calls without showing how to handle the response, save files, or verify installation. The install workflow lacks actual file-writing commands or code. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced with numbered steps covering search → present → retrieve → install → confirm. However, the verification step (step 4 in install) only checks frontmatter is intact but doesn't include error recovery or validation of all files. For a file-writing operation, a feedback loop for handling failures is missing. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~60 lines) with no need for external references, the content is well-organized into logical sections (Workflow, Example, Available Tools, How to Search, How to Get, How to Install, Guidelines) that are easy to navigate and appropriately scoped. | 3 / 3 |
Total | 9 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- f/awesome-chatgpt-prompts
- Commit
b5a3e42
- 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.