skills-discovery

Search for and install Agent Skills that give you specialized capabilities. Before starting work, ask might a skill exist that handles this better than my base knowledge? If the task involves specific technologies, frameworks, file formats, or expert domains. Search proactively, even if the user doesn't mention skills. Skills encode best practices, tools, and techniques you wouldn't otherwise have. Also use when users explicitly ask to find, install, or manage skills.

Quality

76%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/skills-discovery/SKILL.md

Quality

Discovery

75%

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

The description effectively communicates its meta-skill purpose and provides clear 'when to use' guidance, earning strong marks for completeness and distinctiveness. However, it mixes operational instructions (behavioral guidance for Claude) with capability description, and the specificity of concrete actions could be improved. The use of second person ('give you') should also be noted as a minor voice issue.

Suggestions

Replace second-person voice ('give you specialized capabilities') with third-person ('provides specialized capabilities') and remove the internal behavioral coaching ('ask might a skill exist') to focus on concrete capability description.

Add more natural trigger terms users might say, such as 'plugin', 'extension', 'add capability', 'skill store', or 'browse skills' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain (Agent Skills) and some actions ('search for and install'), but also includes vague advisory language like 'ask might a skill exist' and 'search proactively' which are more behavioral guidance than concrete capability descriptions.	2 / 3
Completeness	The description clearly answers both 'what' (search for and install Agent Skills) and 'when' (when tasks involve specific technologies/frameworks/file formats/expert domains, or when users explicitly ask to find/install/manage skills). It has explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes some natural keywords like 'find, install, or manage skills' and mentions 'technologies, frameworks, file formats, expert domains,' but misses common user phrasings like 'add a plugin,' 'skill store,' 'capability,' or 'extension.' The proactive search guidance is more of an internal instruction than a trigger term.	2 / 3
Distinctiveness Conflict Risk	This skill has a very clear niche — it's a meta-skill about finding and installing other skills. This is unlikely to conflict with any domain-specific skill since it operates at a different level entirely.	3 / 3
	Total	10 / 12 Passed

Implementation

77%

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

This is a solid, actionable skill with clear executable commands and a well-defined workflow for discovering and installing skills. Its main weakness is moderate verbosity—the supported clients list, repeated search motivation framing, and inline API response schemas could be tightened or split out. The examples are practical and the troubleshooting section adds useful error recovery guidance.

Suggestions

Condense the 'When to search for skills' section—the numbered list and bullet list convey the same idea; merge them into a single concise block.

Consider moving the full supported clients list and API response schema into a separate reference file to reduce the main skill's token footprint.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient but includes some unnecessary content. The long list of supported clients could be more compact, the response structure JSON example is somewhat verbose, and the 'When to search for skills' section repeats the same idea multiple ways. However, it avoids explaining basic concepts Claude already knows.	2 / 3
Actionability	Provides fully executable curl commands, npx installation commands with specific flags, concrete examples of user interactions, and exact API endpoints. The commands are copy-paste ready with clear parameter documentation.	3 / 3
Workflow Clarity	The workflow is clearly sequenced: check installed skills → search registry → evaluate results → determine client → install with correct flags. The 'Presenting results to users' section provides a clear checklist, and the troubleshooting section covers error recovery. For this type of non-destructive operation, the workflow is appropriately detailed.	3 / 3
Progressive Disclosure	The content is well-structured with clear sections, but it's all in one file with no references to supporting documents. The supported clients list, full API response schema, and troubleshooting could be split into separate reference files. However, the content is organized with clear headers and the total length is manageable.	2 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: laurent-r/agent-stuff
Commit: 81d7528

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.