agentfolio

Skill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory.

Quality

26%

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 ./plugins/antigravity-awesome-skills-claude/skills/agentfolio/SKILL.md

Quality

Discovery

32%

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 identifies its domain (AgentFolio directory for AI agents) but lacks concrete action verbs, explicit trigger conditions, and natural user language variations. It reads more like a tagline than a functional skill description that would help Claude reliably select it from a large skill set.

Suggestions

Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks about finding AI agents, browsing agent directories, or mentions AgentFolio.'

List specific concrete actions the skill performs, such as 'search for agents by category, compare agent capabilities, retrieve agent details and documentation, explore agent ecosystems.'

Include natural keyword variations users might say, such as 'find agents', 'agent directory', 'agent catalog', 'browse AI tools', 'look up agents'.

Dimension	Reasoning	Score
Specificity	Names the domain ('autonomous AI agents, tools, and ecosystems') and some actions ('discovering and researching'), but doesn't list multiple concrete actions like searching, comparing, filtering, or retrieving specific agent details.	2 / 3
Completeness	Describes what it does at a high level but has no explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also fairly weak, so this scores a 1.	1 / 3
Trigger Term Quality	Includes some relevant keywords like 'AI agents', 'tools', 'ecosystems', and 'AgentFolio', but misses common user variations like 'agent directory', 'find agents', 'agent search', 'agent catalog', or 'browse agents'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'AgentFolio directory' provides some distinctiveness as a specific tool/platform, but 'AI agents, tools, and ecosystems' is broad enough to potentially overlap with other AI-related skills.	2 / 3
	Total	7 / 12 Passed

Implementation

20%

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

This skill reads more like a marketing overview or user guide for a website than an actionable skill for Claude. It lacks any concrete, executable instructions—no code, no API endpoints, no structured output templates—and instead describes manual browser-based workflows that Claude cannot directly perform. The content is also significantly padded with explanations of obvious concepts and redundant sections.

Suggestions

Add concrete, executable guidance: define a structured output format (e.g., JSON schema for agent comparison tables), provide specific API calls or web scraping patterns if AgentFolio has an API, or at minimum provide a template Claude can fill in.

Remove sections that explain things Claude already knows (what autonomous agents are, what SaaS means, how to use a search bar) and collapse the redundant Capabilities/When to Use/intro sections into a single brief overview.

Clarify how Claude should actually interact with AgentFolio—can it fetch the URL? Is there an API? If it's browser-only, acknowledge this limitation upfront and provide alternative actionable steps (e.g., asking the user to paste content).

Add a concrete output example showing what a completed agent comparison or landscape scan should look like, so Claude has a clear target format.

Dimension	Reasoning	Score
Conciseness	The skill is highly verbose, explaining concepts Claude already knows (what a directory is, how to use a search bar, what SaaS means). The 'Capabilities' section largely restates the introduction. The 'Limitations' section contains generic boilerplate. Much of this content could be cut by 60%+ without losing actionable information.	1 / 3
Actionability	There is no concrete, executable guidance anywhere—no code, no API calls, no CLI commands, no structured output formats. The instructions amount to 'visit a website and search for things,' which is vague direction rather than actionable skill content. Claude cannot programmatically browse AgentFolio, making the steps essentially unusable.	1 / 3
Workflow Clarity	The steps are sequenced (open, search, evaluate, synthesize) and the example workflows provide reasonable structure. However, there are no validation checkpoints, no concrete output schemas or checklists to verify completeness, and the steps remain at a high level of abstraction without specific verification criteria.	2 / 3
Progressive Disclosure	The content uses headers and sections for organization, which is reasonable. However, it's a monolithic document with no references to supporting files, and several sections (Capabilities, When to Use, Limitations) contain redundant or boilerplate content that inflates the file without adding value. For a skill with no bundle files, the inline content could be much more tightly organized.	2 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: sickn33/antigravity-awesome-skills
Commit: a4d3e3a

Reviewed: 5 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.