agentfolio

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

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/agentfolio/SKILL.md

Quality

Content

67%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.

The body is a well-structured, actionable guide for an instruction-only skill: a clear four-step usage workflow, concrete evaluation criteria, worked example scenarios, and ready-to-use prompts. Its main weakness is redundancy — the skill's scope is restated in three sections, which wastes tokens without adding guidance. Consolidating those sections and adding a light verification step for directory findings would raise the score.

Suggestions

Merge "This skill helps you", "Capabilities", and "When to Use" into a single short section — they restate the same scope three times and account for most of the wasted tokens.

Add a light validation step to the workflow (e.g., cross-check an agent's claims against its docs/site before including it in a shortlist) to strengthen workflow clarity.

Clarify how the agent should access the directory (browsable URL vs. fetchable page) since "Visit in your browser" is not directly executable for a coding agent.

Dimension	Reasoning	Score
Conciseness	The body never explains concepts Claude already knows, but the same scope is restated across "This skill helps you", "Capabilities", and "When to Use", which is unnecessary padding that could be consolidated. It is noticeably redundant in places (toward anchor 2) but the individual sections are short and purposeful enough to sit at anchor 3 rather than below.	3 / 5
Actionability	Concrete, executable guidance for an instruction-only skill: specific URL ("Visit `https://agentfolio.io`"), concrete capture criteria ("Core promise", "Input / output shape", "Autonomy model", "Deployment model"), example search strings ("testing agent", "CI agent"), and a comparison-table column spec. It is not a 5 because some directions remain abstract ("Gather example agent behavior and UX patterns") and "visit in your browser" is not directly executable by a coding agent with no browsing tooling specified.	4 / 5
Workflow Clarity	"How to Use AgentFolio" gives a clear 4-step sequence (open directory → search by intent → evaluate candidates → synthesize insights) with well-defined sub-steps, and the Limitations section adds a "Stop and ask for clarification" guardrail. It is not a 5 because there are no explicit validation checkpoints on findings (e.g., verify an entry still exists or matches the claimed capability), and not a 3 because the sequence is complete and steps are concretely defined.	4 / 5
Progressive Disclosure	No bundle files exist, and the ~90-line body is cleanly organized into well-labeled sections with nothing that clearly belongs in a separate reference file. Structure is good (anchor 4); it is not a 5 because the simple-skill exception is specified for under-50-line skills and the redundant scope sections suggest the overview itself could be tightened before any split would be needed.	4 / 5
	Total	15 / 20 Passed

Description

53%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.

The description communicates a clear niche tied to the AgentFolio directory but reads as a one-sentence scope statement rather than a full trigger-rich description. Its main weakness is the missing "Use when..." clause, which caps completeness and leaves natural trigger terms underdeveloped. Adding explicit usage triggers and a few more concrete actions would move it toward the strong examples.

Suggestions

Append an explicit trigger clause, e.g.: "Use when the user wants to find, compare, or research AI agents, agent frameworks, or agent tools instead of building one from scratch."

List 2-3 more concrete actions in the description (e.g., compare agents by capabilities and integrations, shortlist vendors, gather UX/benchmark examples) to lift specificity beyond generic discovering/researching.

Include natural synonyms users would say — "AI agent directory", "agent frameworks", "agent landscape", "vendor comparison" — to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	"discovering and researching autonomous AI agents, tools, and ecosystems" names the domain and 1-2 concrete actions, but the action verbs are generic and the objects broad. It does not list several specific actions (e.g., compare, shortlist, benchmark), so it falls short of anchor 4, while it goes beyond merely naming a domain (anchor 2).	3 / 5
Completeness	The "what" is clear (discover and research agents via the AgentFolio directory), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 4 because the "when" is entirely missing rather than merely imprecise, and not a 2 because the "what" is concrete, not vague.	3 / 5
Trigger Term Quality	"autonomous AI agents" and "AgentFolio" are relevant, naturally-sayable terms, but common variations users would actually say ("find agents", "compare agent frameworks", "agent directory", "AI tools landscape") are absent. Keyword coverage exists but is incomplete, matching anchor 3 rather than the good coverage of anchor 4.	3 / 5
Distinctiveness Conflict Risk	The named "AgentFolio directory" carves out a distinct niche (agent discovery/research) with only minor overlap risk against general research or web-search skills. It is not a 5 because "tools, and ecosystems" broadens the scope and no distinct trigger phrases are given to minimize conflict further.	4 / 5
	Total	13 / 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: sickn33/agentic-awesome-skills
Path: skills/agentfolio/SKILL.md
Commit: 7b534bc

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.