autonomous-agents

Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it'...

1.18x

Quality

27%

Does it follow best practices?

Impact

82%

1.18x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/antigravity-autonomous-agents/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.

This description is severely truncated, cutting off mid-sentence which makes full evaluation impossible. What is visible focuses on defining what autonomous agents ARE rather than what the skill DOES or WHEN to use it. The description lacks explicit trigger guidance and reads more like an educational introduction than a functional skill description.

Suggestions

Complete the truncated description and add an explicit 'Use when...' clause with trigger terms like 'build agent', 'autonomous workflow', 'agentic system', 'multi-step automation'

Shift from defining autonomous agents conceptually to listing concrete actions the skill performs (e.g., 'Designs agent architectures, implements tool-calling loops, adds error recovery mechanisms')

Include natural user phrases that would trigger this skill, such as 'create an agent', 'build autonomous system', 'agent that can...'

Dimension	Reasoning	Score
Specificity	The description names the domain (autonomous agents) and mentions some actions ('decompose goals, plan actions, execute tools, and self-correct'), but these are conceptual descriptions of what agents ARE rather than concrete actions the skill performs. The description is truncated, limiting full assessment.	2 / 3
Completeness	The description explains WHAT autonomous agents are conceptually but is truncated mid-sentence ('it'...') and shows no 'Use when...' clause or explicit trigger guidance. Missing the 'when' component entirely caps this at 1.	1 / 3
Trigger Term Quality	Contains relevant keywords like 'autonomous agents', 'AI systems', 'plan actions', 'execute tools', and 'self-correct' that users might mention. However, the description is truncated and may be missing common variations or natural user phrases.	2 / 3
Distinctiveness Conflict Risk	The focus on 'autonomous agents' provides some distinctiveness, but terms like 'AI systems', 'plan actions', and 'execute tools' could overlap with general AI/automation skills. The truncation prevents full assessment of distinctiveness.	2 / 3
	Total	7 / 12 Passed

Implementation

22%

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

This skill is essentially a skeleton or outline rather than actionable guidance. It names important concepts (ReAct, Plan-Execute, Reflection patterns) but provides zero implementation details, code examples, or concrete steps. The Sharp Edges table is malformed with placeholder text, and the overview is truncated mid-sentence, making this skill unusable in its current state.

Suggestions

Add executable code examples for each pattern (ReAct loop, Plan-Execute, Reflection) showing actual implementation with tool calls and state management

Fix the Sharp Edges table - replace placeholder 'Issue' text with actual issues (e.g., 'Compounding errors', 'Cost explosion', 'Hallucinated actions') and provide real solutions instead of just headers

Complete the truncated overview and add a concrete quick-start example showing a minimal working agent with guardrails

For each anti-pattern, explain what it looks like and provide a concrete alternative approach

Dimension	Reasoning	Score
Conciseness	The philosophical framing ('You are an agent architect who has learned hard lessons') adds some unnecessary context, but the content is relatively brief. However, the truncated text and malformed tables waste tokens without providing value.	2 / 3
Actionability	The skill provides no concrete code, commands, or executable examples. Pattern names like 'ReAct Agent Loop' and 'Plan-Execute Pattern' are mentioned but never explained or demonstrated with actual implementation guidance.	1 / 3
Workflow Clarity	No clear steps or sequences are provided for any of the mentioned patterns. The 'Sharp Edges' table is malformed with placeholder 'Issue' text and solutions that are just headers without content. No validation checkpoints exist.	1 / 3
Progressive Disclosure	The content has some structure with sections for Patterns, Anti-Patterns, and Sharp Edges. However, the Related Skills references are not linked, and the content appears truncated mid-sentence in the overview, suggesting poor organization.	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: boisenoise/skills-collections
Commit: 5c5ae21

Reviewed: 3 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.