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's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b
37
Quality
22%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/skills/autonomous-agents/SKILL.mdQuality
Discovery
N/ABased on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
Something went wrong
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 with minimal actual content. It names important concepts (ReAct, Plan-Execute, Reflection patterns) but provides no implementation details, code examples, or actionable guidance. The sharp edges table contains placeholder 'Issue' text and solution headers without content, suggesting incomplete development.
Suggestions
Add executable code examples for each pattern (ReAct loop, Plan-Execute, Reflection) showing the actual implementation structure
Fill in the Anti-Patterns section with concrete examples of what NOT to do and why, with code showing the problematic pattern
Complete the Sharp Edges table with actual issues (e.g., 'Compounding error rates', 'Context window exhaustion') and detailed solutions rather than placeholder text
Add a concrete workflow example showing how to build a constrained agent step-by-step with validation checkpoints
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief but includes some unnecessary philosophical framing ('You are an agent architect who has learned the hard lessons'). The capabilities list is redundant tagging rather than useful content. The sharp edges table has placeholder 'Issue' text that wastes tokens. | 2 / 3 |
Actionability | The skill provides no concrete code, commands, or executable examples. Pattern names are listed (ReAct, Plan-Execute, Reflection) with one-line descriptions but no implementation details. Anti-patterns are headers with no content. This describes rather than instructs. | 1 / 3 |
Workflow Clarity | Despite covering agent loops and patterns that inherently involve multi-step processes, there are no actual workflow sequences, validation checkpoints, or step-by-step guidance. The sharp edges table has 'solutions' that are just headers with no content. | 1 / 3 |
Progressive Disclosure | The content has some structure with clear sections (Patterns, Anti-Patterns, Sharp Edges, Related Skills), but the sections are mostly empty placeholders. References to related skills exist but the main content that should be present is missing entirely. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
90%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
- duclm1x1/Dive-Ai
- Commit
20ba150
- 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.