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
40
Quality
27%
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 ./.agent/skills/autonomous-agents/SKILL.mdQuality
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 reads more like an educational overview or documentation about autonomous agents than a skill description for Claude's selection. It lacks concrete actions Claude would perform, has no 'Use when...' clause, and appears to be truncated. The conceptual content about compounding error rates, while interesting, doesn't help Claude know when to apply this skill.
Suggestions
Add an explicit 'Use when...' clause with natural trigger phrases like 'build an agent', 'autonomous workflow', 'agent reliability', 'ReAct pattern'
Replace conceptual explanations with concrete actions: 'Designs agent architectures, implements ReAct loops, adds reflection and self-correction mechanisms'
Complete the truncated description and remove educational content about error rates - focus on what Claude does and when to use it
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (autonomous agents) and lists some concepts (agent loops, ReAct, Plan-Execute, goal decomposition, reflection patterns), but these are conceptual topics rather than concrete actions Claude would perform. No specific verbs describing what Claude does with this skill. | 2 / 3 |
Completeness | Provides conceptual 'what' (covers agent loops, patterns, reliability) but no explicit 'when' clause. The description reads more like educational content about agents than guidance for when Claude should select this skill. Also appears truncated mid-sentence. | 1 / 3 |
Trigger Term Quality | Includes some relevant technical terms like 'autonomous agents', 'ReAct', 'Plan-Execute', 'goal decomposition', but these are jargon-heavy. Missing natural user phrases like 'build an agent', 'create autonomous workflow', or 'agent reliability'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on autonomous agents and specific patterns like ReAct provides some distinctiveness, but the broad scope ('production reliability', 'goal decomposition') could overlap with general coding, architecture, or planning skills. | 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 content is incomplete and lacks actionable guidance. While it attempts progressive disclosure by linking to sub-skills, the main file provides no concrete examples, workflows, or executable code. The philosophical framing about agent reliability is interesting but doesn't translate into practical instructions Claude can follow.
Suggestions
Add a concrete 'Quick Start' section with executable code showing a minimal agent loop implementation
Include a decision flowchart or checklist for choosing between ReAct vs Plan-Execute patterns
Add brief summaries (1-2 sentences each) for each sub-skill link explaining when to use each pattern
Complete the truncated content and remove the redundant 'Capabilities' list that duplicates the sub-skill links
| 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 given the sub-skill links. The content appears truncated mid-sentence. | 2 / 3 |
Actionability | No concrete code, commands, or executable examples are provided. The content describes concepts and links to sub-skills but offers no actionable guidance in the main skill file itself - just abstract philosophy about autonomy being 'earned.' | 1 / 3 |
Workflow Clarity | No workflow or sequence is defined. The skill mentions concepts like 'guardrails before capabilities' but provides no steps, validation checkpoints, or process for building agents. The content is purely conceptual with no operational guidance. | 1 / 3 |
Progressive Disclosure | The skill does link to sub-skills with clear naming (ReAct, Plan-Execute, etc.), which is good structure. However, the main file provides almost no overview content - it's essentially just links with minimal context about what each sub-skill covers or when to use them. | 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
- Dokhacgiakhoa/antigravity-ide
- Commit
3395991
- 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.