autonomous-agent-patterns
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool ...
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill autonomous-agent-patterns71
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillAgent success when using this skill
Validation for skill structure
Discovery
67%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 has good structure with an explicit 'Use when' clause and covers a specific domain (autonomous coding agents). However, it lists topic areas rather than concrete actions, and the truncation prevents full evaluation of trigger term coverage. The description would benefit from more action-oriented language.
Suggestions
Replace topic areas with concrete actions (e.g., 'Guides implementation of tool calling, designs permission flows, structures agent loops' instead of 'Covers tool integration, permission systems')
Add more natural trigger term variations users might say, such as 'agentic systems', 'agent architecture', 'LLM agents', 'autonomous AI'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (autonomous coding agents) and lists several areas covered (tool integration, permission systems, browser automation, human-in-the-loop workflows), but these are topic areas rather than concrete actions the skill performs. | 2 / 3 |
Completeness | Clearly answers 'what' (design patterns for autonomous coding agents covering specific topics) and includes explicit 'Use when' clause with trigger scenarios (building AI agents, designing tool...). Despite truncation, the structure is complete. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'AI agents', 'tool integration', 'browser automation', but the description is truncated and may be missing additional trigger terms. Terms like 'coding agents' and 'autonomous' are somewhat natural but could include more variations users might say. | 2 / 3 |
Distinctiveness Conflict Risk | Focuses on autonomous coding agents which is fairly specific, but 'tool integration' and 'design patterns' could overlap with general software architecture or other agent-related skills. The niche is reasonably clear but not maximally distinct. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive, actionable skill with excellent code examples covering autonomous agent patterns. The main weaknesses are verbosity (could trim explanatory text Claude doesn't need) and the monolithic structure that puts all detailed implementations in one file rather than using progressive disclosure to separate overview from deep-dive content.
Suggestions
Remove the 'When to Use This Skill' section and inline docstring explanations that describe obvious functionality - Claude can infer these
Split detailed implementations (browser automation, MCP integration, checkpoint management) into separate reference files, keeping SKILL.md as a concise overview with links
Add explicit validation checkpoints to workflows, especially for the 'create_tool' pattern which generates and executes code dynamically
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary explanatory text (e.g., 'Use different models for different purposes' comments, verbose docstrings). The 'When to Use This Skill' section adds little value for Claude. Could be tightened by ~20-30%. | 2 / 3 |
Actionability | Provides fully executable Python code throughout with concrete implementations of agent loops, tools, permission systems, and browser automation. Code is copy-paste ready with proper imports and class structures. | 3 / 3 |
Workflow Clarity | The agent loop pattern is clear, but validation checkpoints are implicit rather than explicit. The checklist at the end mentions safety but doesn't integrate validation steps into the workflows. Missing explicit 'validate -> fix -> retry' loops for risky operations like tool creation. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and a table of contents via numbered headers. However, this is a monolithic 400+ line file that could benefit from splitting detailed implementations (browser automation, MCP integration) into separate reference files. External resources are listed but internal progressive disclosure is lacking. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (765 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- 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.