autonomous-agent-patterns
Design patterns for building autonomous coding agents, inspired by [Cline](https://github.com/cline/cline) and [OpenAI Codex](https://github.com/openai/codex).
33
18%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-autonomous-agent-patterns/SKILL.mdQuality
Discovery
22%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 is too vague and abstract, reading more like a topic label than an actionable skill description. It lacks concrete actions the skill performs and entirely omits explicit trigger guidance ('Use when...'). The references to Cline and OpenAI Codex add some distinctiveness but don't compensate for the missing specificity and completeness.
Suggestions
Add a 'Use when...' clause specifying triggers, e.g., 'Use when the user asks about building coding agents, agentic tool-use loops, or autonomous code generation architectures.'
List specific concrete actions the skill provides, e.g., 'Describes agent loop patterns, tool-calling architectures, sandboxed execution strategies, and error-recovery mechanisms for autonomous coding agents.'
Include additional natural trigger terms users might say, such as 'agentic coding', 'agent loop', 'tool use pattern', 'code agent architecture', or 'autonomous developer tools'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'design patterns for building autonomous coding agents' but does not list any concrete actions. It references inspirations (Cline, OpenAI Codex) but doesn't specify what the skill actually does—no verbs like 'generates', 'scaffolds', 'implements' are present. | 1 / 3 |
Completeness | The description partially addresses 'what' (design patterns for coding agents) but is vague, and there is no 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | It includes some relevant keywords like 'autonomous coding agents', 'design patterns', 'Cline', and 'OpenAI Codex' that a user might mention. However, it misses common variations like 'agentic', 'tool use', 'code generation loop', 'agent architecture', or 'coding assistant'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'autonomous coding agents' and specific projects (Cline, OpenAI Codex) provides some distinctiveness, but 'design patterns' is broad enough to overlap with general software architecture or coding pattern skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a verbose catalog of autonomous agent design patterns that reads more like a tutorial or reference document than a concise, actionable skill file. It explains many concepts Claude already understands, includes lengthy code examples that aren't fully executable, and lacks any workflow sequencing or validation steps. The monolithic structure with no progressive disclosure makes it an inefficient use of context window.
Suggestions
Reduce content to under 100 lines by providing only the unique, non-obvious patterns (e.g., the edit tool's occurrence validation, the permission level enum) and removing patterns Claude can generate from brief descriptions.
Split detailed sections (browser automation, MCP integration, sandboxing, context management) into separate referenced files and keep SKILL.md as a concise overview with links.
Add a concrete workflow with numbered steps and validation checkpoints for building an agent end-to-end (e.g., 1. Define tools → 2. Implement permission layer → 3. Test with dry-run → 4. Enable live execution).
Make code examples fully executable by including all imports, defining ToolResult, and ensuring examples can run standalone—or explicitly note they are design patterns and provide a working minimal example separately.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~600+ lines. Explains basic concepts Claude already knows (what an agent loop is, how file I/O works, what browser automation is). The multi-model architecture section explains obvious model selection logic. Much of the code is illustrative boilerplate that doesn't add unique value—Claude can generate these patterns from brief descriptions. | 1 / 3 |
Actionability | The code examples are fairly concrete and near-executable, but they rely on undefined imports (ToolResult, playwright, html_to_markdown), missing class definitions, and incomplete implementations. They serve more as design pattern illustrations than copy-paste-ready code. The MCP section uses a fictional 'from mcp import Server, Tool' that doesn't match real MCP SDKs. | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow for actually building an agent. The content presents isolated pattern snippets without sequencing them into a coherent build process. There are no validation checkpoints, no 'do this then verify that' steps. The checklist at the end is generic and not tied to concrete verification actions. | 1 / 3 |
Progressive Disclosure | All content is monolithically inlined in a single massive file with no references to supporting files. There are no bundle files, yet the content is far too long for a single SKILL.md. Sections like browser automation, MCP integration, and context management could each be separate referenced documents. The external links at the bottom are general resources, not structured skill references. | 1 / 3 |
Total | 5 / 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 (770 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 | |
- Repository
- boisenoise/skills-collections
- Commit
431bfad
- 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.