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).

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Quality

Content

65%

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

The body is a strong, action-oriented patterns catalog with rich executable examples, but it is long and monolithic, lacks a sequenced workflow with validation checkpoints, and buries time-sensitive model identifiers inline. Actionability is excellent; the other dimensions are mid-range.

Suggestions

Split large independent sections (e.g., Browser Automation, MCP Integration) into reference files linked from a concise overview in SKILL.md to improve progressive disclosure and token efficiency.

Add an explicit end-to-end build workflow with validation checkpoints (e.g., define tools -> configure permissions -> validate sandbox -> test approval flow) rather than only a flat best-practices checklist.

Move hardcoded model identifiers ('gpt-3.5-turbo', 'claude-3-sonnet') into a parameterized or 'deprecated/old patterns' section so time-sensitive specifics do not age the guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, executable code, but at ~770 lines it is verbose, includes didactic commentary and an ASCII diagram, and hardcodes time-sensitive model names ('gpt-3.5-turbo', 'claude-3-sonnet') outside any deprecated section, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'.	2 / 3
Actionability	It provides extensive concrete, largely executable Python class examples (AgentLoop, EditFileTool, ApprovalManager, SandboxedExecution, BrowserTool, MCPAgent) that are essentially copy-paste ready, matching the 'fully executable code/commands; specific examples' anchor.	3 / 3
Workflow Clarity	Numbered sections and a Best Practices Checklist give structure, but there is no sequenced build workflow with explicit validation checkpoints or feedback loops for the destructive and sandboxed operations described, matching 'steps listed but validation gaps'.	2 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so the skill is a single monolithic ~770-line file with content such as browser automation and MCP that should be split into separate files; clear numbered sections keep it above a 'wall of text', matching 'some structure but content that should be separate is inline'.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 clearly identifies its domain and inspiration but is generic: it states what without an explicit when-to-use trigger and without enumerating concrete capabilities. It sits squarely at the middle of the scale across all dimensions.

Suggestions

Add an explicit 'Use when...' clause with natural trigger terms (e.g., building AI coding agents, designing tool-calling/function-calling APIs, or setting up agent permission/approval systems).

Replace the abstract 'design patterns for building' phrasing with a short list of concrete actions the skill delivers (e.g., 'implement agent loops, design tool schemas, add permission and sandboxing systems').

Include common user-facing variations of the trigger terms ('AI agent', 'tool calling', 'function calling', 'agent loop') to improve distinctiveness and recall.

Dimension	Reasoning	Score
Specificity	The description names the domain ('autonomous coding agents') and an action category ('design patterns for building') but does not list multiple specific concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It states what the skill covers but provides no explicit 'Use when...' trigger guidance, so per the judging guidelines completeness is capped at 2 ('has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	'autonomous coding agents' is a relevant phrase a user might say, but it is somewhat technical and misses common variations such as 'AI agent', 'tool calling', or 'function calling', fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	'autonomous coding agents' is a reasonably distinct niche, but the broad 'design patterns for building' phrasing could still overlap with general coding or AI-development skills, matching the 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: boisenoise/skills-collections
Commit: f36337d

Reviewed: 2 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.