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

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/autonomous-agent-patterns/SKILL.md

The canonical home for this skill is autonomous-agent-patterns in sickn33/agentic-awesome-skills

Quality

Content

53%Weight 40%Scale 1-5

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

The content is a well-organized, actionable catalog of concrete code patterns, but it is a monolithic 750-line single file with no progressive disclosure and includes outdated hard-coded model names. Workflow guidance is pattern-based rather than checkpointed.

Suggestions

Move the bulkier code catalogs (tool schemas, browser automation, MCP integration) into separate reference files under references/ and keep SKILL.md as a concise overview with one-level-deep links.

Remove or relocate hard-coded model names ("gpt-3.5-turbo", "claude-3-sonnet") to a deprecated/old-patterns section, or replace them with role-based placeholders ('fast model', 'smart model').

Add an explicit end-to-end workflow with validation checkpoints for destructive operations (e.g. validate path/command -> execute sandboxed -> verify result) rather than presenting each safety pattern in isolation.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean code with little prose padding, but at ~750 lines it is voluminous for a SKILL.md and includes time-sensitive hard-coded model names ("gpt-3.5-turbo", "claude-3-sonnet") that the rubric penalizes unless placed in a deprecation section.	3 / 5
Actionability	It provides concrete, mostly-executable Python class examples across tool design, permissions, sandboxing, and browser automation, with only minor gaps (missing imports and illustrative-only patterns like the MCP code-gen block).	4 / 5
Workflow Clarity	Content is organized as numbered topical sections rather than a sequenced workflow, and destructive/batch operations (run_command, delete_file, sandboxing) are presented as patterns without explicit validate-then-proceed checkpoints, capping this dimension at 3.	3 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets directories are absent) and the entire catalog is inlined into a single ~750-line SKILL.md; large blocks like the full tool schemas and browser automation code clearly belong in separate reference files.	2 / 5
	Total	12 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 states the domain and inspiration sources but lacks any explicit trigger guidance and enumerates no concrete capabilities. It is reasonably distinctive but generic in its action language.

Suggestions

Add an explicit 'Use when...' clause listing concrete triggers, e.g. 'Use when building autonomous coding agents, designing tool/function-calling APIs, or implementing permission and approval systems.'

Replace the abstract 'design patterns' with 2-3 concrete capabilities (tool schema design, permission/sandboxing patterns, browser automation) so specificity rises above 3.

Include natural keyword variations users would say (agent loop, tool calling, human-in-the-loop, sandboxing) alongside the brand references.

Dimension	Reasoning	Score
Specificity	The phrase "Design patterns for building autonomous coding agents" names the domain and the action area, but 'design patterns' is abstract and does not enumerate concrete capabilities (permissions, tool design, browser automation) found in the body.	3 / 5
Completeness	It gives a clear 'what' (design patterns for building autonomous coding agents, inspired by Cline/Codex) but no 'when' / 'Use when...' clause; the rubric caps completeness at 3 when explicit trigger guidance is missing.	3 / 5
Trigger Term Quality	"autonomous coding agents" plus the brand names "Cline" and "OpenAI Codex" provide some relevant keywords, but common natural variations a user would say (tool calling, permission/approval systems, browser automation) are absent.	3 / 5
Distinctiveness Conflict Risk	The autonomous coding-agent niche plus the explicit Cline/OpenAI Codex brand references make it mostly distinct from other skills, with only minor overlap risk against general agent-design skills.	4 / 5
	Total	13 / 20 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 (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	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/autonomous-agent-patterns/SKILL.md
Commit: debb2ec

Reviewed: 1 day 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.