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

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/autonomous-agent-patterns/SKILL.md

Quality

Content

71%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 body is a well-structured, token-efficient overview that practices clean progressive disclosure with a single real, one-level-deep reference; its weakness is that no executable guidance lives in the body itself, all actionability being delegated to the guide.

Suggestions

Add a brief inline quick-start snippet (e.g., a minimal agent-loop or tool-schema sketch) so the body carries some executable guidance rather than delegating all of it to the guide.

Remove the redundant opening blockquote that repeats the frontmatter description verbatim to tighten token efficiency.

Tighten the generic Limitations boilerplate so only skill-specific constraints remain.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, but the opening blockquote duplicates the frontmatter description verbatim and the Limitations section is near-generic boilerplate, so it is efficient with minor instances that could be trimmed rather than perfectly lean.	4 / 5
Actionability	The body offers concrete trigger guidance ('Use this skill when: Building autonomous AI agents, Designing tool/function calling APIs, ...') and a clear pointer to the real detailed guide, but contains no executable code or steps in the body itself, leaving key execution details delegated rather than present.	3 / 5
Workflow Clarity	The single sequenced instruction ('Read the detailed guide before executing this skill') is unambiguous, with an explicit validation emphasis ('Treat its safety, prerequisites, and validation requirements as mandatory') and a stop-and-ask limitation, fitting 'clear sequence with most checkpoints present' with only minor gaps.	4 / 5
Progressive Disclosure	The body is a clear overview pointing to exactly one well-signaled reference (references/detailed-guide.md) that is one level deep and does not chain further references; the guide is real (751 lines, well-sectioned), matching the 'clear overview with well-signaled one-level-deep references' anchor.	5 / 5
	Total	16 / 20 Passed

Description

48%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 names its niche and third-person voice is correct, but it lacks concrete action specificity and any 'Use when' trigger clause, capping completeness and specificity at low-mid scores.

Suggestions

Add an explicit 'Use when ...' trigger clause listing concrete scenarios (e.g., when designing tool/function-calling APIs or human-in-the-loop approval systems) to raise completeness above 3.

Replace the generic verbs 'design patterns'/'building' with 2-3 concrete capabilities (e.g., 'implement tool-calling APIs, design permission/approval systems, automate browsers') to improve specificity.

Include natural synonyms users would say ('AI agents', 'tool calling', 'function calling') alongside the named products to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('building autonomous coding agents') but the only actions ('design patterns', 'building') are generic and not concrete capabilities, matching the 'names domain but actions are minimal or generic' anchor; it does not list specific actions like tool-calling or approval systems (which appear only in the body).	2 / 5
Completeness	It gives a clear 'what' ('Design patterns for building autonomous coding agents') but has no 'Use when...' or equivalent trigger clause, so per the missing-trigger cap it cannot exceed 3; this matches the 'clear what but when missing or only weakly implied' anchor.	3 / 5
Trigger Term Quality	It includes the natural term 'autonomous coding agents' and named products (Cline, OpenAI Codex) users might mention, but lacks common variations/synonyms like 'AI agents', 'tool calling', or 'function calling', matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	It carves a fairly clear niche (autonomous coding agents) with distinct named inspirations, but 'design patterns for building agents' could still overlap with general agent-building skills, fitting 'mostly distinct; minor overlap risk' better than the fully-distinct 5 anchor.	4 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/autonomous-agent-patterns/SKILL.md
Commit: b1aebac

Reviewed: ~18 hours 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.