autonomous-loops

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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, highly actionable reference with executable code, clear sequenced workflows, and explicit feedback loops for error recovery. Its weaknesses are conciseness (overall length plus a time-sensitive version note placed outside a deprecated section) and progressive disclosure (everything inline with no external reference files).

Suggestions

Move the v1.8.0 compatibility/deprecation note into a clearly labeled "Deprecated / Old patterns" section so time-sensitive version information does not penalize conciseness.

Split the larger pattern sections (e.g. Continuous Claude PR Loop, Ralphinho DAG) into one-level-deep reference files referenced from a leaner overview, improving progressive disclosure.

Trim the ASCII architecture diagrams or consolidate overlapping tables to tighten token usage without losing the concrete commands.

Dimension	Reasoning	Score
Conciseness	Most content earns its place as reference material Claude would not already know (community patterns, flags, interfaces) and avoids explaining basics, but the body is very long and the time-sensitive v1.8.0 compatibility note sits at the top rather than in a deprecated/old-patterns section, so it is mostly efficient with some tightening needed.	2 / 3
Actionability	It provides abundant executable, copy-paste-ready guidance: concrete `claude -p` bash pipelines, model-routing and --allowedTools flags, continuous-claude CLI invocations with real flags, and a TypeScript WorkUnit interface, matching the anchor for fully executable commands and specific examples.	3 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced with validation and feedback loops: the Continuous Claude loop numbers each step with CI-check polling and retry, and the Ralphinho merge queue includes eviction capture and context-fed re-runs, satisfying the anchor for clear sequences with explicit validation and error-recovery loops.	3 / 3
Progressive Disclosure	No bundle files exist in references/scripts/assets, so all ~600 lines live inline in SKILL.md with no one-level-deep references; the section organization is clear, but content that could be split into per-pattern reference files is inline, matching the anchor for some structure with content that should be separate kept inline.	2 / 3
	Total	10 / 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 is specific and in correct third-person voice, naming a clear domain and two concrete pattern types, but it lacks any explicit "Use when..." trigger guidance. This caps completeness and leaves trigger-term and distinctiveness coverage at a moderate level.

Suggestions

Append a "Use when..." clause naming natural triggers, e.g. setting up autonomous/continuous Claude Code loops, choosing a loop architecture, or building CI-style development pipelines.

Soften the jargon ("RFC-driven multi-agent DAG systems") or pair it with plainer natural terms ("multi-agent parallel workflows") so the description matches what users actually say.

Differentiate from the canonical continuous-agent-loop skill in the description itself, since the body notes an overlap/deprecation risk.

Dimension	Reasoning	Score
Specificity	Names the domain ("autonomous Claude Code loops") and two concrete pattern types ("simple sequential pipelines" and "RFC-driven multi-agent DAG systems"), but does not comprehensively list multiple concrete actions, matching the anchor that names a domain and some actions without being comprehensive.	2 / 3
Completeness	It clearly states what the skill covers ("Patterns and architectures for autonomous Claude Code loops") but provides no explicit "when to use" trigger guidance, so per the rubric a missing Use-when clause caps completeness at 2.	2 / 3
Trigger Term Quality	"autonomous Claude Code loops" is a term a user might say, but "RFC-driven multi-agent DAG systems" is technical jargon and no "Use when..." clause supplies common natural variations, so coverage is partial rather than strong.	2 / 3
Distinctiveness Conflict Risk	The niche is reasonably specific to autonomous loops, but it overlaps with the noted canonical "continuous-agent-loop" skill and lacks explicit distinct triggers, so it could still overlap with a similar skill rather than being clearly conflict-free.	2 / 3
	Total	8 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (611 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: affaan-m/ECC
Commit: 4130457

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.