continuous-agent-loop

Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. Use when running an agent loop that must self-check, gate on evals, and recover from failures.

Quality

70%

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 ./skills/continuous-agent-loop/SKILL.md

The canonical home for this skill is tdg-personal/continuous-agent-loop

Quality

Content

65%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 well-structured and concise for an overview/routing skill, but it stops short on actionability and workflow clarity: it references named pipelines and a slash command without executable detail, and its agent-loop workflows lack explicit validation gates despite the destructive/batch nature of the task.

Suggestions

Add a concrete example or minimal command for at least one loop variant (e.g., a sample eval-gate invocation) so the routing targets are actionable rather than just named.

Insert an explicit validation/verification checkpoint into the Recovery workflow (e.g., 'verify eval passes before unfreezing the loop') to satisfy the feedback-loop requirement for batch/destructive operations.

Move the 'v1.8+ supersedes autonomous-loops' version note into a dedicated 'Compatibility' or deprecated-reference line so the time-sensitive metadata does not dilute the overview.

Dimension	Reasoning	Score
Conciseness	The body is lean with terse sectioned lists, but the opening 'v1.8+ canonical ... supersedes autonomous-loops ... for one release' line is time-sensitive version metadata that does not earn its tokens, matching the 'efficient; minor instances that could be trimmed' anchor.	4 / 5
Actionability	It names concrete routing targets (continuous-pr, rfc-dag, infinite, sequential) and a slash command (/harness-audit), but offers no executable code or commands a reader can actually run, fitting 'some concrete guidance but incomplete; missing key details'.	3 / 5
Workflow Clarity	A clear selection decision tree and a sequenced recovery list are present, but there are no explicit validation checkpoints or feedback loops for an inherently batch/destructive agent-loop context, capping it at 3 per the feedback-loop guideline.	3 / 5
Progressive Disclosure	At under 50 lines with no bundle files needed, the content is cleanly organized into well-signaled sections (Loop Selection Flow, Combined Pattern, Failure Modes, Recovery), qualifying for the simple-skill 5 anchor on organization alone.	5 / 5
	Total	15 / 20 Passed

Description

75%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 is strong and explicit: it states the domain, lists concrete capabilities, and provides a clear 'Use when' trigger clause. It is well above midpoint but stops short of top marks because the 'what' is phrased as 'patterns' and a few natural trigger synonyms are missing.

Dimension	Reasoning	Score
Specificity	The description names the domain ('continuous autonomous agent loops') and lists several concrete capabilities — 'quality gates, evals, and recovery controls' — matching the 'lists several specific actions; minor gaps' anchor, falling short of the fully comprehensive 5.	4 / 5
Completeness	Both 'what' ('Patterns for ... loops with quality gates, evals, and recovery controls') and 'when' ('Use when running an agent loop that must self-check, gate on evals, and recover from failures') are present and explicit, but the 'what' is framed as 'Patterns for' rather than directly enumerated actions, leaving it just short of the 5 anchor.	4 / 5
Trigger Term Quality	It includes natural phrases a user would say ('running an agent loop', 'self-check', 'gate on evals', 'recover from failures'), giving good keyword coverage, though a few common synonyms are absent so it is not a 5.	4 / 5
Distinctiveness Conflict Risk	The agent-loop-plus-gates-and-recovery niche is mostly distinct with clear triggers, with only minor overlap risk against closely related general agent skills, fitting the 4 anchor.	4 / 5
	Total	16 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/continuous-agent-loop/SKILL.md
Commit: 06c5e11

Reviewed: 3 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.