continuous-agent-loop

Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

Quality

61%

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

72%

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

The body is lean and well-organized with a useful selection flow and recovery list, but it stays at the level of named patterns rather than executable instruction and lacks validation checkpoints for risky loop operations. It is a good index-style overview that would benefit from concrete commands and a validate-then-proceed loop.

Suggestions

Add at least one executable example (e.g., the command or config to start a loop and run `/quality-gate`), so guidance is actionable rather than just directional.

Insert explicit validation checkpoints in the recovery flow, e.g. 'run `/harness-audit`, confirm churn metric improved, then resume' rather than a flat bullet list.

If the named external patterns (ralphinho-rfc-pipeline, eval-harness, etc.) are real referenced skills, link them as one-level-deep references so navigation is explicit.

Dimension	Reasoning	Score
Conciseness	The body is short and dense; it assumes Claude's competence and adds only domain specifics (named patterns, a selection flow, failure modes), with no padding or explanation of concepts Claude already knows.	3 / 3
Actionability	It points to named patterns and tools (`ralphinho-rfc-pipeline`, `plankton-code-quality`, `/quality-gate`, `eval-harness`, `nanoclaw-repl`) and gives a selection decision tree, but provides no executable commands or concrete steps for actually running a loop, so guidance is directional rather than copy-paste ready.	2 / 3
Workflow Clarity	The selection flow is a clear sequence and the recovery section lists ordered steps, but there are no validation checkpoints or feedback loops for the batch/destructive loop operations described, which the rubric requires for a 3.	2 / 3
Progressive Disclosure	This is a short, single-purpose overview skill with no bundle files; its content is well-organized into clearly labeled sections (selection flow, combined pattern, failure modes, recovery), which the rubric's simple-skill note allows to score 3.	3 / 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 names a specific domain and its pillars (quality gates, evals, recovery) but reads as a noun-phrase label rather than action-oriented guidance and omits any 'Use when' trigger. It is serviceable but stops just short of the strong examples.

Suggestions

Lead with concrete verbs, e.g. 'Operate continuous autonomous agent loops by wiring quality gates, evals, and recovery controls into them.'

Add an explicit trigger clause, e.g. 'Use when running a long-lived agent loop, diagnosing loop churn, or guarding PR/CI with quality gates and evals.'

Surface natural user phrasings such as 'agent loop', 'CI/PR loop', 'eval harness', or 'loop stuck/churning' as keywords.

Dimension	Reasoning	Score
Specificity	Phrases like 'continuous autonomous agent loops', 'quality gates', 'evals', and 'recovery controls' name the domain and several constituent capabilities, but they describe categories of patterns rather than concrete actions the skill performs.	2 / 3
Completeness	It states what the skill covers ('Patterns for ... loops with ... gates, evals, and recovery'), but there is no 'Use when...' clause or equivalent explicit guidance on when to invoke it, which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	'agent loops', 'quality gates', and 'evals' are plausible search terms, but 'continuous autonomous agent loops' is more internal jargon than something a user would naturally say; common variations like 'CI/PR loop' or 'agent churn' are absent.	2 / 3
Distinctiveness Conflict Risk	The 'continuous autonomous agent loops' niche is fairly specific and unlikely to broadly conflict, but without explicit triggers it could still overlap with adjacent loop/orchestration skills.	2 / 3
	Total	8 / 12 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: 754b8dd

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.