loop-engineering

Loop engineering runtime Grill + Monitor

Quality

44%

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 ./src/skills/loop-engineering/SKILL.md

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 a concise, well-sectioned instruction set with concrete callback signatures and enum choices, but it stops short of fully actionable guidance: it never shows how to actually invoke a loop and leaves the iterative verify-retry-escalate workflow implicit rather than explicitly sequenced with checkpoints.

Suggestions

Add a concrete end-to-end example showing how to start a loop, including the orchestrator call and an example successCommand/successPath, so the guidance is copy-paste ready.

Spell out the execute→verify→retry→escalate sequence with explicit checkpoints (e.g., "on failure, increment attempt; at max attempts, call onEscalated"), including the manual-review pause and resolveManualReview flow as a numbered loop.

Briefly define opaque terms inline ("autoresearch pattern", "Grill") or drop them if they add tokens without aiding execution.

Dimension	Reasoning	Score
Conciseness	The body is lean bullets and callback signatures with no padding or explanation of concepts Claude already knows; every line carries information, though some jargon ("autoresearch pattern") is terse.	3 / 3
Actionability	It gives concrete identifiers (callback signatures, success-type enums, resolveManualReview/cancel calls) but is incomplete: there is no executable invocation example and the orchestrator API to actually start or run a loop is unspecified.	2 / 3
Workflow Clarity	The Grill interview is sequenced (steps 1-7) and callbacks are listed, but the iterative execute→verify→retry→escalate flow and its validation checkpoints are implied rather than laid out as an explicit ordered workflow.	2 / 3
Progressive Disclosure	No bundle files exist and the skill is under 50 lines with no need for external references; it is well-organized into clear sections (Grill, Loop Monitor, Notes), meeting the simple-skill bar for a 3.	3 / 3
	Total	10 / 12 Passed

Description

17%

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 a terse domain label rather than a capability statement: it names a niche and two components but provides no concrete actions, no natural user trigger terms, and no "when to use it" guidance. It is distinguishable only loosely and relies on opaque internal jargon.

Suggestions

Rewrite as a concrete capability statement with verbs, e.g. "Orchestrates iterative fix-verify loops by interviewing for goals, success criteria, and verification type, then monitoring completion, escalation, and manual review."

Add an explicit "Use when..." trigger clause listing natural phrases a user would say, such as "Use when running a fix-verify loop, retrying until a test/build/lint/command passes, or when manual human verification of a loop is needed."

Replace internal jargon ("Grill") with descriptive language or define it inline so the description reads naturally to a user.

Dimension	Reasoning	Score
Specificity	"Loop engineering runtime Grill + Monitor" names a domain and two sub-components (Grill, Monitor) but describes no concrete actions, sitting between a vague label and a capability statement.	2 / 3
Completeness	It states only a domain label with no real statement of what the skill does, and entirely lacks any "Use when..." trigger guidance, so both what and when are weak.	1 / 3
Trigger Term Quality	"Grill" is internal orchestrator jargon and "Monitor" is generic; a user would not naturally say these words, and there are no natural trigger phrases.	1 / 3
Distinctiveness Conflict Risk	"Loop engineering" is a somewhat specific niche, but opaque jargon ("Grill") and the generic term "Monitor" leave it able to overlap with other monitoring skills.	2 / 3
	Total	6 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alvinunreal/oh-my-opencode-slim
Path: src/skills/loop-engineering/SKILL.md
Commit: 1c0e1f4

Reviewed: about 6 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.