loop-library

Compatibility alias for Loopy. Use only when an existing installation or older instruction explicitly invokes loop-library; use Loopy for new installations and requests. Provides the same discovery, recommendation, audit, repair, adaptation, guided crafting, bounded execution, run debrief, project loop saving, and publication-preparation workflows.

Quality

85%

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

Quality

Content

85%Weight 40%Scale 1-3

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

The content is a well-structured instruction skill with actionable scripts, templates, explicit validation, and clean one-level-deep reference delegation. Its main weakness is conciseness, as grounding and feedback-cycle guidance is restated across sections.

Suggestions

Consolidate the repeated grounding rules ("Keep every workflow grounded" plus the per-section untrusted-evidence reminders) into a single canonical statement referenced where needed.

Tighten the overlap between "Craft a loop through an interview", "Design the feedback cycle", and "Validate every crafted loop" to reduce restated feedback-cycle language.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence and avoids explaining known concepts, but grounding rules and feedback-cycle guidance recur across several sections, adding length that could be tightened.	2 / 3
Actionability	Provides exact routing, a verbatim interview script, a concrete delivery markdown template, a compression guide, and an explicit LOOPS.md field list — concrete and copy-ready rather than abstract.	3 / 3
Workflow Clarity	Multi-step process is clearly sequenced (route → workflow → design → validate → deliver) with explicit validation checkpoints such as the silent preflight cycle and approval gating for destructive/external actions.	3 / 3
Progressive Disclosure	The body is an overview that delegates each workflow to a one-level-deep, clearly signaled reference (discover.md, audit.md, run.md, debrief.md, publish.md), all verified to exist with no further nesting.	3 / 3
	Total	11 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 defines a compatibility alias, names many concrete workflows, and gives explicit when-to-use guidance that separates it from the primary Loopy skill. Trigger-term coverage is the weakest point, relying on the single alias token.

Suggestions

Add a couple of natural trigger variations beyond the bare "loop-library" token so the description matches how users actually phrase legacy invocations.

Consider naming the single most representative workflow first so the long enumeration does not dilute the core capability.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "discovery, recommendation, audit, repair, adaptation, guided crafting, bounded execution, run debrief, project loop saving, and publication-preparation workflows" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ("Provides the same ... workflows") and when ("Use only when an existing installation or older instruction explicitly invokes loop-library; use Loopy for new installations").	3 / 3
Trigger Term Quality	The explicit trigger token "loop-library" is named ("explicitly invokes loop-library"), but natural-term coverage is narrow with few common variations, so it lands above the no-keyword anchor but below full coverage.	2 / 3
Distinctiveness Conflict Risk	Scoped as a legacy alias with explicit guidance to prefer Loopy for new use, giving it a clear niche and low conflict risk with the primary skill.	3 / 3
	Total	11 / 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: Forward-Future/loopy
Path: skills/loop-library/SKILL.md
Commit: 75966cb

Reviewed: 2 months 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.