Name: install-loop
Rating: 64.8 (1 reviews)
Author: cobusgreyling

install-loop

Install Loop Engineering into a project via the unified CLI front door (@cobusgreyling/loop). Prefer this over invoking loop-init / loop-audit separately. Week-one is report-only; never enable auto-merge or unattended fixes unless the human explicitly asks and doctor is healthy.

Quality

76%

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/install-loop/SKILL.md

Quality

Content

93%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 a lean, highly actionable install runbook with concrete commands and a clear sequenced workflow supported by doctor validation and stop conditions. The only gap is an implicit rather than explicit error-recovery feedback loop in the doctor step.

Dimension	Reasoning	Score
Conciseness	Lean throughout: tables, bullets, and copy-paste commands with no padding explaining what Loop is or basic concepts; every token earns its place.	5 / 5
Actionability	Fully executable copy-paste-ready commands (npx @cobusgreyling/loop init/doctor/cost/badge), a pattern-selection table, tool flags, and exit-code semantics cover the common cases concretely.	5 / 5
Workflow Clarity	Clearly sequenced 1-7 steps with a doctor validation checkpoint (exit 0/1/2) and stop-condition guards; the error-recovery feedback loop is only implicit ('follow the top 3 printed actions') rather than an explicit validate-fix-retry loop, so it sits just below the top anchor.	4 / 5
Progressive Disclosure	Well-organized single-level sections (Goal, Steps, Compatibility, Stop conditions) with no nested references and no bundle files needed; easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

58%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 concrete and well-scoped to a specific product, but lacks an explicit 'Use when...' trigger clause and leans on product jargon rather than natural user phrasing. Tightening the trigger guidance would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when setting up Loop Engineering in a repo or when the user asks to install/scaffold loop') to satisfy the completeness trigger requirement.

Include natural user-facing trigger phrases (e.g., 'set up loop', 'scaffold loop', 'loop ready score') alongside the product terms so users naturally invoke this skill.

Clarify the distinction from loop-init/loop-audit in one phrase so the sibling overlap does not create ambiguity about when each applies.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions (install via CLI, prefer over loop-init/loop-audit, report-only week-one, guard auto-merge) with only minor coverage gaps, fitting between the 1-2-action and comprehensive anchors.	4 / 5
Completeness	Has a clear 'what' (install Loop Engineering via the unified CLI) but the 'when' is only weakly implied by constraints; per guideline, the missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant product terms (@cobusgreyling/loop, loop-init/loop-audit, doctor, report-only) but these lean technical-jargon heavy and lack natural user-facing synonyms or an explicit 'Use when...' trigger phrase.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear product niche with distinct triggers, but explicitly coexists with sibling loop-init/loop-audit doors, creating minor overlap risk with closely related skills.	4 / 5
	Total	14 / 20 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: cobusgreyling/loop-engineering
Path: skills/install-loop/SKILL.md
Commit: 0dc0f3f

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.