squad-conventions

Core conventions and patterns used in the Squad codebase

Quality

55%

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 ./.copilot/skills/squad-conventions/SKILL.md

Quality

Content

68%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 tight, well-organized conventions reference with concrete code and commands and strong anti-patterns. Its main gap is the absence of a true multi-step workflow with validation checkpoints, which keeps workflow_clarity at 3 despite otherwise strong structure.

Suggestions

Add a short validated workflow for destructive or batch operations (e.g. init/upgrade) with explicit validation checkpoints to raise workflow_clarity.

Provide copy-paste-ready snippets for copyRecursive and the init idempotency check so actionability fully covers common cases.

Trim framing sentences like 'Understanding these patterns is essential...' to push conciseness toward 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, stating hard constraints plainly ('This is a hard constraint, not a preference') with minimal generic explanation. It is not 5 because a few asides ('Understanding these patterns is essential before modifying any Squad source code') could be trimmed.	4 / 5
Actionability	It provides mostly executable guidance: concrete code for fatal() and skip-if-exists, specific commands ('npm test', 'node --test test/'), and named functions (copyRecursive, fatal). It is not 5 because a couple of patterns (e.g. copyRecursive, init idempotency) describe behavior without copy-paste-ready code covering common cases.	4 / 5
Workflow Clarity	This is a conventions/reference skill rather than a sequenced workflow, so patterns are well organized but there is no multi-step process with validation checkpoints. It matches anchor 3 'sequence present but checkpoints missing or implicit' and is not capped by a destructive-op workflow since none is presented.	3 / 5
Progressive Disclosure	Content is well structured into Context, Patterns, Examples, and Anti-Patterns with clear section headers and no nested references. It is not 5 because the body slightly exceeds 50 lines and a few Patterns subsections could be externalized, so it is not the maximally lean single-screen overview.	4 / 5
	Total	15 / 20 Passed

Description

41%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 identifies a clear, distinct niche (Squad codebase conventions) but offers no concrete actions and no 'when to use' trigger guidance, capping completeness. Adding concrete capabilities and a 'Use when...' clause would materially raise the score.

Suggestions

Add concrete capabilities the skill provides, e.g. 'Apply zero-dependency, Node built-in, and fatal()-error-handling conventions when modifying the Squad CLI.'

Append a 'Use when...' trigger clause naming natural phrases users would say, e.g. 'Use when modifying create-squad source, adding error handling, or touching package.json dependencies.'

Replace 'patterns' with specific terms users naturally mention (dependencies, init flow, Windows compatibility) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The phrase 'Core conventions and patterns' names the domain but lists no concrete actions, matching the anchor 'Names the domain but actions are minimal or generic'. It does not reach 3 because no specific capabilities are enumerated.	2 / 5
Completeness	It gives a clear 'what' (core conventions and patterns) but provides no 'when' guidance or 'Use when...' clause, which caps completeness at 3 per the rubric. It is not 4 because there is no explicit trigger guidance at all.	3 / 5
Trigger Term Quality	'conventions', 'patterns', and 'Squad codebase' are one or two generic keywords; the natural phrases a user would actually say are missing. It stays at 2 rather than 3 because there is no broader coverage of synonyms or natural trigger terms.	2 / 5
Distinctiveness Conflict Risk	Tying the description to 'the Squad codebase' gives it a clear niche with only minor overlap risk against general conventions skills. It is not 5 because 'core conventions and patterns' within that niche is still somewhat broad.	4 / 5
	Total	11 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: bradygaster/squad
Path: .copilot/skills/squad-conventions/SKILL.md
Commit: 26d8950

Reviewed: 4 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.