squad-help

How to actually use Squad — Squad is a custom Copilot agent (invoked via the task tool with agent_type='Squad'), not a skill. This file explains the right invocation paths for setting up a team, listing squad commands, and initializing Squad in a new project.

Quality

74%

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 ./.squad/skills/squad-help/SKILL.md

Quality

Content

86%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 strong, actionable routing guide with copy-ready invocations, clear intent-mapped paths, and clean one-level references. The only slack is minor meta-content (the discovery section) that could be trimmed for token efficiency.

Dimension	Reasoning	Score
Conciseness	The core routing guidance is lean and instructional, but the 'How this skill was discovered' section and MANIFEST_SKILL_NAMES detail are meta-context that don't earn their tokens for acting on the skill.	4 / 5
Actionability	Provides copy-paste-ready task() and `squad init` invocations plus concrete natural-language trigger strings and an explicit anti-pattern list, covering the common cases fully.	5 / 5
Workflow Clarity	Three intent-to-path routes (A/B/C) are clearly sequenced with disambiguation guards, but no error-recovery feedback loop is given for failed invocations.	4 / 5
Progressive Disclosure	A well-sectioned overview with one-level-deep, clearly signaled 'See also' references to the actual agent and sibling skill files, with no nested-reference problem.	5 / 5
	Total	18 / 20 Passed

Description

62%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 clearly establishes a distinct niche and names concrete actions, but it omits an explicit 'Use when...' trigger clause and leans on technical invocation jargon rather than natural user phrasing. Adding natural trigger phrases and an explicit use-when clause would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when the user says "use Squad", "set up a squad", or asks about Squad commands' clause to satisfy the completeness 'when' requirement.

Replace or augment the technical 'agent_type=\"Squad\"' phrasing with the natural terms users actually say ("use squad", "squad help", "set up an AI team").

Lead with the user-facing intent before the internal invocation mechanics so the description reads as a trigger match rather than an implementation note.

Dimension	Reasoning	Score
Specificity	Names the Squad-invocation domain and three concrete actions (setting up a team, listing squad commands, initializing Squad in a new project), sitting above the 1-2 action anchor but below comprehensive.	4 / 5
Completeness	Provides a clear 'what' but lacks an explicit 'Use when...' trigger clause, and the 'when' is only weakly implied via invocation description, capping completeness per the rubric guideline.	3 / 5
Trigger Term Quality	Includes technical invocation phrases (agent_type='Squad', task tool) but misses the natural colloquial phrases users actually say like 'use squad' or 'squad help' that the body itself emphasizes.	3 / 5
Distinctiveness Conflict Risk	Explicitly carves a distinct niche (Squad is a custom agent, not a skill) and disambiguates agent vs skill vs slash-command, yielding minimal conflict risk.	5 / 5
	Total	15 / 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: .squad/skills/squad-help/SKILL.md
Commit: a0d2563

Reviewed: about 15 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.