squad-commands

Categorized catalog of common Squad operations. Coordinator reads this file and presents it as an interactive menu when the user asks for available commands or help.

Quality

85%

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

Quality

Content

80%

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 command catalog with concrete commands and well-structured category sections. Its main gaps are the absence of post-action validation/feedback loops for destructive operations and a monolithic single-file structure with no progressive disclosure.

Suggestions

Add a brief post-action verification step for confirm:true operations (e.g., after Remove Team Member, re-read team.md to confirm the member and their charter/history are gone) so destructive/batch workflows include an explicit validate→fix→retry loop.

Consider splitting the per-category command details into referenced files (e.g. references/upgrade.md, references/team.md) so SKILL.md stays a concise overview with one-level-deep navigation, improving progressive disclosure.

For file-edit actions (Switch State Backend, Set Default Model), add an explicit validation checkpoint (e.g. parse config.json after the edit) to raise workflow clarity on config-mutating operations.

Dimension	Reasoning	Score
Conciseness	Each entry is terse structured fields (intent, summary, command, args, confirm, platform_caveats) with no explanatory padding of concepts Claude already knows, matching the 3-anchor's lean, every-token-earns-its-place quality.	3 / 3
Actionability	Concrete executable commands ("squad upgrade", "squad init", "squad watch --interval {n}") with args carrying explicit choices and defaults are copy-paste ready, matching the 3-anchor's fully executable guidance.	3 / 3
Workflow Clarity	The menu-presentation workflow is clearly sequenced with back/cancel and a confirmation template, but destructive/batch entries (Remove Team Member, Archive Old Decisions, Remove Marketplace Plugin) have no explicit post-action validate→fix→retry feedback loop, which the guidelines say caps workflow clarity at 2; it is not a 3 because validation checkpoints for error recovery are absent, and not a 1 because the sequence and confirmation gates are present.	2 / 3
Progressive Disclosure	No references/scripts/assets bundle exists and the ~300-line command catalog is entirely inline in one file; it is well-sectioned by category (not a 1-anchor wall of text or nested references) but lacks the one-level-deep reference split or <50-line simplicity that the 3-anchor requires.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 cleanly states what the skill is and when to use it with natural, distinctive trigger terms in proper third-person voice. Its only weakness is specificity: it describes the catalog at a category level rather than enumerating concrete operations.

Dimension	Reasoning	Score
Specificity	Quotes "Categorized catalog of common Squad operations" and "presents it as an interactive menu" name the domain and a couple of actions, but unlike the 3-anchor it does not list multiple specific concrete operations (e.g. upgrade, init, triage); it stays at the domain/some-actions level of the 2-anchor.	2 / 3
Completeness	It states both what ("Categorized catalog of common Squad operations") and when ("when the user asks for available commands or help") with explicit trigger guidance, satisfying the 3-anchor's requirement to clearly answer both what AND when.	3 / 3
Trigger Term Quality	Triggers "squad commands", "what can squad do", "show me squad options", "slash commands" plus "help" are natural phrasings a user would actually say, matching the 3-anchor's good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	The Squad-operations command-catalog niche with Squad-specific triggers ("squad commands", "what can squad do") is clearly distinguishable and unlikely to fire for unrelated skills, matching the 3-anchor's distinct niche.	3 / 3
	Total	11 / 12 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-commands/SKILL.md
Commit: e23dd92

Reviewed: 1 day 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.