personal-squad

User-level AI agents that travel with you across projects

Quality

65%

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/personal-squad/SKILL.md

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 concise and highly actionable with concrete commands, paths, and config examples. Its main weaknesses are that the "workflow" is a runtime description without checkpoints, and a referenced template file is missing from the bundle.

Suggestions

Provide the missing templates/ghost-protocol.md file (or inline the full ghost-protocol rules) so the reference resolves.

Reframe "How It Works" as an explicit user workflow with numbered, verifiable steps and a checkpoint (e.g., confirm agents appear via "squad cast").

Add a brief verification step after "squad personal add" so users can confirm the agent was registered.

Dimension	Reasoning	Score
Conciseness	The body is lean: short sections, bullet lists, command and config blocks, and minimal prose, with little explanation of concepts Claude already knows. Not a 2 because there is no padding to trim.	3 / 3
Actionability	Concrete executable commands ("squad personal init", "squad personal add {name} --role {role}"), exact directory paths, real env vars, and a copy-paste config.json example give fully actionable guidance.	3 / 3
Workflow Clarity	"How It Works" lists numbered runtime steps, but it describes system behavior rather than a guided user procedure and lacks validation checkpoints; not a 3 because it is not a sequenced task workflow.	2 / 3
Progressive Disclosure	Sections are well organized and the ghost-protocol detail is split out via a one-level reference, but the referenced file "templates/ghost-protocol.md" does not exist in the bundle, breaking navigation; not a 3 because of that dangling reference.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 concise and identifies a clear niche, but it reads as a definition rather than a trigger-rich skill description and lacks an explicit "when to use" clause. Most dimensions land at the midpoint as a result.

Suggestions

Add concrete actions the agents perform (e.g., "advise, review, and propose changes") to raise specificity.

Append a "Use when..." clause naming natural triggers such as wanting persistent personal agents across projects.

Sharpen distinctiveness by contrasting explicitly with project agents in the description itself.

Dimension	Reasoning	Score
Specificity	"User-level AI agents that travel with you across projects" names a domain and one behavior but does not list multiple concrete actions; not comprehensive, so it is not a 3.	2 / 3
Completeness	It states what the skill provides (user-level AI agents) but has no "Use when..." or equivalent trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	"AI agents" and "projects" are natural terms a user might say, but the phrasing is definitional and misses common variations or explicit triggers, falling short of full coverage.	2 / 3
Distinctiveness Conflict Risk	The "user-level / travel across projects" framing is somewhat distinctive from project-scoped skills, but "AI agents" is broad enough that it could still overlap with related skills.	2 / 3
	Total	8 / 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/personal-squad/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.