agent-squad

Main agent orchestrator that coordinates a specialized squad of agents

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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 well-structured, actionable orchestrator guide with clear sequenced workflows and concrete templates. Its main weakness is conciseness and the absence of progressive disclosure — everything lives inline in a single long file.

Suggestions

Move the detailed per-agent table and the full briefing-packet/state templates into a referenced file (e.g. AGENTS.md) and keep SKILL.md as a lean overview with one-level-deep links.

Trim redundancy by merging 'What the Main Agent Never Does' into Core Principles rather than restating the same constraints.

Consider extracting the routing-logic matrices into a separate ROUTING.md reference to reduce the inline token footprint.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with useful concrete templates, but the 'What the Main Agent Never Does' section reiterates Core Principles and the overall length could be tightened, matching 'mostly efficient but could be tightened'.	2 / 3
Actionability	It provides concrete, copy-paste-ready templates (compressed summary, structured relay, briefing packet, project-state object) and exact routing sequences, giving fully actionable guidance for an instruction-only skill.	3 / 3
Workflow Clarity	Routing logic is a clearly sequenced checklist with explicit gating checkpoints ('after Quinn PASS', 'after Luna PASS or PASS WITH CONDITIONS') plus a blocker-handling feedback section, matching the clear-sequence-with-checkpoints anchor.	3 / 3
Progressive Disclosure	The skill is well-sectioned but monolithic: ~180 lines all inline with no one-level-deep references, and the detailed templates/agent table are content that could be split out; the under-50-line simple-skill exemption does not apply.	2 / 3
	Total	10 / 12 Passed

Description

35%

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 role but relies on jargon and omits any 'when to use' trigger guidance, weakening trigger-term quality and completeness. It reads as an internal label rather than a user-facing activation phrase.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrases (e.g., 'Use when coordinating multiple specialized agents on a software project, or when the user asks to orchestrate an agent squad').

Replace the vague verb 'coordinates' with concrete actions (e.g., 'routes requests to specialized agents, compresses their reports, and relays structured summaries').

Include common trigger variations users would actually say ('orchestrate agents', 'coordinate the squad', 'route to the right agent') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('orchestrator', 'specialized squad of agents') and the action 'coordinates', but that single verb is vague rather than a list of concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It states what the skill does but never states when to use it; per the judging guidelines a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	There are no natural terms a user would actually say ('orchestrator', 'squad of agents' are internal jargon), and no 'Use when...' clause is present, matching the 'no natural keywords; technical jargon' anchor.	1 / 3
Distinctiveness Conflict Risk	The orchestration niche is somewhat specific, but without distinct trigger phrases it could still overlap with other agent-orchestration or meta skills.	2 / 3
	Total	7 / 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: sickn33/antigravity-awesome-skills
Commit: 6e69f00

Reviewed: 5 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.