aiox-squad-creator

Activate the AIOX Squad Creator agent (Craft). Use to create, validate, publish and manage squads Trigger when user asks to squad-creator, or says 'activate squad-creator', 'switch to squad-creator', '@squad-creator'.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.kimi/skills/aiox-squad-creator/SKILL.md

Quality

Content

51%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 skill is highly actionable with concrete command examples and well-sequenced validated workflows, but it is verbose and structurally weak: a large duplicated YAML agent definition is inlined rather than split into a reference file, and no bundle files back the cited tasks/scripts/schemas.

Suggestions

Move the 'COMPLETE AGENT DEFINITION' YAML block into a separate bundle file (e.g. references/agent-definition.yaml) and reference it one level deep, eliminating the duplication with the Identity/Star Commands sections already present.

Remove the redundant second copy of the commands list — keep a single canonical command table to cut roughly half the tokens.

Either create the referenced bundle files (tasks/*.md, scripts/squad/*.js, squad-schema.json) under references/scripts/assets so the cited paths resolve, or drop the dependencies listing if they are not bundled.

Dimension	Reasoning	Score
Conciseness	The body is heavily padded with duplicated activation machinery — the Star Commands table and the commands list appear twice, and a ~200-line YAML 'Full Agent Definition' reiterates persona/core_principles/commands already stated above, adding substantial tokens Claude does not need.	2 / 5
Actionability	Provides concrete, copy-pasteable command invocations with arguments and flags (e.g. 'design-squad --docs ./docs/prd/my-project.md', 'extend-squad {name} --add task --name my-task --agent lead-agent') plus an explicit squad directory structure, giving mostly executable guidance.	4 / 5
Workflow Clarity	Three sequenced workflow options (guided design, direct creation, continuous improvement) each include a validate step and clear ordering; validation feedback loops are reinforced by the '*validate-squad' command and 'Common Pitfalls', with only minor checkpoint gaps before distribution.	4 / 5
Progressive Disclosure	Content that clearly belongs in a separate file — the entire COMPLETE AGENT DEFINITION YAML block — is inlined verbatim, and there are no bundle files present despite references to external tasks/scripts/schemas, leaving structure monolithic and references buried/unresolved.	2 / 5
	Total	12 / 20 Passed

Description

75%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 successfully pairs concrete capabilities with explicit activation triggers in third person, covering both 'what' and 'when'. Its main weaknesses are run-on phrasing and a narrow trigger vocabulary that lacks synonyms.

Suggestions

Split the run-on sentence so the 'Use when...' clause is its own clear sentence, e.g. 'Use to create, validate, publish and manage squads. Use when the user asks to squad-creator, or says "activate squad-creator", "switch to squad-creator", or "@squad-creator".'

Add natural trigger synonyms and the file/manifest terms users might mention (e.g. 'squad manifest', 'squad.yaml', 'design a squad', 'analyze a squad').

Add a period or clearer delimiter before 'Trigger when' to improve readability and parsing.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('create, validate, publish and manage squads') giving clear domain coverage, though the actions remain slightly high-level without more granular specifics.	4 / 5
Completeness	Explicitly answers both 'what' (create/validate/publish/manage squads) and 'when' (explicit trigger clauses), but the run-on sentence merges them and the 'when' could be more crisply separated.	4 / 5
Trigger Term Quality	Includes natural user phrasings ('activate squad-creator', 'switch to squad-creator', '@squad-creator') that users would actually say, but misses common synonyms and file extensions beyond the core trigger phrases.	4 / 5
Distinctiveness Conflict Risk	Tied to a distinct 'squad-creator' niche with specific activation triggers, leaving only minor overlap risk with other AIOX agents that share similar command vocabulary.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: SynkraAI/aiox-core
Path: .kimi/skills/aiox-squad-creator/SKILL.md
Commit: 4ef6530

Reviewed: 2 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.