create-agent

Create a new custom agent from scratch. Runs a 6-phase interview to understand purpose, capabilities, triggers, output format, and coordination rules, then generates the agent file. Triggers: EN: "create a new agent", "custom agent", "I need a new agent", "build an agent", "new crew member". IT: "crea un nuovo agente", "agente personalizzato", "nuovo membro del crew". FR: "créer un nouvel agent", "agent personnalisé". ES: "crear un nuevo agente", "agente personalizado". DE: "neuen Agenten erstellen". PT: "criar um novo agente".

Quality

90%

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

81%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 well-sequenced, highly actionable interview protocol with strong validation and resume feedback loops. Its chief weakness is verbosity from repeated reinforcement of the same NEVER-rules and a duplicated post-it protocol, plus a monolithic structure that could offload the question bank to a reference file.

Suggestions

Consolidate the post-it protocol: describe it once (in the 'Post-it Protocol' section) and have the step list and checklist reference it, instead of re-stating the resume/read/write instructions three times.

Merge the HARD CONSTRAINT rules, the RULES list, and the phase checklist into a single canonical rules block so each constraint appears exactly once.

Move the 11-question phase bank and the post-it template into a references/ file (e.g. interview-questions.md) and link to it, reducing the monolithic SKILL.md body and improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded: the post-it protocol is restated in step 3, the 'Post-it Protocol' section, and the checklist, and the NEVER-rules are repeated across the HARD CONSTRAINT, RULES, and checklist blocks — these could be consolidated without losing clarity.	3 / 5
Actionability	Highly actionable for an instruction skill: exact per-phase questions, concrete tool mappings (Read, Write, Edit, Glob, Grep), precise save paths, registry/directory insertion markers, and a copy-ready post-it template with named fields.	5 / 5
Workflow Clarity	Clear six-phase sequence with explicit validation checkpoints — phase checklist, mandatory Phase 6 confirmation before file generation, and a resume-from-recorded-phase feedback loop via the post-it — covering error recovery for a complex process.	5 / 5
Progressive Disclosure	Well-organized into clear phase sections with explicitly signalled references to vault files (agent-template.md, agents-registry.md, agents.md); the main gap is that the full inline question bank and post-it template could live in a reference file for a skill this long, and no bundle files are provided.	4 / 5
	Total	17 / 20 Passed

Description

100%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 is strong: third-person voice, a concrete multi-step 'what', and an explicit 'when' with natural, multilingual trigger phrases including synonyms. It is distinguishable and low-conflict.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions — 'Runs a 6-phase interview to understand purpose, capabilities, triggers, output format, and coordination rules, then generates the agent file' — giving comprehensive coverage of the workflow rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both 'what' (create a custom agent via a 6-phase interview that generates the file) and 'when' via a labelled 'Triggers:' clause with concrete trigger phrases, so the missing-trigger cap does not apply.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases a user would actually say ('create a new agent', 'I need a new agent', 'build an agent', 'new crew member') with synonyms, across six languages.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (custom-agent creation) with distinct triggers, so it is unlikely to fire for unrelated skills; minimal conflict risk.	5 / 5
	Total	20 / 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: gnekt/My-Brain-Is-Full-Crew
Path: tests/regression/snapshot/.claude/skills/create-agent/SKILL.md
Commit: 238ae8c

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.