role-creator

Create and update Codex custom agents using standalone custom-agent TOML files.

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 actionable and workflow-driven with executable commands, validation checkpoints, and error-recovery guidance, but it is slightly verbose in its command examples and fails to signal the actual bundled reference file.

Suggestions

Replace the nonexistent `templates/` reference with a clear link to the real `references/role-config-reference.md` and signal it where the role-file contract is discussed.

De-duplicate the Commands section: show the core command once and list optional flags (--nickname-candidates, --sandbox-mode, --web-search) separately rather than repeating the full command.

Move the detailed role-file contract / optional-keys enumeration into the existing reference file to keep SKILL.md a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean bullets with no concept preamble, but the Commands section repeats the full first command block with all flags in the second example, and some contract details restate earlier content; it could be tightened to earn level 3.	2 / 3
Actionability	Concrete executable commands with real flags and absolute script paths, explicit required-keys lists, and a copy-paste ready JSON call example give fully executable, copy-paste-ready guidance.	3 / 3
Workflow Clarity	A numbered 5-step workflow includes an explicit "Validate TOML parse and required keys" checkpoint plus error-recovery guardrails (unknown agent_type -> verify scope/path; tomlq syntax check), satisfying clear sequence with validation and feedback loops.	3 / 3
Progressive Disclosure	Sections are well organized, but the body never links to the existing references/role-config-reference.md and the References section points to a nonexistent templates/ dir instead of the actual bundle file; references are present but not clearly signaled against the real bundle structure.	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 clearly states what the skill does using concrete action verbs and a specific domain, but it omits any explicit "when to use it" trigger guidance, which limits completeness and distinctiveness.

Suggestions

Add a "Use when..." clause naming natural triggers (e.g., "Use when creating, updating, or troubleshooting a Codex custom agent or its TOML file").

Expand trigger-term coverage with common variations a user might say ("custom Codex agent", "agent TOML", "role file").

List a couple more concrete actions (e.g., validate keys, fix unknown agent_type errors) to push specificity toward level 3.

Dimension	Reasoning	Score
Specificity	Quotes "Create and update Codex custom agents using standalone custom-agent TOML files" name two concrete actions on a specific domain, but do not list multiple distinct concrete actions as the level-3 anchor requires; level 1 is too vague for the named actions.	2 / 3
Completeness	The what is clear (create/update Codex custom agents via TOML files) but there is no "Use when..." clause or equivalent trigger guidance, which the rubric caps at 2.	2 / 3
Trigger Term Quality	Natural terms like "Codex custom agents" and "custom-agent TOML files" are present, but coverage lacks common variations a user might say; not the broad variant coverage of level 3.	2 / 3
Distinctiveness Conflict Risk	The Codex-custom-agent / TOML niche is somewhat specific, but it could still overlap with general Codex config or agent-management skills and lacks explicit distinct triggers.	2 / 3
	Total	8 / 12 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: am-will/codex-skills
Commit: e343715

Reviewed: 14 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.