role-creator
Create and install Codex custom agent roles in ~/.codex/config.toml, generate role config files, enforce supported keys, and guide users through required role inputs (model, reasoning effort, developer_instructions).
81
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
67%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 excels at specificity and distinctiveness, clearly defining what the skill does with concrete actions and a unique domain (Codex agent roles). However, it lacks an explicit 'Use when...' clause and could benefit from more natural trigger terms that users would actually say when needing this functionality.
Suggestions
Add a 'Use when...' clause with trigger phrases like 'Use when the user wants to create a custom Codex role, configure agent personas, or modify ~/.codex/config.toml'
Include more natural user-facing trigger terms such as 'custom persona', 'new agent', 'configure Codex', or 'agent configuration'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create and install Codex custom agent roles', 'generate role config files', 'enforce supported keys', and 'guide users through required role inputs' with specific parameters named (model, reasoning effort, developer_instructions). | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance to tell Claude when to select this skill. | 2 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'Codex', 'agent roles', 'config.toml', and 'role config files', but missing common variations users might say like 'custom persona', 'agent setup', 'configure Codex', or 'add new role'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Codex custom agent roles with distinct file path (~/.codex/config.toml) and specific parameters; unlikely to conflict with other skills due to the unique domain. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill with excellent actionability and workflow clarity. The explicit input collection gate, validation steps, and concrete command examples make it highly executable. Minor verbosity in repeating the 'minimal by default' policy across multiple sections could be consolidated for better token efficiency.
Suggestions
Consolidate the repeated 'do not set optional keys unless explicitly requested' guidance into a single, prominent policy statement rather than restating it in multiple sections (Overview, Default Policy, Knowledge vs Application Rule).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (e.g., repeating the 'do not set optional keys unless requested' concept multiple times across sections). The structured format helps, but could be tightened by consolidating similar guidance. | 2 / 3 |
Actionability | Provides fully executable bash commands with complete flag examples, concrete JSON spawn examples, and specific file paths. The commands are copy-paste ready with clear parameter explanations. | 3 / 3 |
Workflow Clarity | Clear 6-step workflow with explicit gates (Step 1 hard gate before writing), validation checkpoints (Step 5), backup safety measures, and error recovery guidance in Guardrails section. The 'Execution gate' explicitly prevents proceeding without required inputs. | 3 / 3 |
Progressive Disclosure | Well-organized with clear section headers, references to external templates (templates/*.toml) and reference docs (references/role-config-reference.md) for advanced details. Main content stays focused on workflow while pointing to deeper resources. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
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.