model-usage
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
91
Quality
88%
Does it follow best practices?
Impact
100%
3.70xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted description with explicit trigger guidance and good keyword coverage for the CodexBar CLI domain. The main weakness is that the specific capabilities could be more concrete (e.g., what commands are run, what output formats are supported). Overall, it effectively communicates when Claude should select this skill.
Suggestions
Add more concrete actions like specific CLI commands or output formats (e.g., 'runs codexbar cost --json', 'outputs CSV summaries')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (CodexBar CLI cost usage) and describes actions (summarize per-model usage, model breakdown), but lacks comprehensive concrete actions like specific commands or output formats. | 2 / 3 |
Completeness | Clearly answers both what (summarize per-model usage for Codex/Claude with current model or full breakdown) and when (explicit 'Trigger when' clause specifying model-level usage/cost data requests or scriptable summary needs). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms: 'model-level usage', 'cost data', 'codexbar', 'per-model summary', 'cost JSON', 'Codex', 'Claude'. Users asking about usage costs would likely use these terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to CodexBar CLI tool with distinct triggers around 'codexbar', 'per-model', and 'cost JSON'. Unlikely to conflict with general cost or usage skills due to the specific tool name. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that provides actionable CLI commands with clear examples. The content is appropriately structured with good progressive disclosure. The main weakness is the lack of validation steps or error handling guidance for when the CLI or script fails.
Suggestions
Add a brief validation step or expected output example so users can verify the script ran correctly
Include basic error handling guidance (e.g., what to check if the CLI returns empty JSON or the script fails)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient, assuming Claude knows what JSON, CLI tools, and Python scripts are. No unnecessary explanations of basic concepts; every section serves a clear purpose. | 3 / 3 |
Actionability | Provides fully executable bash commands with concrete flags and options. Examples are copy-paste ready with clear parameter variations (--mode current/all, --format json --pretty). | 3 / 3 |
Workflow Clarity | Steps are listed but lack explicit validation checkpoints. The workflow (fetch JSON → run script) is clear, but there's no guidance on verifying output correctness or handling errors if the CLI fails. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections (Quick start, Current model logic, Inputs, Output). References external documentation appropriately with a single-level reference to codexbar-cli.md. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- trpc-group/trpc-agent-go
- Commit
8763418
- 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.