ccboard
Launch and navigate the ccboard TUI/Web dashboard for Claude Code. Use when monitoring token usage, tracking costs, browsing sessions, or checking MCP server status across projects.
56
63%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/skills/ccboard/SKILL.mdQuality
Discovery
100%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 skill description that clearly identifies the specific tool (ccboard), its purpose (dashboard for Claude Code), and explicit trigger conditions covering monitoring, cost tracking, session browsing, and MCP server status. It uses third person voice, is concise, and has strong distinctiveness with minimal conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Launch and navigate the ccboard TUI/Web dashboard', 'monitoring token usage', 'tracking costs', 'browsing sessions', 'checking MCP server status across projects'. | 3 / 3 |
Completeness | Clearly answers both what ('Launch and navigate the ccboard TUI/Web dashboard for Claude Code') and when ('Use when monitoring token usage, tracking costs, browsing sessions, or checking MCP server status across projects') with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'token usage', 'tracking costs', 'sessions', 'MCP server status', 'dashboard', 'ccboard', 'TUI/Web'. These cover the natural ways a user would refer to monitoring and cost tracking. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — references a specific tool ('ccboard'), a specific context ('Claude Code'), and specific use cases (token usage, costs, MCP server status) that are unlikely to overlap with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads like a comprehensive GitHub README rather than a focused skill file for Claude. It is extremely verbose, including sections on contributing, credits, license, architecture, and future roadmap that are irrelevant to Claude's task of launching and navigating the dashboard. The actionable content (commands, keyboard shortcuts, troubleshooting) is buried in excessive descriptive material.
Suggestions
Cut the file to ~80 lines focusing only on: installation command, launch commands, tab navigation keys, common action keys, and troubleshooting steps. Remove Contributing, Credits, License, Architecture, Performance, and Limitations sections entirely.
Move detailed per-tab feature descriptions into a separate TABS_REFERENCE.md file and link to it from a concise overview.
Add explicit validation steps to workflows—e.g., after MCP config editing: 'Press r to refresh status, verify server shows ● Running before proceeding.'
Remove explanatory prose that describes what ccboard is and instead focus on concrete commands and keyboard sequences Claude should use to accomplish specific monitoring tasks.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. Includes extensive information Claude doesn't need: architecture details, contributing guidelines, credits, license, performance benchmarks, future roadmap, and detailed descriptions of every UI tab. Much of this is README content, not actionable skill guidance. | 1 / 3 |
Actionability | Provides concrete commands (/dashboard, /costs, /mcp-status) and keyboard shortcuts, plus some usage examples with bash blocks. However, much content is descriptive rather than instructive (listing features rather than guiding actions), and the usage examples are mostly comments rather than executable workflows. | 2 / 3 |
Workflow Clarity | Usage examples show basic sequences (launch → navigate → check), and troubleshooting has clear steps. However, there are no validation checkpoints or feedback loops—e.g., after editing MCP config there's no verification step to confirm changes took effect. The workflows are more like feature tours than guided processes. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. Everything is inlined—architecture, contributing, credits, license, roadmap, detailed tab descriptions—all content that should either be omitted or split into separate reference files. No bundle files exist to support progressive disclosure. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Commit
60a4372
- 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.