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.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./examples/skills/ccboard/SKILL.md

Quality

Content

38%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 well-organized as documentation but functions as a verbose product README rather than a lean skill, padding the context with UI catalogues and placeholders Claude already doesn't need. It is partially actionable via commands and keys but lacks validation checkpoints and fails to surface the bundled install scripts.

Suggestions

Trim the body to a concise overview plus launch/usage commands; move the per-tab feature catalogue, performance specs, credits, and architecture into a separate reference file or omit them.

Reference the bundled scripts explicitly (e.g. 'Install: bash scripts/install-ccboard.sh; check status: bash scripts/check-install.sh') so progressive disclosure is one level deep and actionable.

Add a validation checkpoint to the installation workflow (e.g. run scripts/check-install.sh after install and confirm the version before proceeding).

Dimension	Reasoning	Score
Conciseness	The body is a ~250-line marketing-style README that extensively enumerates UI tabs, credits, performance stats, and architecture that Claude does not need; substantial padding such as emoji-decorated sections and 'Repository: https://github.com/{OWNER}/ccboard' placeholders.	2 / 5
Actionability	Provides concrete commands and keybindings (e.g. '/dashboard', 'ccboard web --port 8080', press '6'), but the 'usage examples' are largely comments describing intent rather than copy-paste ready instruction sequences.	3 / 5
Workflow Clarity	Installation and launch steps are sequenced, but there are no validation checkpoints and the body never references the bundled install/check scripts despite their existence, leaving the actual setup workflow implicit.	3 / 5
Progressive Disclosure	Content is a monolithic inlined README with no references to the bundled scripts/ files; the install and check scripts exist but are not linked or signaled from the body, so structure that should be split is buried.	2 / 5
	Total	10 / 20 Passed

Description

83%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 specific, action-oriented, and includes an explicit 'Use when' trigger clause covering several natural user phrases. It is concise and clear, with only minor gaps in keyword synonyms and slight overlap risk with adjacent analytics skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Launch and navigate', 'monitoring token usage', 'tracking costs', 'browsing sessions', 'checking MCP server status') tied to a named tool, with minor gaps in coverage of the full feature set.	4 / 5
Completeness	Explicitly answers 'what' ('Launch and navigate the ccboard TUI/Web dashboard') and 'when' ('Use when monitoring token usage, tracking costs, browsing sessions, or checking MCP server status') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'token usage', 'tracking costs', 'browsing sessions', and 'MCP server status', though it omits synonyms such as 'spending', 'history', or 'cache hit rate'.	4 / 5
Distinctiveness Conflict Risk	The ccboard dashboard niche is fairly distinct, but the monitoring/cost-tracking framing has minor overlap with general analytics or billing skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: FlorianBruniaux/claude-code-ultimate-guide
Path: examples/skills/ccboard/SKILL.md
Commit: 752edfe

Reviewed: about 10 hours 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.