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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is thorough and accurate but far too verbose for a SKILL.md, dwelling on UI feature inventories and details Claude already infers. It is moderately actionable via concrete commands yet lacks validation checkpoints and overloads the overview file instead of progressively disclosing detail to reference files.

Suggestions

Trim the body to a lean overview: collapse the per-tab feature inventories, performance specs, credits, and architecture sections into a short summary or move them into separate reference files (e.g. ARCHITECTURE.md, TROUBLESHOOTING.md).

Add explicit validation/verification steps to the installation and usage workflows — e.g. run scripts/check-install.sh to confirm the binary is on PATH before proceeding.

Link the existing bundle scripts from the body (e.g. 'Install: bash scripts/install-ccboard.sh; verify: bash scripts/check-install.sh') so the progressive-disclosure structure is signaled and the scripts are discoverable.

Dimension	Reasoning	Score
Conciseness	The body is ~390 lines and heavily padded with content Claude does not need to be told — exhaustive tab inventories, full keybinding tables, performance specs, credits, and marketing-style feature lists that explain what the tool is rather than how to invoke it.	1 / 3
Actionability	It provides concrete slash commands and `ccboard` CLI invocations that are copy-paste ready, but the bulk of the body describes UI features ('8 Interactive Tabs', 'Dual-pane') rather than giving executable guidance for accomplishing tasks.	2 / 3
Workflow Clarity	Usage examples loosely sequence steps but there are no explicit validation checkpoints; installation has no verify step beyond the separate check-install.sh script, and troubleshooting steps are listed without feedback loops.	2 / 3
Progressive Disclosure	Structure uses clear sections, but the SKILL.md is monolithic — nearly everything (architecture, performance, credits, full troubleshooting) is inline rather than split into one-level-deep reference files; the only bundle files are two install scripts that the body does not explicitly link to.	2 / 3
	Total	7 / 12 Passed

Description

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.

The description is specific, uses natural trigger terms, and clearly answers both what the skill does and when to use it. It is concise without fluff and well-differentiated from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions including 'monitoring token usage, tracking costs, browsing sessions, or checking MCP server status across projects', each tied to a specific dashboard capability.	3 / 3
Completeness	Explicitly states both what it does ('Launch and navigate the ccboard TUI/Web dashboard') and when to use it ('Use when monitoring token usage, tracking costs...'), satisfying the 'what' and 'when' requirement.	3 / 3
Trigger Term Quality	Uses natural phrases a user would say — 'token usage', 'tracking costs', 'browsing sessions', 'MCP server status' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The ccboard dashboard niche is distinct and the triggers are specific enough that it is unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
Commit: eb4fbbd

Reviewed: 2 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.