ctx-doctor

Run context-mode diagnostics. Checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. Trigger: /context-mode:ctx-doctor

Quality

83%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

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

This is an excellent, lean skill that clearly instructs Claude to call an MCP tool and display results, with a well-defined fallback path. It respects Claude's intelligence, provides executable commands, and is appropriately structured for its simplicity. The cross-client compatibility note about renderer-safe formatting is a valuable detail that earns its place.

Dimension	Reasoning	Score
Conciseness	Every token earns its place. No unnecessary explanation of what MCP tools are or how diagnostics work. The fallback path is concise but complete.	3 / 3
Actionability	Provides a concrete primary action (call `ctx_doctor` MCP tool), specific display instructions with exact prefixes, and an executable bash fallback with a real command. Copy-paste ready.	3 / 3
Workflow Clarity	Clear three-step sequence: call tool → display verbatim → fallback if needed. The fallback includes a concrete derivation path and command. For this simple single-purpose diagnostic skill, the workflow is unambiguous and complete.	3 / 3
Progressive Disclosure	For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized into a clear instruction list with no unnecessary nesting or monolithic blocks.	3 / 3
	Total	12 / 12 Passed

Description

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 is technically specific and clearly identifies what the skill does with concrete diagnostic checks. However, it lacks a natural-language 'Use when...' clause and relies on a slash command as the trigger mechanism rather than describing user scenarios. The technical specificity makes it distinctive but limits discoverability through natural language queries.

Suggestions

Add a 'Use when...' clause describing scenarios, e.g., 'Use when context-mode is malfunctioning, plugins fail to register, or the user needs to troubleshoot their context-mode setup.'

Include natural trigger terms users might say, such as 'troubleshoot', 'debug', 'health check', 'context-mode not working', or 'diagnose issues'.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. These are clearly defined diagnostic capabilities.	3 / 3
Completeness	The 'what' is well-covered (runs diagnostics checking specific components), but the 'when' is only expressed as a slash command trigger rather than an explicit 'Use when...' clause describing scenarios like 'when context-mode is not working' or 'when diagnosing plugin issues'.	2 / 3
Trigger Term Quality	Includes some relevant technical terms like 'diagnostics', 'runtimes', 'FTS5', 'plugin registration', but the trigger is a slash command '/context-mode:ctx-doctor' rather than natural language terms a user would say. Missing natural phrases like 'troubleshoot', 'debug', 'health check'.	2 / 3
Distinctiveness Conflict Risk	Very specific niche: context-mode diagnostics with a unique slash command trigger. Unlikely to conflict with other skills due to the highly specific domain (context-mode, FTS5, plugin registration) and explicit command trigger.	3 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 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

Repository: mksglu/context-mode
Commit: e174272

Reviewed: 1 day 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.