CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-tools-setup

Set up, connect, validate, and repair Claude Desktop and MCP servers using Desktop Commander — inspecting and fixing mcp.json / claude_desktop_config.json, getting MCP servers to connect, and diagnosing local AI tooling. Use when a user wants to install, configure, connect, validate, or fix Claude Desktop, an MCP server, an MCP config file, or a local AI agent/gateway. Trigger on the symptoms that actually bring people in: "Claude can't see my tools", "my MCP server isn't showing up", "tools aren't loading in Claude", "add an MCP server", "my MCP isn't connecting", "fix my Claude Desktop config", "the agent won't respond", "wire up Ollama / LM Studio", "restart Claude Desktop". Also covers local agent gateways like OpenClaw and Hermes.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A well-structured, validation-heavy troubleshooting skill with clear workflow sequencing and clean one-level reference routing. Weakest on conciseness (rationale clauses) and on body-level actionability, since the copy-paste specifics live in the reference files.

Suggestions

Trim inferable rationale from the golden rules — e.g. drop 'file paths, commands, and config locations differ across macOS, Windows, and Linux, so confirm the platform before assuming anything' to just 'Detect the OS and shell first via get_config.systemInfo'.

Add one short inline example of a concrete config edit (e.g. a minimal claude_desktop_config.json mcpServers block) so the body is executable without always opening a reference.

Make the error-recovery feedback loop explicit in the general workflow (e.g. 'if verification fails, re-read logs for the first real error and retry from step 3') rather than leaving it implied.

DimensionReasoningScore

Conciseness

Mostly lean and actionable, but several golden rules carry rationale clauses Claude could infer (e.g. 'file paths, commands, and config locations differ across macOS, Windows, and Linux, so confirm the platform') that could be trimmed.

4 / 5

Actionability

Names concrete tools and commands inline — start_process, edit_block, list_processes, cp/lsof/netstat, curl — but defers the exact paths and full command sequences to the reference files, leaving minor gaps in the body itself.

4 / 5

Workflow Clarity

Clear 6-step general workflow with an explicit verify step, a 5-step ordered diagnostic checklist, and pervasive validation checkpoints ('Validate the JSON after every edit', 'Verify, then stop') appropriate to risky config edits.

5 / 5

Progressive Disclosure

Clean overview that routes to three real, one-level-deep reference files (claude-desktop-mcp.md, openclaw.md, hermes.md), each clearly signaled with '→ Read references/...'; no nesting.

5 / 5

Total

18

/

20

Passed

Description

96%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.

A strong, concrete description with explicit what/when structure and an unusually rich set of natural trigger phrases. Its only weakness is breadth: casting over several distinct tools slightly raises overlap risk versus a tighter scope.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Set up, connect, validate, and repair', 'inspecting and fixing mcp.json / claude_desktop_config.json', 'getting MCP servers to connect', 'diagnosing' — covering install/configure/validate/repair comprehensively.

5 / 5

Completeness

Explicitly answers both what ('Set up, connect, validate, and repair Claude Desktop and MCP servers...') and when ('Use when a user wants to install, configure, connect, validate, or fix...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Packs in natural phrases users actually say — 'Claude can't see my tools', 'my MCP server isn't showing up', 'add an MCP server', 'fix my Claude Desktop config', 'wire up Ollama / LM Studio' — with synonyms and product names.

5 / 5

Distinctiveness Conflict Risk

Distinct MCP/Claude-Desktop niche with highly specific triggers, but the broad net over OpenClaw, Hermes, Ollama, and LM Studio creates minor overlap risk with hypothetical dedicated per-tool skills.

4 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
wonderwhy-er/DesktopCommanderMCP
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.