CtrlK
BlogDocsLog inGet started
Tessl Logo

desktop-commander-overview

Use for Desktop Commander MCP capabilities — persistent shells and REPLs, long-running processes, filesystem beyond the workspace, structured files (.xlsx, .docx, .pdf, images) and large local data files such as CSVs, ripgrep search at scale, SSH, or cross-turn state.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

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.

The body is a well-structured, action-oriented overview that delegates detailed parameter shapes to the MCP and provides sequenced workflows with explicit validation and feedback loops. Its main weakness is the use of intentionally-justified pseudocode and minor cross-example redundancy.

Suggestions

Tighten repeated caveats (e.g. the persistent-shell 'separate start_process calls do not share state' note and the `write_pdf` parameter deferral) so each is stated once and referenced when needed, trimming tokens without losing clarity.

For at least one representative workflow, show the real object-shaped argument the MCP expects (in addition to the pseudocode shorthand) so the example doubles as a copy-paste-ready template, nudging actionability toward 5.

Move the per-tool parameter/return-shape hints that currently appear inline in workflows into a short cross-referenced 'tool inventory' note, keeping the workflow prose focused on sequencing.

DimensionReasoningScore

Conciseness

Largely efficient and assumes Claude's competence (no explanations of what PDF/CSV/SSH are), with minor redundancy such as the repeated `write_pdf` notes and the persistent-shell caveat restated across several workflows. It is above the midpoint but not every token earns its place.

4 / 5

Actionability

Concrete tool sequences with real tool names and argument shapes (e.g. `start_process("ssh user@prod.example.com", timeout_ms=...)`, `edit_block(file_path, old_string, new_string)`) cover common cases, but they are explicitly pseudocode shorthand with the real object-shaped args deferred to MCP tool descriptions — executable guidance with minor gaps rather than copy-paste-ready code.

4 / 5

Workflow Clarity

Workflows are clearly sequenced tool-by-tool with explicit validation/confirmation checkpoints for risky ops (confirmation before SSH/deploy) and a genuine feedback loop for the monorepo refactor: re-run `start_search` and page `get_more_search_results` 'until the run completes — only then can you confirm zero remaining hits'.

5 / 5

Progressive Disclosure

Clean sectioned overview ('What this MCP gives', 'Example workflows', 'Core tool inventory', 'Conventions') with the bulk detail clearly signaled one level deep to 'the MCP's own tool descriptions' and 'the `write_pdf` tool description'; no bundle files exist to require further splitting.

5 / 5

Total

18

/

20

Passed

Description

100%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, complete, and distinctive: it explicitly names what Desktop Commander enables and provides a 'Use for ...' trigger clause covering natural terms and file extensions. No vague fluff or over-claims are present.

DimensionReasoningScore

Specificity

Names the Desktop Commander MCP domain and lists multiple concrete capabilities — 'persistent shells and REPLs, long-running processes, filesystem beyond the workspace, structured files (.xlsx, .docx, .pdf, images) and large local data files such as CSVs, ripgrep search at scale, SSH, or cross-turn state' — giving comprehensive coverage of specific actions.

5 / 5

Completeness

Explicit 'what' (enumerated capabilities) and an explicit trigger clause 'Use for Desktop Commander MCP capabilities — ...' answering 'when'; both are concrete rather than vague.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural user terms plus file extensions and synonyms: 'shells and REPLs', 'CSVs', 'SSH', 'search at scale', '.xlsx', '.docx', '.pdf', 'images', 'large local data files' — the phrases a user would naturally say when needing this skill.

5 / 5

Distinctiveness Conflict Risk

Distinctive triggers tied to one specific MCP (persistent shells/REPLs, SSH, ripgrep at scale, cross-turn state) carve a clear niche with minimal overlap risk against other skills.

5 / 5

Total

20

/

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.