CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

connect-chatcut-desktop

Install, open, connect, or repair ChatCut Desktop when the chatcut_desktop MCP tools are missing or unavailable. Do not use from a managed agent already running inside ChatCut Desktop, or when chatcut_desktop tools are already available.

68

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 concise, well-structured, and actionable with concrete URLs and platform-specific steps, and includes sensible validation and safety boundaries. It is a strong, self-contained instruction skill with only minor actionability gaps.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, giving only domain-specific facts (exact URLs, supported OSes, install steps) with no padding or explanation of concepts Claude already knows.

5 / 5

Actionability

It gives concrete, executable guidance (specific download URLs per platform, mount/copy to /Applications, inspect codesign/quarantine) but stops short of literal copy-paste commands for some steps, leaving minor gaps.

4 / 5

Workflow Clarity

A clear numbered install/repair sequence with validation-flavored checkpoints ('inspect it before replacing it', 'only after the signature validates', 'Retry one fresh download... Do not loop') is present; it is not a destructive/batch operation needing the strict cap, though an explicit verify-after-open step would make it 5.

4 / 5

Progressive Disclosure

At ~55 lines with no bundle files and no external references, the content is appropriately self-contained and organized into well-signaled sections (Download, Install or repair, User handoff) — matching the simple-skill exception where progressive disclosure scores 5 with just well-organized sections.

5 / 5

Total

18

/

20

Passed

Description

78%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, well-scoped, and clearly distinguishes itself with explicit trigger and anti-trigger conditions. It fully answers both what and when, with only minor room for more natural-synonym coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Install, open, connect, or repair') for a named target (ChatCut Desktop / chatcut_desktop MCP tools), with only minor coverage gaps such as omitting uninstall or update.

4 / 5

Completeness

It states a clear 'what' (install/open/connect/repair ChatCut Desktop) and a 'when' ('when the chatcut_desktop MCP tools are missing or unavailable'), plus an explicit anti-trigger; the 'when' could be more expansive but is clearly present.

4 / 5

Trigger Term Quality

Natural phrases like 'Install, open, connect, or repair', 'MCP tools are missing or unavailable', and 'managed agent' are well chosen, but it lacks common synonyms a user might say (e.g. 'desktop app won't start', 'ChatCut not working').

4 / 5

Distinctiveness Conflict Risk

The niche is sharply defined (ChatCut Desktop / chatcut_desktop MCP tool availability) with explicit negative triggers ('Do not use from a managed agent...', 'when tools are already available'), making misfiring on unrelated skills very unlikely.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

openai/plugins

Path

plugins/chatcut/skills/connect-chatcut-desktop/SKILL.md

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.