CtrlK
BlogDocsLog inGet started
Tessl Logo

engineer-plugin-mcp

Build AI-IDE plugin MCP elements - stdio JSON-RPC servers, tool schemas, host wiring for Claude Code/Codex, event-name mapping and validation. Use when building or adding an MCP server to a plugin. Not for plugin manifests or packaging.

65

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/flowai-engineering/skills/engineer-plugin-mcp/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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, concise orientation skill with a clear validated workflow. Its main weakness is actionability: it describes the process but provides no executable code, schema fragments, or concrete commands, relying entirely on external docs.

Suggestions

Add a minimal executable example (e.g. a stdio JSON-RPC server skeleton in Python/TypeScript or a sample tool input-schema JSON) so Claude has a copy-paste starting point.

Add an explicit fix-and-retry loop to the Validate step ("If the handshake or tool call fails, fix the input/schema and re-probe") to lift workflow_clarity to 5.

Collapse the overlapping guidance between Server Rules and the Workflow/Validation Notes sections to remove redundancy.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's MCP knowledge; the only redundancy is overlap between the Workflow, Server Rules, and Validation Notes sections, which could be tightened.

4 / 5

Actionability

Concrete process guidance exists (classify, define contract, choose transport, generate wiring) but it delegates all specifics to external docs with no executable code, commands, or schema examples — incomplete for direct execution.

3 / 5

Workflow Clarity

A clear six-step sequence with an explicit validation probe step ("Confirm the protocol handshake and tool call"), missing only a fix-and-retry feedback loop to reach 5.

4 / 5

Progressive Disclosure

Well-organized into signaled sections pointing one level out to official doc URLs; no bundle files exist, and the single-file structure is appropriate for an orientation skill, with only minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

87%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 well-crafted description: concrete capabilities, explicit use-when trigger, and a disambiguating negative boundary. Minor room for more synonyms/file-extension trigger terms.

Suggestions

Add natural synonyms or file extensions to the trigger clause (e.g. ".mcp.json", "MCP config", "tool server") to broaden trigger-term coverage.

Consider naming the host set less as a fixed list ("Claude Code/Codex") and more as open-ended to avoid implying exclusivity.

DimensionReasoningScore

Specificity

Lists several concrete actions ("stdio JSON-RPC servers, tool schemas, host wiring... event-name mapping and validation") with minor framing gaps; not quite the comprehensive coverage of a 5.

4 / 5

Completeness

Explicitly answers both what ("Build AI-IDE plugin MCP elements...") and when ("Use when building or adding an MCP server to a plugin") with concrete trigger phrases and a negative boundary.

5 / 5

Trigger Term Quality

"Use when building or adding an MCP server to a plugin" supplies good natural keywords (MCP server, plugin) but misses common synonyms and file extensions that would push it to 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche (plugin MCP servers) plus the negative boundary "Not for plugin manifests or packaging" sharply separates it from sibling skills, giving minimal conflict risk.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
korchasa/flowai-plugins
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.