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 adding an MCP server to a plugin.

69

Quality

83%

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

75%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, competent body that stays lean and defers volatile protocol/host details to official docs. It loses points mainly to Workflow/Server-Rules redundancy, an implicit validation feedback loop, and the deliberate absence of executable examples.

Suggestions

De-duplicate the Workflow and Server Rules sections: fold the overlapping 'Keep host wiring outside the server implementation' and 'Keep protocol strict and deterministic' rules into one place to tighten conciseness.

Make the validation feedback loop explicit in step 6: add 'if the probe fails, fix the server/wiring and re-run; only proceed when the handshake and tool call succeed' to lift workflow_clarity.

Add one minimal concrete probe example (e.g. a sample JSON-RPC initialize/call exchange or a one-line SDK invocation) so the actionability guidance has a copy-paste-ready anchor, even while deferring full protocol details to the docs.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence (no explaining what MCP or JSON-RPC is), but the Workflow and Server Rules sections overlap — e.g. 'Keep host wiring outside the server implementation' appears in both step 5 and Server Rules — so minor trimming is possible.

4 / 5

Actionability

Specific, actionable guidance ('Validate required paths and credentials at startup', 'Capture server logs for evidence') with a concrete Output Shape; appropriate for an instruction-only skill that defers code to official docs, though no executable probe example is provided.

4 / 5

Workflow Clarity

A clear 6-step sequence with a validation probe at step 6, but the validate->fix->retry feedback loop is only implicit ('Confirm the protocol handshake...') rather than spelled out, leaving a minor validation gap.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections that function as an overview, with well-signaled one-level-deep references to official docs via URLs; no bundle files exist to split further, so it is a single well-structured file with minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

92%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, specific description that clearly states both capability and a concrete use-trigger for a well-bounded niche. The only soft spot is trigger-term breadth, which is partly inherent to the specialized vocabulary.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'stdio JSON-RPC servers, tool schemas, host wiring for Claude Code/Codex, event-name mapping, and validation' — giving comprehensive coverage of the plugin-MCP niche, matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers both what ('Build AI-IDE plugin MCP elements - ...') and when ('Use when adding an MCP server to a plugin') with a concrete trigger phrase, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Natural trigger terms 'MCP server' and 'plugin' appear in 'Use when adding an MCP server to a plugin', but the niche has few synonyms and variations like 'model context protocol' or 'tool server' are absent, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche — MCP servers inside AI-IDE plugins — with distinct triggers, giving minimal overlap risk with other skills.

5 / 5

Total

19

/

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.