CtrlK
BlogDocsLog inGet started
Tessl Logo

mcp-manager

Manage MCP (Model Context Protocol) servers for openclacky: add, list, probe, remove, reconfigure. Edits ~/.clacky/mcp.json so the user never writes JSON by hand. Trigger on: add mcp, install mcp, setup mcp, configure mcp, mcp list, mcp remove, mcp probe, mcp reconfigure.

76

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 thorough, actionable skill with executable commands, strong validation checkpoints, and a well-structured add flow. Slightly held back by duplicated request bodies and a monolithic layout that could offload the server catalog to a reference file.

Suggestions

Deduplicate the create/update request-body examples: keep one copy in the API cheat sheet and reference it from Step 5 instead of repeating the full stdio and http JSON blocks.

Move the Known-Good Server Catalog into references/catalog.md and link to it from the body, reducing the inline footprint while keeping the overview scannable.

DimensionReasoningScore

Conciseness

Mostly lean and efficient, assuming Claude's competence (no padding about what MCP or curl is), but the stdio/http request bodies are duplicated across the API cheat sheet and Step 5, a minor redundancy that could be trimmed.

4 / 5

Actionability

Fully executable curl commands with complete JSON bodies, specific package names, args, and env vars for both stdio and http cases — copy-paste ready and covering the common cases.

5 / 5

Workflow Clarity

The 7-step add flow is clearly sequenced with explicit validation checkpoints (runtime preflight, user confirm, post-save probe) and an error-recovery feedback loop on probe failure, matching the score-5 anchor.

5 / 5

Progressive Disclosure

Well-organized with clear single-level section headers and no nested references, but the 325-line monolith (notably the ~90-line Known-Good Server Catalog) could be split into a one-level-deep reference file rather than fully inlined.

4 / 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.

A strong, third-person description that names concrete actions, gives explicit trigger phrases with synonyms, and clearly answers both what and when. No first/second-person voice to penalize.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'add, list, probe, remove, reconfigure' — covering the skill's full scope comprehensively, matching the score-5 anchor.

5 / 5

Completeness

Clearly answers both 'what' ('Manage MCP servers ... add, list, probe, remove, reconfigure. Edits ~/.clacky/mcp.json') and 'when' (explicit 'Trigger on:' clause), matching the score-5 anchor.

5 / 5

Trigger Term Quality

Explicit 'Trigger on: add mcp, install mcp, setup mcp, configure mcp, mcp list, mcp remove, mcp probe, mcp reconfigure' provides comprehensive natural phrases including synonyms users would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear niche (MCP servers for openclacky) with distinct, MCP-specific triggers; minimal overlap risk with other skills.

5 / 5

Total

20

/

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
clacky-ai/openclacky
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.