CtrlK
BlogDocsLog inGet started
Tessl Logo

mcp-server-management

Use when admin asks to configure an MCP tool server (e.g., GitHub, weather API), rotate credentials, grant/revoke worker access to MCP tools, or add a custom API integration via YAML.

70

Quality

86%

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

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An efficient, well-organized router skill: the SKILL.md carries the high-value gotchas and routes each situation to the right reference, with strong validation emphasis. Its weakness is that executable command sequences live entirely in the bundle files rather than being shown inline, lowering actionability and workflow_clarity.

Suggestions

Add a short inline Quick Start block with 2-3 copy-paste-ready example commands (e.g., the setup-mcp-server.sh invocation for a GitHub server) to lift actionability toward the executable-code bar.

Include a brief numbered create/update workflow inline (create -> wait ~10s -> verify with mcporter -> notify) with the validation checkpoints already documented, so the sequence is visible without opening a reference.

Optionally inline the single most common credential-rotation command so destructive operations have an explicit, sequenced example in the body.

DimensionReasoningScore

Conciseness

The body is lean and every line carries non-obvious operational knowledge (cloud-mode caveat, ~10s auth delay, SSE-200 quirk, accessToken convention, REPLACE semantics); it does not restate what MCP is, matching the lean-and-efficient anchor rather than the mostly-efficient anchor 2.

3 / 3

Actionability

Routing is concrete (named scripts setup-mcp-server.sh/setup-mcp-proxy.sh, env var AGENTTEAMS_RUNTIME=aliyun, endpoint POST /mcp/<name>/message, accessToken key) but the actual executable commands are deferred to bundle files rather than given as inline copy-paste-ready examples, falling short of the anchor-3 'fully executable' bar while exceeding anchor 1's vagueness.

2 / 3

Workflow Clarity

Validation checkpoints are explicit ('always wait and verify with mcporter before notifying Workers', 'verify end-to-end... Do not push broken tools') for risky credential/access operations, but the multi-step sequence itself is not laid out inline — it lives in the reference docs — so it does not reach the anchor-3 clear-sequence-with-checkpoints bar.

2 / 3

Progressive Disclosure

A concise overview plus a situation→file routing table points to one-level-deep, real reference files (all verified to exist), with always-needed gotchas inline and procedures split out, matching the clear-overview well-signaled-references anchor rather than the less-organized anchor 2.

3 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, concise description that explicitly pairs the 'when' (Use when admin asks...) with four concrete 'what' actions in a distinctive niche, using natural trigger terms. No vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'configure an MCP tool server', 'rotate credentials', 'grant/revoke worker access', 'add a custom API integration via YAML' — matching the anchor for several specific concrete actions rather than the single-action anchor 2.

3 / 3

Completeness

Explicit 'Use when admin asks to...' trigger clause answers 'when', and the enumerated actions answer 'what'; it is not capped at 2 because the 'Use when...' guidance is present and explicit.

3 / 3

Trigger Term Quality

Phrasings like 'admin asks to configure an MCP tool server', 'rotate credentials', 'grant/revoke worker access', and 'add a custom API integration' are natural admin requests a user would actually say, giving good coverage rather than only some relevant keywords.

3 / 3

Distinctiveness Conflict Risk

The MCP-tool-server / Higress-gateway / worker-access niche with these specific triggers is clearly distinct and unlikely to fire for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

12

/

12

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
agentscope-ai/AgentTeams
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.