CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

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.

An exemplary router-style skill body: dense with non-obvious operational gotchas, explicit verification checkpoints, and a clean one-level-deep reference structure with a situation-to-doc routing table. The only notable gap is the absence of even a one-line script invocation example inline.

DimensionReasoningScore

Conciseness

Every line carries non-obvious operational knowledge Claude could not know ("Auth plugin takes ~10s to activate", "Consumer authorization is a REPLACE operation", "MCP Server SSE endpoint always returns 200", "accessToken: \"\" as the credential key"). Nothing explains generic concepts; the overview, gotchas, and routing table all earn their tokens.

5 / 5

Actionability

Concrete guidance throughout: both scripts are named ("setup-mcp-server.sh", "setup-mcp-proxy.sh"), template paths given ("references/mcp-*.yaml"), and the situation→doc routing table maps each task to a specific file. Not a 5 because no invocation syntax for either script appears inline — the reader must open a reference even for a one-line usage example.

4 / 5

Workflow Clarity

Validation checkpoints are explicit and prominent ("always wait and verify with mcporter before notifying Workers", "Always verify end-to-end before notifying Workers", "wait for reconciliation and file-sync before verifying tools"), which satisfies the destructive/batch validation requirement. Not a 5 because the create→verify→notify sequence is implicit across gotchas rather than an ordered workflow; not a 3 because checkpoints are explicit, not missing.

4 / 5

Progressive Disclosure

Model progressive disclosure: lean overview and gotchas inline, details split into five one-level-deep reference files (all verified to exist, with no chained references), an explicit situation→doc routing table, and "Read the relevant doc before executing. Do not load all of them." prevents over-loading context.

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.

A strong trigger-focused description with explicit when-guidance and concrete, distinct capability terms. Its main weakness is that the what is subordinated to the when-clause and the skill's proxy-an-existing-MCP-server capability is entirely unrepresented.

Suggestions

Lead with an independent what-sentence before the trigger clause, e.g., "Creates, updates, and proxies MCP tool servers on the Higress AI Gateway... Use when admin asks to..." to make both what and when fully explicit.

Add the proxy capability as a trigger, e.g., "proxy an existing MCP server (SSE/StreamableHTTP)", since setup-mcp-proxy.sh is half the skill's functionality.

Include a couple of natural synonyms users would say, such as "set up MCP tools" or "add a tool to the gateway", to broaden trigger coverage.

DimensionReasoningScore

Specificity

Four concrete actions are explicitly stated: "configure an MCP tool server", "rotate credentials", "grant/revoke worker access to MCP tools", and "add a custom API integration via YAML", with concrete hooks ("e.g., GitHub, weather API"). Not a 5 because proxying existing MCP servers (SSE/HTTP) — a core capability with its own script in the bundle — is absent from the description; not a 3 because coverage well exceeds 1-2 actions.

4 / 5

Completeness

The when is explicit and specific ("Use when admin asks to..."), and the what is present via the action verbs, but the capabilities are subordinated inside the when-clause rather than stated as an independent what-sentence, and the proxy capability is missing. Not a 5 since the what is not fully explicit; not a 3 because both what and when are present and concrete.

4 / 5

Trigger Term Quality

Natural admin phrasing is present ("configure an MCP tool server", "rotate credentials", "grant/revoke worker access", "custom API integration via YAML") plus concrete triggers "GitHub, weather API". A few natural terms are missing — no synonym for proxying an existing MCP server, nor "set up", "list", or "delete" server operations.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers: "MCP tool server" configuration, worker access grants/revokes, and credential rotation scoped to MCP tools are unlikely to collide with other skills' triggers. Voice is third person/standard "Use when" form.

5 / 5

Total

17

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

agentscope-ai/AgentTeams

Path

manager/agent/skills/mcp-server-management/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.