higress-gateway-management

Manage the Higress AI Gateway via its Console API (consumers, routes, AI providers, MCP servers). Use when creating consumers, configuring routes, or managing AI gateway settings.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

80%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.

The content is highly actionable and token-efficient, with executable curl examples and genuinely useful domain gotchas. Its main weaknesses are missing validation checkpoints around destructive operations and a missed progressive-disclosure opportunity: a large reference bundle exists but is never referenced.

Suggestions

Add a verification step after destructive or mutating operations (e.g., re-run the list endpoint or a GET after DELETE/PUT to confirm the change applied) to establish a validate-feedback loop.

Reference the provided bundle explicitly from the body (e.g., 'Full endpoint/schema reference: see references/higress-api-doc.json') and consider moving the exhaustive per-operation curl catalog there, keeping SKILL.md as a concise overview.

After POST /v1/ai/routes and PUT mutations, note the ~10-40s auth-plugin propagation delay as an explicit 'then wait and verify' checkpoint rather than only in Important Notes.

Dimension	Reasoning	Score
Conciseness	The body is lean and dominated by executable curl/jq commands with brief, domain-specific notes (version-field quirks, auth-activation timing, the /v1/ai/routes warning) that Claude would not already know, with no generic concept padding.	3 / 3
Actionability	Every operation ships as fully executable, copy-paste-ready curl with real example values (worker-alice, deepseek-route) and concrete jq transforms, not pseudocode.	3 / 3
Workflow Clarity	Sequencing is explicit (Step 1 GET / Step 2 modify / Step 3 PUT, plus the GET-before-PUT version guidance), but destructive DELETE and mutation workflows lack any verification checkpoint to confirm the change took effect, which caps clarity at 2.	2 / 3
Progressive Disclosure	Sections are well organized and there is a helpful cross-skill pointer (mcp-server-management), but ~200 lines of inline API reference duplicate what the provided references/higress-api-doc.json bundle could hold, and that bundle file is never signaled or linked from the body.	2 / 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.

The description is concise, specific, and clearly answers both what the skill does and when to use it with natural trigger terms, all in third person. It carves a clear niche unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete management actions across 'consumers, routes, AI providers, MCP servers' rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers what ('Manage the Higress AI Gateway via its Console API') and when ('Use when creating consumers, configuring routes, or managing AI gateway settings').	3 / 3
Trigger Term Quality	Natural trigger phrasings users would say ('creating consumers, configuring routes, or managing AI gateway settings') give good coverage rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The 'Higress AI Gateway' niche with domain-specific triggers is clearly distinguishable and unlikely to fire for unrelated skills; uses third person ('Manage').	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: agentscope-ai/AgentTeams
Path: manager/agent/skills-alpha/higress-gateway-management/SKILL.md
Commit: 785c2db

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.