awada-channel-setup

启用并配置 awada channel，使对外 crew（如 sales-cs）能以企业微信联系人的形态连接外部用户。当用户或 main agent 要求启用 sales-cs 时使用本技能：建议配置 awada channel → 获得确认 → 按 SOP 完成安装依赖、写 openclaw.json、重启 Gateway。

Quality

88%

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

77%

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

A well-structured, concise operational SOP with a clear sequenced workflow and validation, but actionability and progressive disclosure are weakened by a script-name mismatch and a dangling template-file reference that is absent from the bundle.

Suggestions

Reconcile the command name: the body says run `awada-channel-setup` but the bundle script is `scripts/apply-awada-config.py` — either add an entry point/alias named `awada-channel-setup` or update the body to invoke `python scripts/apply-awada-config.py`.

Ship the referenced `openclaw-awada-sample.json` template in the bundle (or remove the reference); both the body and the script read it as the config template, so its absence breaks step 2.

In step 2, explicitly link the bundle script path (e.g. `scripts/apply-awada-config.py`) so the reference from SKILL.md to the bundle file is clearly signaled.

Dimension	Reasoning	Score
Conciseness	The body is dense with project-specific operational detail (Docker vs systemd paths, relay scope requirements, customerDB hook defaults) and does not pad with concepts Claude already knows; references like "it-engineer MEMORY「binding routing 坑」" assume competence rather than re-explaining.	3 / 3
Actionability	It gives concrete commands (pnpm install --prod, systemctl --user restart, docker restart) and a real script, but the body instructs running `awada-channel-setup` while the bundle script is actually `scripts/apply-awada-config.py`, and both reference an `openclaw-awada-sample.json` template that is absent from the bundle — key details are incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	The SOP is a clearly numbered 4-step sequence (confirm deps → write openclaw.json → restart Gateway → verify) with an explicit validation step (channel connected, test round-trip, customerDB records) and a user-consent checkpoint before the destructive restart, satisfying the level-3 anchor.	3 / 3
Progressive Disclosure	Sections are well organized and the single script reference is one level deep, but the body never explicitly links the `scripts/apply-awada-config.py` bundle file (it only says "用本技能脚本") and references a missing `openclaw-awada-sample.json`, leaving navigation partly unclear.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 states concrete capabilities, an explicit use-when trigger, and a clearly bounded niche. It avoids vague fluff and over-claims while remaining concise.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "安装依赖、写 openclaw.json、重启 Gateway" and "启用并配置 awada channel" — rather than vague language, matching the level-3 anchor for several specific concrete actions.	3 / 3
Completeness	It explicitly answers both what (启用/配置 awada channel so sales-cs connects as an enterprise-WeChat contact, plus the SOP steps) and when ("当用户或 main agent 要求启用 sales-cs 时使用本技能"), satisfying the level-3 anchor for explicit triggers on both.	3 / 3
Trigger Term Quality	Natural trigger terms a user would say are well covered — "启用 sales-cs", "awada channel", "对外 crew", "企业微信" — and the explicit clause "当用户或 main agent 要求启用 sales-cs 时使用本技能" reads like a real trigger phrase.	3 / 3
Distinctiveness Conflict Risk	The niche is very specific (awada channel setup for the sales-cs crew) with distinct triggers tied to sales-cs/awada, making conflict with other skills unlikely.	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: TeamWiseFlow/xiaobei
Path: crews/it-engineer/skills/awada-channel-setup/SKILL.md
Commit: bcef823

Reviewed: 3 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.