sales-cs-review

当用户想复盘或升级已启用的 sales-cs 时使用。扫描 sales-cs 的 feedback/ 聚合客户反馈，结合用户意见提出升级建议（调整 MEMORY 客服手册 / 话术 / IDENTITY 称呼 / DECLARED_SKILLS 等），确认后由 main agent 直接改 sales-cs workspace 文件。 sales-cs 是对外 crew，不自行升级，所有调整经本技能由 main agent 落地。

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./crews/main/skills/sales-cs-review/SKILL.md

Quality

Content

75%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 well-structured, mostly lean workflow with concrete commands, named targets, and a strong user-confirmation validation gate for a customer-facing change. The main gaps are the placeholder workspace path and the absence of explicit error-recovery branches.

Suggestions

Replace the literal '<workspace 绝对路径>' placeholder with a resolved or environment-variable-based path (the script already honors SALES_CS_WORKSPACE) so the command is copy-paste ready.

Add a short error-recovery branch in Step 3 (e.g. what to do if a target file is missing or an edit fails) to complete the validation feedback loop.

Surface the SALES_CS_WORKSPACE override and exit-code semantics from scan_feedback.py in the body so callers know how to point the script at the right workspace.

Dimension	Reasoning	Score
Conciseness	Lean, task-focused prose that assumes Claude's competence — no padding about what feedback or crews are — with only minor clauses in Pitfalls that could be trimmed.	4 / 5
Actionability	Provides a concrete bash invocation and names exact files (MEMORY.md / AGENTS.md / IDENTITY.md / SOUL.md / DECLARED_SKILLS) plus a worked suggestion example, but the script path uses a literal '<workspace 绝对路径>' placeholder rather than copy-paste-ready form.	4 / 5
Workflow Clarity	Clear Step 1→4 sequence with an explicit validation checkpoint ('不直接动手，先呈现给用户确认' then '用户确认后落地') for an outward-facing edit, plus a post-change report step; minor gaps are no error-recovery path if an edit fails or a file is missing.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with a single one-level-deep bundle reference (scripts/scan_feedback.py, which exists) and no nested references; the placeholder path and lack of a references/ index keep it just short of ideal.	4 / 5
	Total	16 / 20 Passed

Description

71%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 clear, third-person description that names concrete actions and an explicit trigger clause, well-distinguished from sibling skills. Its main weaknesses are limited natural trigger-term coverage and a 'when' clause that could enumerate more user scenarios.

Suggestions

Add a couple of natural user phrasings to the description (e.g. '复盘下 sales-cs', '调整下客服话术') so the trigger matches what users actually say.

Expand the 'when' clause beyond 复盘/升级 to cover the scenarios already listed in the body (改记忆/说话口气/IDENTITY/客服手册/可用技能).

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — '扫描 feedback/ 聚合客户反馈', '提出升级建议', '调整 MEMORY 客服手册 / 话术 / IDENTITY 称呼 / DECLARED_SKILLS', '由 main agent 直接改 sales-cs workspace 文件' — with named targets, though '提出升级建议' is somewhat generic, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what (scan/aggregate/suggest/adjust files) and when ('当用户想复盘或升级已启用的 sales-cs 时使用'), but the 'when' clause covers only 复盘/升级 and could be more specific.	4 / 5
Trigger Term Quality	Contains relevant keywords like '复盘', '升级', '客户反馈' but misses the natural phrasings a user would actually say (e.g. '看看客服最近怎么样', '调整下客服话术') that appear only in the body, not the description.	3 / 5
Distinctiveness Conflict Risk	Scoped to a single named crew (sales-cs) at a specific lifecycle stage (review/upgrade of an already-enabled crew), and explicitly distinguished from sales-cs-enablement, giving a clear niche with minimal conflict risk.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: TeamWiseFlow/xiaobei
Path: crews/main/skills/sales-cs-review/SKILL.md
Commit: fdc03d6

Reviewed: 25 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.