email-ops

邮件操作技能。代替用户起草并发送邮件。

Quality

67%

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 ./skills/email-ops/SKILL.md

Quality

Content

81%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.

The body is a well-structured, actionable email-drafting/sending workflow with strong validation and error-recovery checkpoints around the destructive send step, scoring highly on workflow clarity and actionability. The main refinements are tightening minor redundancy and aligning the send-command reference with the actual bundled script name.

Dimension	Reasoning	Score
Conciseness	The body is efficient: per-type LLM prompt templates and a single send command earn their tokens rather than explaining concepts Claude already knows; minor redundancy (follow-up timing appears both in Step 2 and the timing table) keeps it just below a 5.	4 / 5
Actionability	It gives a concrete executable send command ('email-ops --to ... --subject ... --body ...') and copy-ready per-type prompt templates with explicit format requirements; the PATH wrapper reference slightly mismatches the bundled script name (send_email.py), a minor gap that prevents a 5.	4 / 5
Workflow Clarity	A clear 6-step sequence with explicit validation checkpoints for the destructive send action: default-draft behavior, send-only-on-explicit-request, post-send Sent-folder confirmation, and a 常见错误 recovery table covering SMTP auth failure and missing-recipient cases — matching the anchor for clear sequence with explicit validation and error-recovery feedback loops.	5 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections (steps, prompt templates, timing table, error table) with the only bundle file being scripts/send_email.py; the inline per-type prompt templates could arguably be externalized but are reasonable inline, matching the anchor for good structure with minor organization gaps rather than the clean one-level-deep reference split of a 5.	4 / 5
	Total	17 / 20 Passed

Description

53%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.

The description is concise and states a clear capability in third person, but it omits explicit trigger/Use-when guidance and lacks keyword variations, which caps both completeness and trigger-term quality at the midpoint. Adding a 'Use when...' clause with synonyms would lift completeness and trigger coverage.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g., 起草邮件 / 发邮件 / 回复邮件 / 跟进客户) to raise completeness above 3.

Include keyword synonyms and variations (邮件 / email / 邮件草稿 / 回复 / 跟进) to broaden trigger-term coverage.

Mention the supported send channels or account types briefly to sharpen distinctiveness from generic messaging skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('邮件操作技能') and two concrete actions ('起草并发送邮件'), matching the anchor for 1-2 concrete actions without comprehensive coverage; it is not at 4 because no additional specific actions are enumerated.	3 / 5
Completeness	It gives a clear 'what' ('代替用户起草并发送邮件') but no explicit 'when'/'Use when' trigger guidance; per the guideline a missing Use-when clause caps completeness at 3, and it is not 2 because the what is concrete rather than vague.	3 / 5
Trigger Term Quality	The single natural keyword '邮件' is present and user-plausible, but no synonyms, variations, or related trigger phrases are included, matching the anchor for some relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	Email drafting/sending is a mostly distinct niche with only minor overlap risk against general communication skills, matching the anchor for mostly distinct with minor overlap; it is not 5 because no concrete trigger phrasing sharpens the niche.	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
description_field	'description' is very short (19 chars), consider making it more detailed	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: TeamWiseFlow/xiaobei
Path: skills/email-ops/SKILL.md
Commit: fdc03d6

Reviewed: 11 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.