himalaya

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./src/qwenpaw/agents/skills/himalaya-en/SKILL.md

Quality

Content

65%

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 with concrete commands and real pitfall warnings, but conciseness and workflow clarity are held back by a duplicated inline config block, missing verification steps for destructive email operations, and a broken reference to a non-existent message-composition.md file.

Suggestions

Fix the broken reference: either create references/message-composition.md or remove the 'see references/message-composition.md' pointer on the MML tip line.

Replace the inline config.toml block with a pointer to references/configuration.md to remove duplication, or keep only a minimal snippet inline.

Add a verification checkpoint before destructive operations, e.g. 'himalaya message read 42' to confirm the right message before running 'himalaya message delete 42'.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean actionable commands with little concept-explanation fluff, but the inline ~20-line config.toml block duplicates references/configuration.md and the full Python smtplib script could be referenced rather than inlined; not a 3 because of this tightening opportunity, not a 1 because no padded boilerplate.	2 / 3
Actionability	Provides numerous concrete, copy-paste-ready commands (himalaya envelope list, message read 42, template write \| template send) plus a complete executable Python attachment script; matches the 'fully executable, copy-paste ready' anchor and is not a 2 because examples are complete rather than pseudocode.	3 / 3
Workflow Clarity	Operations are well organized and the recommended send path with pitfalls is clear, but destructive operations (message delete 42, message move 42) have no validation/verification checkpoint before acting; per the rubric missing validation for destructive operations caps workflow_clarity at 2, and it is not a 3 for that reason.	2 / 3
Progressive Disclosure	There is a signaled one-level reference to the real references/configuration.md, but the body also references references/message-composition.md which does not exist (broken navigation) and the inline config block duplicates the reference file; not a 3 because of the broken link and duplication, not a 1 because structure and one real reference are present.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 specific and distinctive, naming a concrete tool and enumerating many real email actions with natural trigger terms. Its main weakness is the absence of an explicit 'when to use' trigger clause, which caps completeness.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user wants to send, read, search, or organize email from the terminal with himalaya.'

Drop or de-emphasize the 'MML (MIME Meta Language)' jargon in the description since a user would rarely say it; keep it for the body.

Dimension	Reasoning	Score
Specificity	Lists seven concrete actions (列出、阅读、撰写、回复、转发、搜索、整理邮件) plus multi-account and MML support, matching the 'multiple specific concrete actions' anchor; not a 2 because it is comprehensive rather than partial.	3 / 3
Completeness	Clearly states what the tool does but has no 'Use when...' clause or equivalent trigger guidance for when Claude should invoke it; per the judging guideline a missing explicit trigger caps completeness at 2, and it is not a 3 for that reason.	2 / 3
Trigger Term Quality	Uses natural terms a user would say (管理邮件、撰写、阅读、搜索、回复、转发) alongside the tool name; not a 2 because common variations are well covered, though 'MML (MIME Meta Language)' is jargon it supplements rather than dominates.	3 / 3
Distinctiveness Conflict Risk	Names the specific CLI tool himalaya and a distinct email-management niche via IMAP/SMTP, unlikely to trigger for the wrong skill; not a 2 because it is clearly distinguishable rather than overlapping.	3 / 3
	Total	11 / 12 Passed

Validation

75%

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 — 12 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: agentscope-ai/QwenPaw
Path: src/qwenpaw/agents/skills/himalaya-en/SKILL.md
Commit: 734c8b9

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.