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).

1.69x

Quality

77%

Does it follow best practices?

Impact

93%

1.69x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/himalaya/SKILL.md

The canonical home for this skill is himalaya in Hung-Reo/hungreo-openclaw

Quality

Content

80%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, highly actionable command reference with exemplary progressive disclosure — both referenced files exist, are clearly signaled, and correctly absorb the detailed material. The two weaknesses are the duplicated inline config template (a token-efficiency cost) and the lack of any validation/verification step around destructive operations like message deletion. Adding a read-and-confirm step before delete/move and trimming the inline TOML would bring this to near-perfect.

Suggestions

Add a validation checkpoint before destructive operations, e.g., "Run `himalaya message read 42` and confirm the sender/subject before `himalaya message delete 42`" — the missing verification currently caps workflow clarity at 3.

Trim the ~25-line inline TOML block to a minimal snippet and point to `references/configuration.md` (which already contains the same setup plus provider-specific variants) to remove duplication.

Clarify the search example ("himalaya envelope list from john@example.com subject meeting") with a one-line note on the filter syntax, since it is the only command whose argument structure is not self-evident.

Dimension	Reasoning	Score
Conciseness	The body is a lean command reference — terse section headers, minimal prose, no explanation of concepts Claude already knows (no "what is IMAP" padding). The one inefficiency is the ~25-line inline TOML config template, which substantially duplicates the minimal IMAP+SMTP setup in references/configuration.md and could be trimmed to a short snippet plus a pointer. This fits the score-4 anchor (efficient, minor instances that could be trimmed) rather than 5, where every token would earn its place.	4 / 5
Actionability	Every section gives copy-paste-ready, concrete commands covering the common cases: "himalaya envelope list", "himalaya message read 42", "himalaya message reply 42 --all", "himalaya message move 42 \"Archive\"", "himalaya attachment download 42 --dir ~/Downloads", "himalaya envelope list --output json", and a full stdin send example. This matches the score-5 anchor (fully executable, copy-paste ready, common cases covered); it is not 4 because there are no notable gaps in executable detail.	5 / 5
Workflow Clarity	Prerequisites and configuration setup form a clear sequence ("himalaya account configure" or manual config.toml), and the Tips note "Message IDs are relative to the current folder; re-list after folder changes" shows some care. However, destructive operations — "himalaya message delete 42" — are presented with no validation checkpoint (no read-before-delete, folder confirmation, or verification step), so per the rubric guidelines workflow clarity is capped at 3 for missing validation in destructive operations. It is not 4 because a required checkpoint is absent, not merely minor.	3 / 5
Progressive Disclosure	The body opens with a clearly signaled References section — "`references/configuration.md` (config file setup + IMAP/SMTP authentication)" and "`references/message-composition.md` (MML syntax for composing emails)" — both of which exist as real bundle files, are exactly one level deep, and are re-pointed to in the Tips. The split is appropriate: quick-start config and common operations inline, provider-specific configs (Gmail/iCloud/OAuth2) and full MML syntax in the references. This matches the score-5 anchor (clear overview with well-signaled one-level-deep references, easy navigation).	5 / 5
	Total	17 / 20 Passed

Description

75%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 specific, well-scoped description with concrete action verbs and a distinct niche, written in appropriate third-person voice. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness and slightly limits trigger-term coverage. Adding trigger phrases (e.g., "Use when the user asks to check, reply to, send, or search email from the terminal") would raise it to top marks.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to read, reply to, forward, send, or search emails from the terminal" — the missing 'Use when...' guidance currently caps completeness at 3.

Include common synonyms and vocabulary users naturally say, such as "mail", "inbox", and "attachments", to improve trigger-term coverage from good to comprehensive.

Mention attachments explicitly (download/save attachments is a supported capability documented in the body) so the description's capability list is fully comprehensive.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "list, read, write, reply, forward, search, and organize emails" — plus "Supports multiple accounts and message composition with MML (MIME Meta Language)", giving comprehensive coverage of the tool's capabilities. It matches the score-5 anchor (multiple specific concrete actions, comprehensive coverage) rather than 4, which expects minor gaps in coverage.	5 / 5
Completeness	The "what" is clear and concrete ("CLI to manage emails via IMAP/SMTP... list, read, write, reply, forward, search, and organize"), but there is no explicit "Use when..." clause or equivalent trigger guidance — "Use `himalaya` to list..." describes how to use it, not when the skill should activate. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3; it is not 4 because the "when" is absent rather than merely implicit.	3 / 5
Trigger Term Quality	Good keyword coverage with natural terms users would say — "emails", "reply", "forward", "search", "list", "terminal" — but common variations like "mail", "inbox", "attachments", or account/provider terms are missing. This sits squarely in the score-4 anchor (good coverage, a few natural terms missing) rather than 5 (comprehensive synonyms/extensions).	4 / 5
Distinctiveness Conflict Risk	The description carves out a clear niche — terminal email management via IMAP/SMTP with MML composition — with distinct trigger vocabulary (reply, forward, search emails) unlikely to fire for unrelated skills. It matches the score-5 anchor (clear niche with distinct triggers, minimal conflict risk); it is not 4 because no closely related skill domain meaningfully overlaps.	5 / 5
	Total	17 / 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
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

	Total	13 / 16 Passed

Repository: trpc-group/trpc-agent-go
Path: openclaw/skills/himalaya/SKILL.md
Commit: 9bb1c42

Reviewed: 5 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.