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

73%

Does it follow best practices?

Impact

93%

1.69x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/himalaya/SKILL.md

Quality

Discovery

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.

This is a strong description with excellent specificity and distinctiveness, clearly naming the tool, protocols, and concrete actions. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. Adding trigger guidance would elevate this from good to excellent.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to send, read, or manage emails from the command line, mentions himalaya, or needs IMAP/SMTP email operations.'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: list, read, write, reply, forward, search, and organize emails. Also mentions specific protocols (IMAP/SMTP), multiple accounts support, and MML composition.	3 / 3
Completeness	Clearly answers 'what does this do' with specific actions and capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied by the nature of the description.	2 / 3
Trigger Term Quality	Includes strong natural trigger terms: 'emails', 'IMAP', 'SMTP', 'terminal', 'himalaya', 'reply', 'forward', 'search', plus the tool name itself. Users asking about email from the CLI would naturally use these terms.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive — the combination of CLI email management, the specific tool name 'himalaya', IMAP/SMTP protocols, and MML creates a very clear niche that is unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Implementation

64%

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

This is a solid command reference for the Himalaya CLI with excellent actionability — nearly every operation has a concrete, executable example. The main weaknesses are that the inline configuration block is lengthy and duplicates what should be in the referenced configuration file, and there are no validation/verification steps after setup or destructive operations like delete. The skill would benefit from being tighter and including a quick verification workflow after configuration.

Suggestions

Move the full TOML configuration example to `references/configuration.md` and keep only the wizard command (`himalaya account configure`) plus a brief note in the main skill, improving both conciseness and progressive disclosure.

Add a verification step after configuration setup, e.g., 'Verify connection: `himalaya envelope list` — if this returns your inbox, setup is complete.'

Add a caution or confirmation note for destructive operations like `message delete`, noting that behavior depends on backend configuration (trash vs permanent delete).

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient with concrete commands, but includes some unnecessary elements like the full TOML configuration example (which is quite long) and the prerequisites section stating obvious things. The tips section also has some filler. However, it doesn't over-explain concepts Claude already knows.	2 / 3
Actionability	Nearly every section provides copy-paste ready commands with specific flags and arguments. The configuration example is complete and executable, search syntax is shown by example, and multiple approaches are given for composing emails (interactive, piped template, flags).	3 / 3
Workflow Clarity	The skill is primarily a command reference rather than a multi-step workflow, so sequencing is less critical. However, there are no validation checkpoints — for example, after configuration setup there's no 'verify your connection works' step, and the delete operation has no confirmation or recovery guidance.	2 / 3
Progressive Disclosure	References to `references/configuration.md` and `references/message-composition.md` are listed at the top, but no bundle files were provided to verify they exist. The main file is quite long (~150 lines of content) and the full configuration TOML could reasonably live in the referenced configuration file instead of being inline.	2 / 3
	Total	9 / 12 Passed

Validation

72%

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 — 8 / 11 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	8 / 11 Passed

Repository: deepgram/dglabs-deepclaw
Commit: ec8d4f8

Reviewed: about 9 hours 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.