Name: apple-mail
Rating: 72 (1 reviews)
Author: mitsuhiko

apple-mail

Search, read, and extract attachments from Apple Mail's local storage. Query emails by sender, recipient, subject, body, date, mailbox, and flags. Read raw RFC822 messages and extract file attachments.

Quality

90%

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

Quality

Content

100%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 an exemplary lean tool reference: executable examples, complete flag documentation, explicit output formats, and non-obvious operational caveats, with zero padding. The only structural observation is that the script path is hardcoded to a user-specific location (~/Development/agent-stuff/...), which is an actionability nit rather than a rubric failure.

Dimension	Reasoning	Score
Conciseness	The body is a lean tool reference — a copy-paste command block, a flag table, an output-format list, and a short Notes section — with no explanation of concepts Claude already knows and no padding. Every section carries information Claude could not infer (e.g., "The body search queries the summaries table (Apple Mail's plaintext preview), not the full email body").	5 / 5
Actionability	All commands are fully executable and copy-paste ready ("$TOOL search --from 'peter@' --subject 'dinner' --limit 5", "$TOOL attachment 783660 'Rechnung.pdf'"), the output format of each subcommand is specified, and the Notes surface real edge cases like percent-encoded mailbox URLs and .partial.emlx files.	5 / 5
Workflow Clarity	This is a read-only query tool ("Read-only — it never modifies mail data"), so no destructive/batch validation cap applies, and the simple-skill exception holds: each subcommand is unambiguous. The Quick Reference also conveys the natural sequence (search → info/read → attachment) and includes a built-in feedback signal ("read warns about this" for .partial.emlx) plus cleanup guidance for the temp directory.	5 / 5
Progressive Disclosure	The skill bundle contains only SKILL.md (no references/, scripts/, or assets/ directories exist), and the body is a compact, well-sectioned single-file reference for one script with its path given up front — nothing is buried, nested, or inlined that belongs in a separate file. No external references are needed at this size, so well-organized sections suffice.	5 / 5
	Total	20 / 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 strong, concrete, third-person description that clearly states what the skill does with specific capability enumeration. Its one material weakness is the absence of any "Use when..." trigger clause, which both caps completeness and leaves trigger guidance implicit.

Suggestions

Append an explicit trigger clause, e.g., "Use when the user mentions Apple Mail, Mail.app, macOS Mail, .emlx files, or wants to search/extract from a local Mail database."

Add natural synonyms and file extensions users would actually say ("Mail.app", "macOS Mail", ".emlx", "email attachments") to broaden trigger term coverage.

Optionally state the platform constraint ("on macOS") in the description so it cannot trigger for non-Apple mail setups.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "Search, read, and extract attachments", "Query emails by sender, recipient, subject, body, date, mailbox, and flags", "Read raw RFC822 messages and extract file attachments" — with comprehensive, non-generic coverage. Not the level below (4) because coverage is broad and every action is concrete with no filler.	5 / 5
Completeness	"What" is explicit (search/read/extract from Apple Mail's local storage with the query dimensions enumerated), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because the "when" is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	Good natural keywords: "Apple Mail", "emails", "sender", "recipient", "subject", "attachments", "mailbox", "flags", "RFC822". Not 5 because common user variations are missing — e.g., "Mail.app", "macOS", ".emlx", "email search" — while the included terms are solid but not exhaustive.	4 / 5
Distinctiveness Conflict Risk	"Apple Mail's local storage" plus "raw RFC822 messages" carves out a clear niche (local macOS Mail database access) with distinct triggers and minimal overlap risk against generic email/IMAP or document skills. Not 4 because the domain anchor is specific enough that mis-triggering for a different skill is unlikely.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mitsuhiko/agent-stuff
Path: skills/apple-mail/SKILL.md
Commit: 0865c84

Reviewed: 8 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.