CtrlK
BlogDocsLog inGet started
Tessl Logo

email-ops-skill

Trigger whenever the user wants to do anything with a real email account: check inbox, read messages, reply, forward, compose, send, search, archive, delete. Typical phrasing: "check my inbox", "what did X send me", "查下我邮箱". **Do not use for**: instant messaging / IM / WeChat / Slack, translating text that merely contains the word "email", or offline parsing of `.eml` files (→ just use Read).

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 tight, highly actionable operations manual with concrete tool usage, mandatory confirmation checkpoints for irreversible actions, and clear batch/destructive safeguards. Only mild conciseness redundancy keeps it from a perfect content score.

Suggestions

Consolidate the send-confirmation guidance so the 'Common Mistakes' entries reference the workflow steps rather than restating them, trimming the small redundancy.

The 'Forwarding Messages' section repeats the confirm-before-send rule already covered in Workflows 1-2; a cross-reference would save tokens.

DimensionReasoningScore

Conciseness

Mostly lean with tool tables and concise operational rationales ('once an email is sent, it can't be recalled'); minor redundancy between the workflow confirmation steps and the 'Common Mistakes' list keeps it just below the leanest anchor.

4 / 5

Actionability

Fully executable guidance: named tools/modes, required parameters (accountEmail, messageId, inReplyTo, references), exact subject prefixes (Re:/Fwd:), pagination (1-50) and batch limits (≤50), and copy-ready plain-text confirmation patterns.

5 / 5

Workflow Clarity

Destructive/batch operations (send, delete, move, batch-*) carry explicit validation checkpoints — 'Show the draft… wait for the user to confirm' and 'show samples and wait for user confirmation before bulk delete/move' — with feedback rationale and ordering, satisfying the validation requirement.

5 / 5

Progressive Disclosure

A single self-contained SKILL.md with no bundle directories and well-organized sections; for a sub-50-line-task single-tool skill this clean structure is appropriate and fully navigable.

5 / 5

Total

19

/

20

Passed

Description

100%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 exemplary: concrete capabilities, natural multilingual trigger phrasing, and explicit negative boundaries that disambiguate it from adjacent skills. It cleanly answers what, when, and what-not-to-use-for.

DimensionReasoningScore

Specificity

Enumerates many concrete actions — 'check inbox, read messages, reply, forward, compose, send, search, archive, delete' — giving comprehensive coverage rather than generic verbs.

5 / 5

Completeness

Explicitly answers both 'what' (operations on a real email account) and 'when' ('Trigger whenever the user wants to do anything with a real email account', typical phrasing, plus an explicit exclusion list).

5 / 5

Trigger Term Quality

Provides natural phrasings users would actually say ('check my inbox', 'what did X send me', '查下我邮箱') plus disambiguating synonyms (IM/WeChat/Slack), covering variations including a non-English trigger.

5 / 5

Distinctiveness Conflict Risk

Carves a clear niche and actively reduces conflict via the 'Do not use for' list (IM/WeChat/Slack, translating 'email' mentions, offline .eml parsing → use Read), minimizing wrong-skill triggering.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
itsablabla/openloaf-web
Reviewed

Table of Contents

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.