CtrlK
BlogDocsLog inGet started
Tessl Logo

mailbox

Use this skill whenever the user needs ANY mailbox/email operation — checking, reading, searching, sending, replying, forwarding, organizing or deleting email, managing threads, connecting a personal mailbox, or registering a new mailbox. This skill is the single entry point for email tasks and orchestrates qwenpawmail-mcp for nine supported personal-mail domains.

72

Quality

90%

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

81%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 well-structured, actionable guide for a specific MCP integration with strong workflow sequencing and validation. It loses a little on conciseness from repeated safety guidance and on actionability from unspecified full tool signatures.

Suggestions

Consolidate the repeated "never store/expose secrets" rules into the Safety section and reference it once from the credential model and Step 3 to trim redundancy.

Add a brief call-signature reference for the most-used write/search tools (e.g. send_message, search_messages, move_message) so guidance is copy-paste ready.

Consider moving the per-domain registration entry table and the full tool tables into a reference file, keeping SKILL.md as a lean overview with one-level-deep pointers.

DimensionReasoningScore

Conciseness

Dense and mostly efficient with no padding about concepts Claude already knows, but the "never store secrets" guidance is repeated across the credential model, Step 3, and Safety sections and could be consolidated.

4 / 5

Actionability

Gives concrete tool names, an explicit agent.json shape, exact registration URLs, and parameters for key calls (e.g. create_mailbox(domain, username)), but full call signatures are not specified for every tool, leaving minor gaps.

4 / 5

Workflow Clarity

The connect/create flow is clearly sequenced (Step 1, 2a, 2b, 3) with explicit validation checkpoints (check_auth after registration, "Do not run other mail tools until it succeeds", confirm-before-delete, UID refresh before acting), satisfying the destructive-operation validation requirement.

5 / 5

Progressive Disclosure

Well-organized into clear sections with no nested references and no bundle files provided; the inline registration and tool-reference tables are reasonable for a single-MCP skill but the ~155-line body is monolithic rather than split into reference files.

4 / 5

Total

17

/

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 strong: concrete, comprehensive action list, explicit what/when triggers, third-person voice, and a clearly distinct niche. The capitalized "ANY" is slightly emphatic but the enumeration and nine-domain scoping keep it from over-claiming.

DimensionReasoningScore

Specificity

Lists many concrete actions ("checking, reading, searching, sending, replying, forwarding, organizing or deleting email, managing threads, connecting a personal mailbox, or registering a new mailbox") and scopes them to a specific MCP for nine domains, giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what ("orchestrates qwenpawmail-mcp for nine supported personal-mail domains") and when ("Use this skill whenever the user needs ANY mailbox/email operation") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrasing is well covered ("check email", "send", "reply", "forward", "search", "organize or delete email", "mailbox") with synonyms (mailbox/email); no relevant file extensions exist for this domain.

5 / 5

Distinctiveness Conflict Risk

Claims a clear niche as "the single entry point for email tasks" tied to a named MCP and nine specific domains, minimizing overlap with other skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
agentscope-ai/QwenPaw
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.