CtrlK
BlogDocsLog inGet started
Tessl Logo

deal-tracker

Builds a relationship or deal summary using the Superhuman Mail MCP server — pulling together all email history, read receipts, and calendar interactions with a specific person or company to act as a lightweight CRM. Use this skill whenever someone asks to "show me all communication with [person/company]", "what's the status of my deal with [company]", "give me a relationship summary for [person]", "when did I last talk to [person]", "pull up everything about [company]", "track this deal", "who haven't I followed up with", "show me engagement on emails I sent to [person]", "CRM view of [person]", "what's my communication history with [person]", or any variation of wanting a consolidated view of a relationship or deal. Trigger broadly — if someone wants to understand the full picture of their interactions with a person or company, this skill should activate.

89

1.41x
Quality

85%

Does it follow best practices?

Impact

96%

1.41x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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, actionable skill body with clear sequencing and concrete MCP call guidance. Main weaknesses are mild verbosity in the cross-platform catalog and the absence of explicit validation checkpoints.

Suggestions

Add explicit validation/sanity-check steps after Step 2 (e.g., confirm threads were returned before building the timeline, handle empty-result cases) to lift workflow clarity toward the top anchor.

Condense the Step 2b cross-platform tool catalog into a compact checklist or move the per-tool detail into a reference file, since it is the most padded section of the body.

Tighten the example output template into a more concrete, minimal structure to improve token efficiency without losing clarity.

DimensionReasoningScore

Conciseness

The body is largely efficient and assumes Claude's competence, but the long Step 2b cross-platform enumeration (listing Slack, Linear, Jira, Asana, ClickUp, Coda, Notion, Confluence, Granola, knowledge graph with repeated descriptions) is somewhat padded and could be trimmed.

4 / 5

Actionability

It names specific executable MCP calls (list_threads with from/to/labels filters, query_email_and_calendar, get_read_statuses, get_thread) and gives concrete query phrasings, but the example output blocks are templates rather than fully copy-paste executable code, leaving minor gaps.

4 / 5

Workflow Clarity

The process is clearly sequenced into Steps 1–4 with a parallel-gathering step and an optional enrichment branch, including branching guidance for yes/no/skip; however there are no explicit validation checkpoints confirming data was retrieved before synthesis, which keeps it just below the top anchor.

4 / 5

Progressive Disclosure

Content is well-organized into clear sections (How it works, Multi-contact view, Important guidelines) with no bundle files to reference; the inlined template blocks are appropriate, though the cross-platform catalog is long enough that it could live in a reference file.

4 / 5

Total

16

/

20

Passed

Description

96%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, specific description with comprehensive natural trigger phrases and clear what/when coverage. Slight over-triggering breadth is the only minor weakness.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — pulling together email history, read receipts, and calendar interactions to act as a lightweight CRM — giving comprehensive, specific capability coverage rather than vague language.

5 / 5

Completeness

It explicitly answers both what (builds a relationship/deal summary from email, receipts, and calendar data) and when (an explicit 'Use this skill whenever...' clause plus many concrete trigger phrases and a broad-trigger instruction), matching the top anchor.

5 / 5

Trigger Term Quality

It includes a broad set of natural trigger phrases users would actually say ('show me all communication with', 'what's the status of my deal with', 'who haven't I followed up with', 'CRM view of') with many phrasing variations, matching the comprehensive-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

The CRM/relationship-summary niche and Superhuman Mail specificity make it largely distinct with minimal conflict risk, but the broad-trigger instruction to 'activate' on any consolidated relationship view slightly raises overlap risk with general mail/contact skills.

4 / 5

Total

19

/

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
superhuman/mcp-mail
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.