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.

1.41x

Quality

92%

Does it follow best practices?

Impact

96%

1.41x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is deal-tracker in superhuman/mcp-mail

Quality

Content

85%

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

The body is highly actionable and well-sequenced with a clear output template, and it is cleanly organized with no nested references. Its main weakness is redundancy: the cross-platform enrichment tools are listed across three steps and could be consolidated to improve token efficiency.

Suggestions

Consolidate the cross-platform tool list: define the Slack/Linear/Coda/Granola/knowledge-graph options once and reference them from Step 2b, the Step 3 template, and Step 4 instead of re-listing them each time.

Fix the inconsistent MCP server casing ('Superhuman_mail.list_threads' vs 'Superhuman_Mail.query_email_and_calendar') so the tool names are uniform and copy-paste reliable.

Trim the prose in 'Important guidelines' where points already follow from the structured steps, keeping only the guidance that is not obvious from the workflow.

Dimension	Reasoning	Score
Conciseness	The body is actionable and avoids explaining concepts Claude already knows, but the cross-platform tool categories (Slack, Linear/Jira, Coda/Notion, Granola, knowledge graph) recur across Step 2b, the Step 3 output template, and Step 4, which could be consolidated and tightened.	2 / 3
Actionability	Names concrete MCP calls with parameters and examples — 'Superhuman_mail.list_threads filtered by the contact's email address... with labels: ["INBOX"]... up to 50 threads', 'get_read_statuses', example calendar query strings — plus a copy-paste output template, matching the top anchor.	3 / 3
Workflow Clarity	A clearly sequenced workflow (Step 1 → 2 → 2b → 3 → 4) with parallel-call instructions and a structured output template that acts as a checklist; the task is read-only so no destructive-operation validation loop is required.	3 / 3
Progressive Disclosure	A single, well-organized SKILL.md with clear header navigation and no bundle files or nested references; per the scoring notes, well-organized sections without external references warrant the top score.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 description: concrete actions, third-person voice, explicit what-and-when triggers, and a well-defined niche. The only minor risk is the 'Trigger broadly' instruction, which could be softened to reduce overlap with general email or CRM skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'Builds a relationship or deal summary', 'pulling together all email history, read receipts, and calendar interactions', 'act as a lightweight CRM' — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (builds a Superhuman Mail MCP relationship/deal summary) and when (an explicit 'Use this skill whenever someone asks...' clause with many triggers), satisfying the top anchor.	3 / 3
Trigger Term Quality	Provides extensive natural phrasings 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', etc.), giving strong coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Superhuman Mail relationship/CRM summaries) with domain-specific triggers; the 'Trigger broadly' phrasing slightly raises overlap risk but the triggers are distinctive enough to avoid the wrong skill firing.	3 / 3
	Total	12 / 12 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: openai/plugins
Path: plugins/superhuman/skills/deal-tracker/SKILL.md
Commit: 11c74d6

Reviewed: about 10 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.