twenty-partner-match

Match a qualified lead to Twenty partners and generate all intro emails in one run. Use when a lead folder exists and you need to find the right implementation partner, either after running twenty-partner-design-doc or standalone when partner-match-criteria.md is already present. Chains back into twenty-lead-intro-call-summary and twenty-partner-design-doc if the criteria file is missing.

Quality

96%

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

92%Weight 40%Scale 1-3

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 multi-phase workflow with strong validation checkpoints and executable code. Its only weakness is progressive disclosure: it is a monolithic file that could offload the GraphQL query and email templates into reference files.

Suggestions

Move the full partners GraphQL query into a references file (e.g. references/partners-query.graphql) and link to it from Phase 1a, keeping only the filter intent inline.

Extract the detailed email rules and per-email templates into a references file (e.g. references/email-templates.md), leaving a concise summary plus signposted link in Phase 2.

Add a short 'Inputs / Outputs' or quick-reference section near the top pointing to the credentials, criteria file, and output filenames so the overview navigates to the detail below.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it gives domain-specific procedure, an executable GraphQL query, and a Python snippet without explaining concepts Claude already knows. Guidance such as 'A match built on a vague brief is noise' earns its place rather than padding.	3 / 3
Actionability	Provides fully executable artifacts, a copy-paste Python Gmail-open script, exact filename patterns, URL format, and subject prefixes, hitting the copy-paste-ready anchor.	3 / 3
Workflow Clarity	Phases 0, 1, and 2 are clearly sequenced with explicit checkpoints: a credentials stop in 0a, a critical brief-quality gate in 0b, and the 1d pause for explicit user confirmation before generating emails, giving feedback loops for this batch email operation.	3 / 3
Progressive Disclosure	It is a well-sectioned single file with no nested references, but at roughly 200 lines it keeps the full GraphQL query, email-rule block, and Python script inline rather than splitting them into one-level-deep reference files, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 third-person, specific, and supplies an explicit 'Use when' trigger plus pipeline chaining context, covering what and when clearly. It is concise without fluff and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions, 'Match a qualified lead to Twenty partners and generate all intro emails in one run', matching the anchor for lists of specific concrete actions rather than vague domain mentions.	3 / 3
Completeness	Explicitly answers both what ('Match a qualified lead to Twenty partners and generate all intro emails') and when ('Use when a lead folder exists and you need to find the right implementation partner'), satisfying the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Includes natural phrasing a user would say, 'you need to find the right implementation partner' and 'a lead folder exists', plus 'match' and 'intro emails', giving good coverage of likely user terms.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche (Twenty partner matching) with distinct triggers and named pipeline dependencies, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: twentyhq/twenty
Path: packages/twenty-apps/internal/twenty-partners/src/skills/twenty-partner-match/SKILL.md
Commit: bb4e427

Reviewed: 6 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.