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

84%

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

88%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 skill body is highly actionable with a well-sequenced, validated workflow and an executable code/query scaffold. The main improvement opportunity is splitting the heavier reference material (GraphQL query, email templates) into a referenced file to lift progressive disclosure.

Suggestions

Move the full partners GraphQL query and the per-email templates into a referenced file (e.g. references/partner-api.md and references/email-templates.md) and link to them from SKILL.md to improve progressive disclosure.

Trim editorializing sentences ('A match built on a vague brief is noise', 'Be honest') to tighten conciseness without losing the validation intent.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — it does not explain GraphQL, APIs, or pagination — with only minor over-explanation that could be trimmed ('A match built on a vague brief is noise', 'Be honest'), fitting the 'efficient, minor instances' anchor rather than the fully lean 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: a complete GraphQL query, a Python Gmail script with cross-platform fallback, exact email templates, subject prefixes, file-naming conventions, and URL schemes — covering the common cases, matching the top anchor.	5 / 5
Workflow Clarity	A clear phased sequence (Phase 0/1/2) with explicit validation checkpoints and feedback loops — credential check that stops cleanly, a critical brief-quality gate before querying the API, and a pause-for-confirmation before sending the batch of emails — fitting the top anchor despite this being a batch operation.	5 / 5
Progressive Disclosure	Well-organized single file with clear section headers and no nested references (the chained skill names are workflow pointers, not doc references), but it is a single longer monolithic document with no separate reference files for the GraphQL query or email templates, so it sits at 'good structure, minor organization gaps' rather than the cleanly-split 5.	4 / 5
	Total	18 / 20 Passed

Description

80%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 clearly states both what the skill does and when to use it with concrete trigger guidance, and is distinct from other skills. Its main weakness is reliance on Twenty-internal identifiers over natural user language in the trigger terms.

Suggestions

Add user-natural synonyms to the trigger (e.g. 'Use when you need to find a Twenty implementation partner or agency for a lead') so it fires on how users actually phrase the request.

Lightly enumerate the outputs in the 'what' clause (e.g. 'and generate the client-notification and partner intro emails') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'Match a qualified lead to Twenty partners and generate all intro emails in one run' — with only minor coverage gaps (does not enumerate the email types), fitting the 'several specific actions, minor gaps' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Explicitly answers both 'what' (match lead to partners, generate intro emails) and 'when' ('Use when a lead folder exists and you need to find the right implementation partner') with concrete trigger phrases, fitting the top anchor; it does not drop to 4 because the 'when' is concrete rather than weakly implied.	5 / 5
Trigger Term Quality	Has a relevant natural phrase ('you need to find the right implementation partner') but leans heavily on internal Twenty jargon ('twenty-partner-design-doc', 'partner-match-criteria.md') rather than the synonyms/variations a user would naturally say, matching the 'some relevant keywords but missing common variations' anchor and not the fuller-coverage 4.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (Twenty partner matching) with distinct triggers and minimal overlap risk with other skills, written in third person, matching the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	17 / 20 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: d43ab16

Reviewed: 9 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.