Name: twenty
Rating: 56.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

twenty

Twenty integration. Manage data, records, and automate workflows. Use when the user wants to interact with Twenty data.

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/twenty/SKILL.md

Quality

Content

67%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 content is a strong, executable CLI integration guide with clear sequencing and good connection-state feedback loops. Its main weaknesses are a duplicated actions section, a broken step cross-reference, and minor redundancy that could be tightened.

Suggestions

Remove or merge the "Popular actions" section, which repeats the "Searching for actions" command without adding new examples.

Fix the "skip to Step 2" reference by labeling the install/auth/connect phase as Step 1 and the search/run phase as Step 2, so the cross-reference resolves.

Trim the opening "Twenty is an accounting and bookkeeping platform..." paragraph to one line, since the skill's value is the CLI workflow rather than the product description.

Dimension	Reasoning	Score
Conciseness	The body is mostly commands and practical prose, but the "Popular actions" section duplicates "Searching for actions" above it and the opening platform description adds explanatory padding that could be trimmed, fitting the mostly-efficient-but-could-be-tightened anchor of 3.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands for every phase (install, login, connection ensure/get, action list/run, request with a full flag table), with only minor gaps like unfilled placeholders (CONNECTION_ID, QUERY) and the thin "Popular actions" stub.	4 / 5
Workflow Clarity	The install → authenticate → connect → search → run → proxy sequence is clear, and the connection polling includes explicit state checks and a retry feedback loop (poll again after the user acts); a broken "skip to Step 2" reference and unlabeled 1a keep it just below 5.	4 / 5
Progressive Disclosure	The single SKILL.md is well organized with clear section headers, code blocks, and a flag table, and no external bundle files are referenced or needed; minor inline bulk (the proxy flag table, clientAction detail) keeps it from a perfect 5.	4 / 5
	Total	15 / 20 Passed

Description

62%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 answers both what and when and is anchored to a distinct named product, but its action vocabulary is generic and its trigger phrase set is narrow. Tightening the verbs and adding concrete Twenty-specific triggers would lift the middle dimensions.

Suggestions

Replace generic verbs ("Manage data, records, automate workflows") with concrete Twenty actions such as create/update contacts, deals, tasks, notes, and invoices.

Expand the "Use when" clause with concrete triggers users actually say, e.g. "Use when the user wants to create or update Twenty contacts, deals, tasks, notes, or invoices."

Mention the key record types (Contact, Deal, Task, Note, Invoice) so the description signals the skill's real scope.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the domain plus a few actions, but the actions ("data", "records", "workflows") are generic rather than concrete like the anchor's "extracts content"; it does not reach the several-specific-actions bar of 4.	3 / 5
Completeness	It has both a clear "what" ("Manage data, records, and automate workflows") and an explicit "when" ("Use when the user wants to interact with Twenty data"), matching the both-present-but-trigger-could-be-more-specific anchor of 4 rather than the comprehensive concrete trigger phrases of 5.	4 / 5
Trigger Term Quality	It surfaces "Twenty", "data", and "records" as natural triggers, but coverage is thin — missing common variations a user might say (e.g. invoices, expenses, contacts) beyond the single phrase "interact with Twenty data".	3 / 5
Distinctiveness Conflict Risk	The named brand "Twenty" carves a clear niche with minimal conflict risk, but the generic "manage data, records, workflows" phrasing leaves minor overlap with other data-integration skills, keeping it just below the fully-distinct anchor of 5.	4 / 5
	Total	14 / 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: membranedev/application-skills
Path: skills/twenty/SKILL.md
Commit: f484c82

Reviewed: 3 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.