CtrlK
BlogDocsLog inGet started
Tessl Logo

twenty-record-presentation

Retrieve and present Twenty CRM records as readable summaries or tables, using the connected Twenty MCP server to discover fields, fetch relevant data, format dates and values, build record links, and avoid raw API output.

57

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/twenty-claude-skills/skills/twenty-record-presentation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

A well-structured, highly actionable presentation skill with concrete examples and Twenty-specific conventions throughout. It is held back by some over-specified markdown formatting detail, no explicit validation checkpoints in the retrieval workflow, and all content being inline rather than progressively disclosed.

Suggestions

Tighten the Table Alignment section by dropping the markdown marker syntax explanation and consolidating the favicon/icon bullets to the cases that actually matter.

Move the Field Labels mapping and detailed date/Table Alignment rules into a reference file (e.g. references/formatting.md), keeping SKILL.md focused on the retrieval workflow and response shape.

Add an explicit verification step in the Retrieval Workflow, e.g. confirm retrieved records match the requested filter/sort before formatting the response.

DimensionReasoningScore

Conciseness

Most of the body is efficient and Twenty-specific (link paths, label mappings, date policy), but the Table Alignment section over-specifies markdown alignment marker syntax (':---', '---:', ':---:') and favicon/icon handling that Claude already knows and could be tightened.

2 / 3

Actionability

It provides concrete, copy-ready guidance: the exact show-page path '/object/:objectNameSingular/:objectRecordId', field-label mappings ('createdAt' → Created), date-format examples, money formatting (EUR 12,450), and complete table/labeled-block examples with realistic data. As an instruction-only skill, the absence of code is not penalized because the guidance is highly actionable.

3 / 3

Workflow Clarity

The Retrieval Workflow gives a clear ordered sequence ('learn_tools → execute_tool', discover-then-retrieve) with sensible edge-case handling (missing context, no MCP server), but there are no explicit validation checkpoints between retrieval and presentation, matching the 'sequence present but checkpoints missing or implicit' anchor.

2 / 3

Progressive Disclosure

The body is well-organized into clear sections with a leading Overview, but all content is inline with no external references; at ~155 lines, reference-style detail (Field Labels mapping, Table Alignment rules, date examples) could be split into reference files, matching 'content that should be separate is inline'.

2 / 3

Total

9

/

12

Passed

Description

67%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.

A specific, well-scoped capability statement for Twenty CRM record presentation with strong action specificity and distinctiveness. Its main weakness is the absence of an explicit 'Use when...' trigger clause and limited coverage of natural user phrasings.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to show, list, look up, or export Twenty CRM records, or wants records presented as readable summaries or tables.'

Add natural user phrasings ('show', 'list', 'display', 'export') alongside 'retrieve and present' to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'discover fields, fetch relevant data, format dates and values, build record links, and avoid raw API output' — matching the 'lists multiple specific concrete actions' anchor. It uses third-person imperative voice ('Retrieve and present...') with no first/second person, so no specificity penalty applies.

3 / 3

Completeness

The 'what' is strong and explicit, but there is no 'Use when...' clause or equivalent explicit trigger guidance; the 'when' is only implied, which per the judging guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

It contains relevant natural terms ('Twenty CRM records', 'readable summaries', 'tables'), but is framed around capabilities rather than the phrasings users actually say, missing common variations like 'show', 'list', 'display', or 'export' my records.

2 / 3

Distinctiveness Conflict Risk

It is tightly scoped to 'Twenty CRM records' and 'the connected Twenty MCP server', a clear named-product niche with distinct triggers unlikely to conflict with other skills.

3 / 3

Total

10

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
twentyhq/twenty
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.