twenty-partner-design-doc

Use when turning a qualified Twenty lead — a call-summary brief plus any client braindump/docs — into a partner brief a partner can scope and quote from. Trigger when pointed at a lead folder (e.g. partners-experience/<LEAD>/) and asked to "draft a design doc", "create a partner brief", "translate this into Twenty terms", "scope this for a partner", or "prep the partner handoff". Default output is zero-inference (only what the client said; empty sections get a placeholder). Pass --full for inference mode. Chains after twenty-lead-intro-call-summary.

Quality

80%

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

66%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 wrapper has a strong, well-validated workflow and good tool-level actionability, but it is undermined by missing bundle files: the doctrine that holds the actual 12-section structure and rules, plus the worked example, are referenced but not shipped, leaving the skill non-executable as bundled. Step 7 is also overloaded and would benefit from being split into a checklist.

Suggestions

Ship design-doc-doctrine.md (and the referenced worked example) in the bundle — e.g. under references/ — or inline the 12-section structure and rules so the skill is executable as distributed.

Break the Step 7 self-check run-on into an explicit bulleted/checkboxed checklist so each failure condition (em dash, bare ~, stray emoji, Source column, bare §N, etc.) is scannable instead of buried in prose.

Convert the 'See <section> in design-doc-doctrine.md' pointers into real relative links (e.g. [Default behavior](references/design-doc-doctrine.md#default-behavior)) once the file exists, so navigation is verifiable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no basic-concept padding, tight Inputs/Modes sections — but Step 7 is a single overloaded run-on enumerating many self-check conditions that could be split into a checklist, keeping it just below the 5 anchor.	4 / 5
Actionability	Gives concrete tooling ('use WebFetch', 'use AskUserQuestion', 'textutil -convert txt', save paths, partner-match-criteria table columns), but the core drafting guidance — 'Draft the doc in the doctrine's 12-section structure, applying every rule in the doctrine' — defers to design-doc-doctrine.md, which is not present in the bundle, so the substantive instructions are incomplete as shipped.	3 / 5
Workflow Clarity	Eight clearly sequenced steps with explicit validation checkpoints and feedback loops — Step 4 'verify load-bearing claims live' via WebFetch, Step 7 self-check with explicit failure/warning conditions — satisfying the validation requirement for batch/document operations and matching the 5 anchor.	5 / 5
Progressive Disclosure	The design is sound — the body is a wrapper that delegates the doctrine to design-doc-doctrine.md with clear one-level signaling ('lives in design-doc-doctrine.md in this folder. Read it and follow it.') — but neither design-doc-doctrine.md nor the referenced worked example partners-experience/TSF/2026-05-26-tsf-design-doc.md exist in the bundle, so navigation leads to dead ends.	2 / 5
	Total	14 / 20 Passed

Description

95%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.

A high-quality description: it states a specific transformation, gives explicit trigger conditions with multiple natural phrases, defines default vs --full behavior, and names its chain predecessor. The only minor gap is that the 'what' is essentially one transformation with modes rather than a list of distinct actions.

Dimension	Reasoning	Score
Specificity	Names concrete operational specifics — 'turning a qualified Twenty lead ... into a partner brief', 'zero-inference', 'Pass --full for inference mode', 'Chains after twenty-lead-intro-call-summary' — but the core is one transformation with two modes rather than many distinct actions, so it sits just below the comprehensive 5 anchor.	4 / 5
Completeness	Explicitly answers both 'what' (turn a lead into a partner brief; zero-inference default; --full inference mode) and 'when' ('Use when turning ...', 'Trigger when pointed at a lead folder ... and asked to ...') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Lists natural phrases a user would actually say — 'draft a design doc', 'create a partner brief', 'translate this into Twenty terms', 'scope this for a partner', 'prep the partner handoff' — with strong synonym coverage matching the comprehensive 5 anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear Twenty-specific niche — 'Twenty lead', 'partner brief a partner can scope and quote from', named chaining to 'twenty-lead-intro-call-summary' — with minimal overlap risk against generic skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: twentyhq/twenty
Path: packages/twenty-apps/internal/twenty-partners/src/skills/twenty-partner-design-doc/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.