direction-picker

Resolves the visual direction at the plan stage from the brief and design system, without asking the user.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/_official/atoms/direction-picker/SKILL.md

Quality

Content

100%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.

This is a tight, exemplary instruction-only skill body: a three-step fallback order for resolving the visual direction, one concrete executable command, a firm prohibition on delegating the choice to the user, and an explicit completion condition plus anti-patterns. It assumes Claude's competence, wastes no tokens, and contains nothing that belongs in a separate file. No weaknesses found.

Dimension	Reasoning	Score
Conciseness	Every sentence carries operational weight: the resolution order, the one executable command, the hard rule against asking the user, and the completion criterion. There is no padding and no explanation of concepts Claude already knows — matches anchor 5 (lean, every token earns its place).	5 / 5
Actionability	The guidance is fully actionable for an instruction-only skill: a numbered fallback chain with an explicit 'stop here', and a copy-paste-ready command (`"$OD_NODE_BIN" "$OD_BIN" tools directions --id <id>`) for the one case needing a tool call. The scoring note confirms absence of code is not penalized when guidance is this concrete.	5 / 5
Workflow Clarity	The resolution sequence (design system → supplied source → self-inference, with 'stop here' at the first match) is unambiguous, and the Convergence section gives an explicit completion checkpoint ('the plan states the chosen direction'). This is a simple, single-purpose skill under 50 lines with no destructive or batch operations, so the simple-skill exception applies and clarity can score 5.	5 / 5
Progressive Disclosure	The skill is under 50 lines with no external content needed — no bundle files exist (references/, scripts/, assets/ are absent) and the body references none. Sections ('Convergence', 'Anti-patterns') are well-organized and the whole skill fits SKILL.md appropriately, satisfying the no-references simple-skill case for a 5.	5 / 5
	Total	20 / 20 Passed

Description

53%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 is specific, well-scoped, and honest about its single purpose ('without asking the user' is a useful behavioral signal), with a clear 'what'. Its main weakness is the absence of any explicit 'Use when...' trigger guidance and of natural synonym terms, leaving 'when' only weakly implied. It is a solid, concise description that falls just short of the good examples on completeness and trigger coverage.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a plan-stage brief needs a committed visual direction or when the user supplies a brand spec, reference URL, or screenshot.'

Include natural synonym terms users would actually say — 'visual style', 'theme', 'look and feel', 'design direction' — alongside 'visual direction'.

Name one or two more concrete actions, such as 'binds design-system tokens and retrieves direction specifications', to broaden capability coverage.

Dimension	Reasoning	Score
Specificity	The description names its domain ('visual direction at the plan stage') and concrete inputs ('from the brief and design system, without asking the user'), which is more informative than anchor 2's bare domain-naming, but it lists only a single action and no downstream steps (binding tokens, resolving specifications), so it is not comprehensive as anchor 4 requires.	3 / 5
Completeness	The 'what' is clear ('Resolves the visual direction... from the brief and design system, without asking the user'), but there is no 'Use when...' clause or equivalent explicit trigger guidance; 'at the plan stage' only weakly implies when. Per the judging guidelines, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords are present ('visual direction', 'brief', 'design system', 'plan stage'), but common natural variations users would say are missing — e.g. 'style', 'theme', 'look and feel', 'aesthetic'. This matches anchor 3 (some relevant keywords, missing synonyms) better than anchor 4's fuller coverage.	3 / 5
Distinctiveness Conflict Risk	'Visual direction at the plan stage' is a clear niche with distinct triggers, but 'design system' and 'brief' could cause minor overlap with general design or branding skills — anchor 4 (mostly distinct, minor overlap risk) fits better than anchor 5's minimal conflict risk.	4 / 5
	Total	13 / 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: nexu-io/open-design
Path: plugins/_official/atoms/direction-picker/SKILL.md
Commit: 1b47e60

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.