creative-director

AI creative director with recursive self-assessment: 20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER, Synectics), 3-axis evaluation calibrated against Cannes/D&AD/HumanKind, 5-phase process from brief to presentation.

Quality

55%

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 ./skills/creative-director/SKILL.md

Quality

Content

42%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-structured as a catalogue entry with clean progressive disclosure, but it advertises an upstream skill rather than instructing Claude how to perform the creative-director task, leaving the orchestration guidance abstract and non-executable. Embedding at least minimal concrete steps or examples would materially raise actionability.

Suggestions

Add concrete, executable guidance for the core task (e.g., a minimal critique rubric, an example prompt, or a sample 5-phase walkthrough) instead of only describing the orchestration at a high level.

Include explicit validation/verification checkpoints in the orchestration steps (e.g., 'confirm the aesthetic bar is defined before generating assets') to lift workflow clarity.

Tighten the orchestration directives into terse imperatives and drop the circular 'How to use' framing to push conciseness toward level 3.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with well-organized sections and no padded concept explanations, but the orchestration steps are abstract directives and the 'How to use' section is somewhat indirect, so it is not the fully lean level 3.	2 / 3
Actionability	Guidance is abstract ('Search across every available Open Design resource', 'Match resources into a staged workflow', 'present a small guided UI-style choice set') with no executable code, commands, or concrete examples; the only actionable line opens a GitHub URL, matching the 'describes rather than instructs' anchor.	1 / 3
Workflow Clarity	Six numbered steps give a clear sequence for the orchestration mode, but there are no explicit validation checkpoints or feedback loops and the checkpoints are only implicit, landing it at level 2.	2 / 3
Progressive Disclosure	The body is a concise overview that points one level out to the upstream README/bundle via a single URL, with no nested local references and well-organized sections; consistent with the absent local bundle, matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	8 / 12 Passed

Description

67%

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 and well-differentiated, but it leans on methodology jargon for trigger terms and omits an explicit 'Use when...' clause, which caps its completeness. Adding natural user-facing triggers and a when-to-use sentence would lift the two weaker dimensions.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger situations, e.g. 'Use when the user wants campaign concepts, creative critiques, or award-caliber ad reviews.'

Soften the methodology jargon with terms users actually say ('ad campaign', 'creative concept', 'campaign critique') alongside SIT/TRIZ/SCAMPER.

Lead with the user-facing outcome before the methodology list so the trigger terms read more naturally.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and a named methodology set ('recursive self-assessment', '3-axis evaluation calibrated against Cannes/D&AD/HumanKind', '5-phase process from brief to presentation'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly answers 'what' but has no 'Use when...' or equivalent explicit when-clause, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Most terms are methodology jargon ('SIT, TRIZ, Bisociation, SCAMPER, Synectics') rather than natural user phrasing; it has some relevant keywords but misses common variations a user would actually say, so it is not the full-coverage level 3.	2 / 3
Distinctiveness Conflict Risk	A clear niche (AI creative direction with named methodologies and award-show calibration) with distinct triggers makes it unlikely to fire for the wrong skill, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 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: skills/creative-director/SKILL.md
Commit: f2760fd

Reviewed: about 15 hours 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.