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

52%

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

46%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 body is a well-structured catalogue/pointer entry that cleanly externalizes the full workflow to an upstream repo, but as a standalone skill it offers little executable guidance — the orchestration steps are abstract and the only runnable command opens a URL. Workflow sequencing is clear but lacks validation checkpoints.

Suggestions

Replace abstract orchestration hints with concrete, runnable examples (e.g., a sample critique prompt, a sample SCAMPER application) or inline a minimal version of the upstream workflow so the skill is usable without installing the bundle.

Add an explicit validation/checkpoint step to the six-step sequence (e.g., 'Confirm the chosen aesthetic bar with the user before generating assets') to lift workflow clarity.

Tighten the Open Design orchestration section by cutting generic framing ("Define what good-looking means before changing pixels") into terse directive bullets, improving token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with clear sectioning, but the Open Design orchestration steps include some generic, slightly padtable direction ("Define what good-looking means", "Search across every available Open Design resource") that could be tightened.	3 / 5
Actionability	Concrete executable guidance is minimal — essentially one `open https://github.com/...` command — while the core orchestration steps are high-level hints ("Match resources into a staged workflow") rather than specific, runnable instructions, and the real workflow is deferred to an upstream repo.	2 / 5
Workflow Clarity	A clear six-step sequence is present, but it lacks explicit validation checkpoints or feedback loops, and the steps describe what to consider rather than verifiable actions.	3 / 5
Progressive Disclosure	Content is well-organized into clearly labeled sections (What it does, Open Design orchestration mode, Source, How to use) with the detailed workflow correctly externalized to the upstream repo, leaving only minor organization gaps.	4 / 5
	Total	12 / 20 Passed

Description

58%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 and distinctive, naming concrete methodologies and an evaluation framework, but it lacks any explicit 'when to use' trigger guidance, which limits its completeness. Trigger-term coverage is moderate, with the most natural phrases residing in a separate frontmatter list rather than the description itself.

Suggestions

Append an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when the user wants campaign concepts, creative critiques, or Cannes/D&AD-style review') so completeness can exceed 3.

Fold one or two of the most natural trigger terms from the frontmatter list into the description body to improve trigger-term quality.

Clarify the vague phrase 'recursive self-assessment' with a concrete action (e.g., 'scores and re-ranks its own concepts') to lift specificity toward 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ("20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER, Synectics)", "3-axis evaluation calibrated against Cannes/D&AD/HumanKind", "5-phase process from brief to presentation") with only minor abstraction gaps around 'recursive self-assessment'.	4 / 5
Completeness	Provides a clear 'what' (creative director with self-assessment, methodologies, evaluation, 5-phase process) but no 'Use when...' or equivalent explicit 'when' guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Contains some relevant natural terms a creative user might say ("creative director", "brief", "presentation", "Cannes", "SCAMPER") but misses common variations and synonyms, and the strongest trigger phrases live in the separate triggers list rather than the description.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear, fairly narrow niche (award-calibrated creative direction) with named methodologies that distinguish it from generic design/critique skills, with only minor overlap risk.	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: nexu-io/open-design
Path: skills/creative-director/SKILL.md
Commit: 1a7a23d

Reviewed: about 5 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.