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

60%

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

53%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 concise, well-sectioned, and honest about being a catalogue entry that defers to the upstream bundle, but as guidance it is largely abstract: the OpenDesign orchestration steps give no concrete, executable instructions for the creative-director workflow itself and include no validation checkpoints. It works as a discovery stub, not as a self-contained skill.

Suggestions

Add a minimal concrete workflow for the core capability (e.g., how to run a SCAMPER/TRIZ pass and score concepts on the 3 axes) instead of only generic orchestration steps.

Replace vague directives like "Search across every available OpenDesign resource" with specific, checkable actions or commands.

Include at least one concrete example of the 3-axis evaluation or a calibration checkpoint so the process is verifiable rather than implied.

Dimension	Reasoning	Score
Conciseness	The ~50-line body is lean with no explanations of concepts Claude already knows; the "What it does" section duplicates the description verbatim and the OpenDesign orchestration language is somewhat boilerplate, so a few tokens could be trimmed. Fits anchor 4 rather than 5 (minor redundancy) and clearly above 3 (no genuinely unnecessary explanation).	4 / 5
Actionability	Steps like "Search across every available OpenDesign resource", "Match resources into a staged workflow", and "present a small guided UI-style choice set" are high-level hints; the only executable item is `open https://github.com/smixs/creative-director-skill`. No concrete guidance for actually applying the 20+ methodologies or the 3-axis evaluation, matching anchor 2 rather than 3 (no partially concrete, executable steps exist).	2 / 5
Workflow Clarity	The six numbered orchestration steps form a coherent sequence, but they are generic and lack validation checkpoints or error-recovery loops, and the actual creative workflow (brief → concept → evaluation → presentation) is never sequenced. Anchor 3: sequence present but checkpoints missing or implicit; not 4 because the steps are abstract rather than concrete-with-minor-gaps.	3 / 5
Progressive Disclosure	A single well-sectioned file with clearly labeled sections and a one-level-deep pointer to the upstream repo; no nested reference chains. Anchor 4 rather than 5 because the skill advertises upstream "assets, scripts, and references" that are not bundled or locally navigable, leaving a minor organization gap.	4 / 5
	Total	13 / 20 Passed

Description

66%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 evaluation axes, but it reads as a feature inventory rather than an action-oriented capability statement and lacks any explicit 'use when' trigger guidance, capping completeness. Third-person voice is correct and the length is reasonable.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for campaign concepts, creative critiques, SCAMPER/TRIZ ideation, or Cannes/D&AD-caliber creative evaluation."

Lead with action verbs (e.g., "Generates and critiques campaign concepts using 20+ ideation methodologies...") instead of the noun-phrase feature inventory.

Include a few natural synonyms users would say ("advertising campaign", "brainstorm", "ad copy", "pitch") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Quotes "20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER, Synectics)", "3-axis evaluation calibrated against Cannes/D&AD/HumanKind", and "5-phase process from brief to presentation" — several concrete, named capabilities, though framed as feature inventory rather than actions performed. Not 5 because coverage of concrete actions is incomplete; not 3 because it lists far more than 1-2 specifics.	4 / 5
Completeness	The "what" is clear and specific, but there is no "Use when..." clause or equivalent trigger guidance inside the description (trigger phrases live only in the separate frontmatter triggers field). Per the judging guideline, a missing 'when' caps completeness at 3.	3 / 5
Trigger Term Quality	"creative director", "SCAMPER", "Cannes", "campaign" (in the body/triggers) are natural user phrases, but common variations like "advertising campaign", "brainstorm", "ad copy", or "pitch" are missing. Good coverage with a few natural terms missing, so anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	Named methodologies (SCAMPER, TRIZ, Synectics) and Cannes/D&AD/HumanKind calibration carve a distinct creative-direction niche with minimal conflict risk. Not 5 because "creative director" could still overlap with generic design/critique skills; not 3 because the niche is more specific than 'somewhat specific'.	4 / 5
	Total	15 / 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: 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.