Generate Instagram image ad concepts with visual descriptions, copy constraints (125/40/30 chars), and HTML mockups. Visual-first, mobile-native single-image ads for Feed and Stories.
73
58%
Does it follow best practices?
Impact
100%
1.56xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./creative-skills/multi-channel-ad-ideation/channels/instagram/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, specific description that clearly communicates the skill's capabilities with concrete details like character limits and ad formats. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The domain-specific terminology makes it highly distinctive.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks to create Instagram ads, social media ad creatives, or IG sponsored content for Feed or Stories.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generating ad concepts, visual descriptions, copy constraints with exact character limits (125/40/30), and HTML mockups. Also specifies formats (Feed and Stories). | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions and constraints, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. Per rubric guidelines, this caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'Instagram', 'image ad', 'ad concepts', 'Feed', 'Stories', 'HTML mockups', 'copy constraints', and 'mobile-native'. These cover the domain well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the combination of Instagram, single-image ads, specific character constraints (125/40/30), Feed/Stories formats, and HTML mockups creates a very clear niche unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is comprehensive but severely over-engineered for its purpose. It contains extensive general design knowledge (composition rules, color psychology, typography best practices) that Claude already knows, inflating the token cost significantly. The core workflow (Phase 1 table concepts → Phase 2 HTML mockups) is reasonably clear, but the actionable content is buried under layers of advisory material that should either be in reference files or omitted entirely.
Suggestions
Cut sections Claude already knows: 'The Instagram Advantage', 'Composition Approaches', 'Color Palette Guidance', 'Typography on Images', 'Visual Styles', and 'Common Pitfalls' — these are general design knowledge. Keep only Instagram-specific constraints (character limits, CTA button options, image specs).
Remove the inline HTML template since you already reference `../references/html-preview-templates.md` — or remove the reference and keep only the inline version, but don't duplicate.
Add explicit character count validation steps: after generating concepts, verify each field meets 125/40/30 limits before presenting to user, with a retry loop if any exceed limits.
Move 'Image Concept Development' and 'Visual Styles' sections to a separate reference file (e.g., `instagram-visual-guide.md`) and link to it, reducing the main skill to under 150 lines focused on the generation workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Explains basic concepts Claude already knows (what Instagram is, what mobile-native means, what Rule of Thirds is, color psychology basics). Sections like 'The Instagram Advantage', 'Visual Styles', 'Color Palette Guidance', 'Composition Approaches', and 'Common Pitfalls' are largely general knowledge that wastes tokens. The full HTML template is inlined despite referencing an external template file. | 1 / 3 |
Actionability | The table format example and HTML template are concrete and copy-paste ready, and the Phase 2 workflow has specific tool calls. However, much of the content is descriptive best practices rather than executable instructions. The copy constraint examples are helpful but the composition/color/typography sections are advisory rather than actionable. | 2 / 3 |
Workflow Clarity | Phase 1 → Phase 2 workflow is clearly sequenced with explicit triggers for when to generate HTML. The HTML generation workflow has numbered steps including file writing and preview opening. However, there's no validation step for character count compliance (just 'validated internally but not shown'), and no error recovery if the mcp tool call fails or if the image file isn't found in the expected format. | 2 / 3 |
Progressive Disclosure | References `../references/html-preview-templates.md` for HTML templates but then includes the full HTML template inline anyway, defeating the purpose. Massive amounts of reference material (composition approaches, color palettes, visual styles, typography best practices, image specifications) are all inlined rather than split into reference files. The multi-channel integration context is well-structured but adds significant length. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- treasure-data/td-skills
- Commit
79bb9b8
- Reviewed
Table of Contents
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.