Skip to main content
ClaudeWave
Skill333 repo starsupdated today

art-direction

The art-direction skill provides frameworks for briefing photographers, illustrators, videographers, and creative teams on specific visual deliverables. Use it when directing creative work that extends an already-approved brand identity into campaigns, photo shoots, illustrations, video, or other branded experiences. It is not for defining brand identity from scratch, writing campaign copy, or establishing project-wide creative strategy.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/rampstackco/claude-skills /tmp/art-direction && cp -r /tmp/art-direction/dist/pi/.agents/skills/art-direction ~/.claude/skills/art-direction
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Art Direction

Direct creative work that extends the brand into specific deliverables. Photography, illustration, video, motion, campaigns, environmental design.

This skill assumes brand identity is approved (`brand-identity` complete). Art direction is about applying and extending it, not defining it.

---

## When to use

- Briefing photographers, illustrators, videographers
- Developing campaign creative concepts
- Directing in-house creative teams
- Writing creative direction documents for vendors
- Evaluating creative deliverables for brand fit
- Adapting brand visual identity to a new format or context

## When NOT to use

- Setting project-wide aesthetic direction across multiple downstream skills (use `creative-direction` instead). This skill briefs specific creative deliverables; `creative-direction` produces the structured aesthetic brief that this skill consumes.
- Defining brand visual identity from scratch (use `brand-identity`)
- Day-to-day component design (use `design-standards`)
- Writing copy for creative work (use `content-and-copy` or `landing-page-copy`)
- Building a design system (use `design-system`)

---

## Required inputs

- The deliverable (photo shoot, illustration set, video, campaign)
- The brand identity (visual system, voice, imagery direction)
- The audience for this specific work
- The goal (brand awareness, conversion, education, emotional connection)
- Budget and timeline
- Distribution context (where it will be seen)

---

## The framework: 5 layers

A creative brief covers five layers. Each must be clear before the brief leaves your hands.

### 1. The story

What this creative work is fundamentally about.

- **The premise.** The core idea in one sentence.
- **The emotional through-line.** What the audience feels.
- **The role of the brand.** How the brand shows up in the story.
- **The takeaway.** What the audience walks away with.

A weak premise produces work that's pretty but says nothing. Spend time here.

### 2. The look

The visual treatment.

**For photography:**
- Subject and composition (close-up, environmental, candid, posed)
- Lighting (natural, studio, dramatic, soft)
- Color palette (true color, treated, monochrome)
- Locations (specific or general direction)
- Wardrobe and props
- Mood references (3 to 5 reference images)

**For illustration:**
- Style (flat, dimensional, hand-drawn, geometric, abstract)
- Color use (full palette, restricted, brand-only)
- Line treatment
- Composition style
- Detail level
- Reference artists or works (with explicit "we want like X but NOT like Y")

**For video / motion:**
- Pacing (slow, medium, fast cuts)
- Camera movement (static, handheld, sweeping)
- Color grading
- Transitions and effects
- Audio direction (music, voiceover, ambient)
- Reference work (3 to 5 examples)

### 3. The execution

Production-level direction.

**Specifications:**
- Deliverable formats and sizes (web hero, social square, print full-page)
- Required shots or frames
- Optional shots if budget allows
- Wardrobe and prop list (for live action)
- Color and asset specs (RGB, CMYK, hex codes for matching)

**Constraints:**
- Things to avoid (specific cliches, forbidden treatments, regulatory)
- Brand-system requirements (logo placement, color use, type rules)

### 4. The variants

How this creative scales across distribution.

Most creative needs to live in multiple places. Plan the variants up front.

**Common variant set for a campaign:**
- Hero web image (16:9 or wider)
- Mobile web hero (4:5 or 1:1)
- Social square (1:1)
- Social vertical (9:16)
- Email banner (3:1 typical)
- Display ad sizes (300x250, 728x90, etc.)
- Print sizes if applicable

For each variant, note: how the composition adapts, what gets cropped or repositioned, what assets are required.

### 5. The standards

The quality bar.

**Technical:**
- Resolution and format requirements
- Color profile
- File naming conventions
- Delivery format (raw + edited, layered files, exported variants)

**Creative:**
- What "approved" looks like (specific examples of acceptable work)
- What "not approved" looks like (specific examples to avoid)
- Number of revision rounds budgeted

---

## Workflow

### For briefing external creative

1. **Confirm the inputs.** Brand identity locked. Audience and goal clear. Budget and timeline known.
2. **Develop the concept.** Premise, emotional through-line, takeaway.
3. **Build the look.** Mood references. Specific direction on style elements.
4. **Write the spec.** Production-level direction. Variants. Constraints.
5. **Brief the vendor.** In writing. Walk through it live. Allow questions.
6. **Review milestones.** Treatment review, halfway review, final review. Don't skip the early reviews; corrections compound.
7. **Approve and document.** What was produced, what's licensed for what use.

### For directing in-house creative

1. **Same brief, lighter format.** In-house direction can be more iterative. Still document the brief.
2. **Co-create.** In-house teams know the brand. Use their judgment. Don't over-direct.
3. **Establish review rhythm.** Daily check-ins for fast work, weekly for longer projects.

### For evaluating existing creative

1. **Score against the brief.** Did the work hit the brief? Where did it deviate?
2. **Score against the brand.** Does this look like the brand? Could this be confused with a competitor?
3. **Score against the goal.** Will this drive the intended outcome?
4. **Identify fixes.** What can be improved? What's a deal-breaker vs. acceptable?

---

## Failure patterns

- **"Modern, clean, minimal" briefs.** Means nothing. Force specificity. Use specific reference brands, named artists, or visual examples.
- **No "what to avoid" direction.** Vendors interpret broadly. Tell them what's out of bounds explicitly.
- **Reference imagery that's actually competitor work.** You'll get something that looks like the competitor. Never use direct competitors as references.
- **Skipping early reviews.** Every revisi
accessibility-auditSkill

Run a comprehensive WCAG accessibility audit covering perceivable, operable, understandable, and robust principles. Use this skill whenever the user wants to audit accessibility, review WCAG compliance, fix accessibility issues, prepare for accessibility certification, address an accessibility lawsuit risk, or systematically improve a site's accessibility. Triggers on accessibility audit, WCAG audit, a11y audit, accessibility compliance, ADA compliance, screen reader test, keyboard navigation, accessibility report, fix accessibility, axe scan. Also triggers when accessibility issues have been reported and need systematic remediation.

ads-creative-developmentSkill

How to produce ad creative that converts at performance scale. Hook patterns, format selection, video pacing, variation systems, sequential testing methodology, fatigue detection, brand-voice alignment without conversion dilution, and platform-specific creative norms. Triggers on ad creative, ad design, hook patterns, ad video pacing, creative testing, ad variations, creative refresh, creative fatigue, refresh ad creative, video ads for Meta, TikTok creative, LinkedIn ad creative, ad asset library. Also triggers when a team is producing creative at scale, planning a creative test cycle, or auditing why creative is not converting.

ads-performance-analyticsSkill

How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media dashboard, attribution analysis, ROAS vs LTV, multi-platform reconciliation, ad incrementality, geo holdout, conversion lift study, ghost bidding, paid media reporting, board-deck paid media metrics, blended CAC, MMM, MTA, last-click attribution. Also triggers when a marketer is about to scale, kill, or rebudget a campaign based on platform metrics, or when reconciling platform reports against warehouse revenue.

after-action-reportSkill

Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event. Triggers on after-action report, AAR, postmortem, retrospective, retro, post-incident review, what went well what didn't, lessons learned, blameless postmortem, root cause analysis, RCA, five whys. Also triggers when the user has just shipped something or just resolved an incident and wants to capture learnings.

ai-content-collaborationSkill

How humans and AI compose in content workflows. Where AI legitimately participates, where humans must own, hybrid workflow patterns, voice ownership preservation, the AI slop problem, disclosure and transparency, team calibration, and the ethics of intellectually honest AI-assisted content production. Triggers on AI content workflow, AI-assisted writing, hybrid content production, AI in editorial, AI slop, AI disclosure, AI usage policy, AI content ethics, voice preservation with AI, team AI calibration. Also triggers when content feels generic despite quality tools, when team AI usage has drifted into inconsistency, or when a regulated or trust-sensitive context requires explicit AI policy.

analytics-strategySkill

Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement. Triggers on analytics strategy, measurement plan, event taxonomy, tracking plan, KPI framework, dashboard design, north star metric, attribution model, conversion tracking, GA4 setup, Mixpanel setup, analytics audit. Also triggers when the user has data but no clear way to use it, or wants to make decisions but doesn't know what to track.

backup-and-disaster-recoverySkill

Plan and run backups, set recovery objectives, and run disaster recovery drills. Use this skill when defining RPO/RTO targets, designing backup architecture, deciding what to back up and how often, planning for full-region or platform outages, or running a restoration drill. Triggers on backup, restore, RPO, RTO, disaster recovery, DR, business continuity, what if the database is gone, what if our hosting goes down, recovery drill, ransomware planning. Also triggers when an incident reveals a gap in restoration capability.

beta-program-managementSkill

Running closed and open betas that produce real signal. Beta participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional feedback loops, clear graduation criteria). Triggers on beta program, alpha test, beta cohort, beta participant, beta feedback, beta to GA decision, design partner, early access program, closed beta, open beta, RC release. Also triggers when a feature is approaching launch and the team needs structured pre-GA validation, when prior betas produced noise rather than signal, or when the team has soft-launched before but wants more structured feedback this time.