Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Logo And Visual System Direction

ASecurity

Direct the visual identity: author the anti-slop creative brief for generative-web-media (setting indemnity_required), run the human-curation + documented-human-authorship gates, and spec the logo suite (lockups/clear-space/min-size/mono/B&W), color roles with WCAG-AA pairs, and type with web-license class. Refuses without a strategy brief. The curated vector is the deliverable — never regenerated in Firefly.

7 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsgosecurity

Works with

cli

Security Analysis

A100/100

Scanned 9/23/2026

$npx -y skills add mcorbett51090/RavenClaude --skill logo-and-visual-system-direction --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Logo And Visual System Direction?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Logo And Visual System Direction
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mcorbett51090-logo-and-visual-system-direction/badge)](https://www.skillsdirectory.com/skills/mcorbett51090-logo-and-visual-system-direction)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: logo-and-visual-system-direction
description: "Direct the visual identity: author the anti-slop creative brief for generative-web-media (setting indemnity_required), run the human-curation + documented-human-authorship gates, and spec the logo suite (lockups/clear-space/min-size/mono/B&W), color roles with WCAG-AA pairs, and type with web-license class. Refuses without a strategy brief. The curated vector is the deliverable — never regenerated in Firefly."
---

# Logo & Visual System Direction

This is where strategy becomes a visual system — by **directing** the generators, **curating** ruthlessly with
a human, and **specifying** the logo/color/type system. This plugin is thin: it authors the brief and sets the
indemnity flag; `generative-web-media` runs generation and picks the provider per-asset; `web-design` builds
the tokens. The value here is direction + curation, not raw pixels.

> **Two hard gates live in this skill.** (1) **strategy-before-visuals** — refuse if no `brand-strategy-brief.md`
> exists. (2) **documented-human-authorship** — a human must select and log a substantial modification before a
> concept becomes a deliverable. The **curated vector is the deliverable and is NEVER regenerated in Firefly**.
> Every font-license/IP claim routes to `security-reviewer`. Prices `[unverified]`.

## Workflow

1. **Gate: strategy exists.** No `brand-strategy-brief.md` → stop, route to `brand-strategist`.
2. **Author the generation brief (the seam).** Fill
   [`../../templates/creative-brief-for-generative-media.md`](../../templates/creative-brief-for-generative-media.md)
   — one brief per `request_kind`. Set `indemnity_required: true` for client-facing/resold assets. Do **not**
   name a provider — media's license gate chooses per-asset.
3. **Generate breadth (or fall back).** Hand the brief to `generative-web-media`. **If it is not installed,**
   emit the brief as a **copy-paste prompt-pack** (below) so the engagement is never blocked.
4. **Gate: human curation + authorship.** A human selects; log the selection **and a substantial human
   modification/arrangement** in [`../../templates/curation-and-authorship-log.md`](../../templates/curation-and-authorship-log.md).
5. **Spec the logo suite, color system, type system** (below), validating WCAG pairs with the runnable checker.
6. **Hand off** to `brand-book-assembly` (compile) and, for tokens, to `web-design:design-tokens-scaffolding`.

## Anti-slop brief authoring

The model defaults to a "legible middle" that reads as slop. Escape it with **specific** constraints:

- **Positive constraints:** "identifiable in one flat color", "reads at 16px favicon size", "geometric sans
  wordmark", "the mark works without the wordmark".
- **Negative constraints:** "no gradient mesh", "no generic swoosh/globe", "avoid the #-blue SaaS palette",
  "not a literal picture of the product".
- **Reference-anchored intent:** "like Stripe's restraint but warmer" beats "modern and clean".
- **Bulk `count`:** generate many; the human curates. Exploration is cheap; refinement is human.

### Prompt-pack fallback (when generative-web-media is absent)

If `generative-web-media` is not installed, render the brief's `intent` + `constraints` + `negative_constraints`
as a numbered prompt list the operator pastes into a vector-capable generator (Recraft/Ideogram class for
logos/wordmarks). **Carry the indemnity note forward** ("client-facing/resold — use an IP-indemnified provider
for imagery; keep the curated vector as the deliverable"), and record `provider` + `license_class` manually in
the authorship log. Never substitute a Firefly regen for the curated vector.

## Logo suite spec (the gold deliverable)

| Variant | Requirement |
|---|---|
| Primary lockup | The default mark + wordmark relationship |
| Secondary / stacked | For constrained widths |
| Mark alone | Works without the wordmark (app icon, favicon) |
| Wordmark alone | Typographic, no mark |
| Clear-space | Defined in terms of a mark-derived unit (e.g. cap-height) |
| Min-size | Smallest legible size, per medium (px for web, mm for print) |
| Mono / one-color | A single flat color version |
| Reversed / B&W | Legible knocked-out on dark and in pure B&W |
| Do / don't gallery | The specific misuses to forbid (stretch, recolor, re-spacing, drop-shadow) |

**True vector (SVG)** is the format; the mark must be **identifiable in B&W** (the acid test of a real mark
vs a gradient-dependent picture).

## Color system spec

- **Roles, not just swatches:** primary / secondary / accent / neutrals (a full neutral ramp).
- **Per color:** HEX + RGB + OKLCH (and CMYK if print is in scope).
- **WCAG pairs — validated, not asserted.** Run [`../../scripts/check-brand-a11y.py`](../../scripts/check-brand-a11y.py)
  on the text/background + accent + UI/focus pairs. AA floor: 4.5:1 normal text, 3:1 large text, 3:1 UI/focus.
  **A primary text pair under 4.5:1 fails the handoff** — fix the palette, don't ship the debt.
- Hand the role/value decisions to `web-design:design-tokens-scaffolding`; do not build the token pipeline here.

## Type system spec

- Families (display / text / mono) + a modular scale + pairing rules + weights actually loaded.
- **Explicit web-license class per family** in [`../../templates/font-license-tracker.md`](../../templates/font-license-tracker.md).
  OFL/Apache self-host is preferred. A **non-self-hostable** font (Adobe Fonts embed-only, Monotype
  pageview-metered) is **blocked from the token export** — see `brand-legal-and-licensing`.

## Anti-patterns

- Generating visuals before the strategy brief exists.
- A "modern/clean/professional" brief (the slop prompt) instead of specific + negative constraints.
- Treating a Firefly regeneration as the "final" logo — it discards the human curation the value rests on.
- A logo that dies in one color or B&W (gradient-dependent = not a mark).
- Shipping a palette whose contrast was eyeballed, not validated.
- Recording a font family with no web-license class.

## See also

- Template (the seam): [`../../templates/creative-brief-for-generative-media.md`](../../templates/creative-brief-for-generative-media.md)
- Template: [`../../templates/curation-and-authorship-log.md`](../../templates/curation-and-authorship-log.md)
- Script: [`../../scripts/check-brand-a11y.py`](../../scripts/check-brand-a11y.py)
- Best-practices: [`../../best-practices/curate-the-vector-dont-regenerate-it.md`](../../best-practices/curate-the-vector-dont-regenerate-it.md),
  [`../../best-practices/color-systems-need-wcag-pairs-not-just-hex.md`](../../best-practices/color-systems-need-wcag-pairs-not-just-hex.md)
- Skill: [`../brand-legal-and-licensing/SKILL.md`](../brand-legal-and-licensing/SKILL.md)

Attribution

mcorbett51090mcorbett51090
View sourceSee grades on GitHubMore from mcorbett51090 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →