Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Iterate On Logo

ASecurity

Use this skill when Tyler asks to iterate on a logo, run an adversarial critique-fix loop, or says 'critique and fix this until done'. Runs scored critique → targeted SVG fix cycles until no fixable issues remain.

8 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add tstapler/dotfiles --skill iterate-on-logo --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Iterate On Logo?

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

Security grade badge for Iterate On Logo
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tstapler-iterate-on-logo/badge)](https://www.skillsdirectory.com/skills/tstapler-iterate-on-logo)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: iterate-on-logo
description: "Use this skill when Tyler asks to iterate on a logo, run an adversarial critique-fix loop, or says 'critique and fix this until done'. Runs scored critique → targeted SVG fix cycles until no fixable issues remain."
---

# iterate-on-logo — Adversarial Critique-Fix Loop

Invoke with: "adversarially critique [iteration-N] and fix it, loop until done"

No subprocess calls. Execute inline. Read the target SVG first, then cycle.

---

## Scoring Rubric

Score each dimension 1–3. Max 15. A round with no 1s is done.

| Dimension | 1 — Broken | 2 — Acceptable | 3 — Strong |
|---|---|---|---|
| **home_read** | Primary metaphor illegible at 200px | Readable with effort | Instant read |
| **brand_fit** | Off-palette or wrong mood | Correct colors, weak mood | Colors + mood both land |
| **distinctiveness** | Generic icon | Recognizable category | Memorable silhouette |
| **favicon_16px** | Collapses to noise | Survives as silhouette | Distinct at 16px |
| **direction_clarity** | No sense of movement | Implied direction | Unambiguous departure vector |

Score ≥ 12 (all 2s or better): declare done, no further iteration.  
Any dimension at 1: fix it, increment iteration number, loop.  
Max 5 rounds — escalate if still failing after round 5.

---

## Geometry Verification (Sortie road icon)

Before writing any SVG that places elements near the road edges, verify clearance:

**Road edge equation** (viewBox 0 0 512 512, V from (72,472)→(256,164)←(440,472)):
```
left_edge_center(y)  = 72  + 184 * (472 - y) / 308
right_edge_center(y) = 440 - 184 * (472 - y) / 308
road_stroke_width    = 32
left_boundary(y)     = left_edge_center(y)  - 16   ← visible left limit
right_boundary(y)    = right_edge_center(y) + 16   ← visible right limit
```

**Rule**: Any element tip that faces the road must satisfy:
- Left-side elements: tip_x < left_boundary(y) at the element's y
- Right-side elements: tip_x > right_boundary(y) at the element's y

Compute at the y of each arm/element tip before writing the rect.

**Centerline perspective** (scale factor approach):
```
s(y) = (y - 164) / 308          ← 0 at horizon (164), 1 at bottom (472)
dash_length(y)   = 42 * s(y)    ← reference 42px at y≈431
dash_sw(y)       = 14 * s(y)    ← reference sw=14 at y≈431
gap(y)           = 28 * s(y)    ← gap shrinks proportionally
```
Apply at each dash midpoint, working bottom-up (near to far).

**Drawing order** (later = on top):
1. Cacti / background elements
2. Road edge lines
3. Centerline dashes
4. Sun rays
5. Horizon circle (caps ray bases)

---

## Loop Protocol

### Round start

1. Read the current iteration SVG
2. Score all 5 dimensions
3. Print: `Round N — score X/15`
4. List findings: dimension, score, specific pixel/geometry evidence

### Fix step (only if any dimension scored 1)

1. Address the lowest-scoring dimension first
2. Verify geometry before writing (use road edge formula above if applicable)
3. Write the new SVG to `logos/iterations/iteration-{N+1}.svg`
4. Update the "Current direction" section of `logos/preview.html`:
   - Add new card at top with label `{N+1} — [one-line fix description] ★ LATEST`
   - Move prior LATEST card down, drop the ★ LATEST badge
5. State what changed and why in one sentence

### Termination conditions

| Condition | Action |
|---|---|
| All dimensions ≥ 2 | Declare done. Print final score. |
| Round 5 reached with 1s remaining | Escalate — describe what can't be auto-fixed and why |
| Remaining issues require concept change | Stop, present the issue to the user |

---

## File paths (Sortie project)

| Resource | Path |
|---|---|
| Iteration SVGs | `logos/iterations/iteration-N.svg` |
| Preview | `logos/preview.html` |
| Concepts | `logos/concepts/concept-*.svg` |

Attribution

tstaplertstapler
View sourceMore from tstapler →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →