logo-design-board
Skill18 starsChanged 8 days agoMITView on GitHub
Use when creating, critiquing, or iterating logo and brand-mark concepts through a designer-distillation board, including brand intake, public-source designer lenses, concept territories, visual prompts, and logo quality scoring.
In this repository55 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ax-extract-workflowSkill
- conversation-json-to-mdSkill
- feature-doc-splitterSkill
- frontend-quality-guardrailsSkill
- git-commit-onlySkill
- git-pushing-fastSkill
- git-push-secondary-merge-primarySkill
- git-stepwise-commitSkill
- git-weekly-reportSkill
- linkedinSkill
- mac-software-storage-cleanupSkill
- multi-lang-readmeSkill
- novel-writerSkill
- react-component-hook-guidelinesSkill
- routerbase-api-integrationSkill
- routerbase-media-generationSkill
- routerbase-model-routingSkill
- topic-bookmarks-reorganizerSkill
- tree-ring-memorySkill
- tweetclaw-twitter-automationSkill
- ui-layout-analyzerSkill
- wechat-theme-extractorSkill
- weixin-article-to-obsidianSkill
- xquik-dataSkill
- x-twitter-scraperSkill
- yuque-lakebook-exportSkill
- ax-extract-workflow-cnSkill
- conversation-json-to-md-cnSkill
- feature-doc-splitter-cnSkill
- frontend-quality-guardrails-cnSkill
- git-commit-only-cnSkill
- git-pushing-fast-cnSkill
- git-push-secondary-merge-primary-cnSkill
- git-stepwise-commit-cnSkill
- git-weekly-report-cnSkill
- linkedin-cnSkill
- logo-design-board-cnSkill
- mac-software-storage-cleanup-cnSkill
- multi-lang-readme-cnSkill
- novel-writer-cnSkill
- react-component-hook-guidelines-cnSkill
- routerbase-api-integration-cnSkill
- routerbase-media-generation-cnSkill
- routerbase-model-routing-cnSkill
- topic-bookmarks-reorganizer-cnSkill
- tree-ring-memory-cnSkill
- tweetclaw-twitter-automation-cnSkill
- ui-layout-analyzer-cnSkill
- wechat-theme-extractor-cnSkill
- weixin-article-to-obsidian-cnSkill
- xquik-data-cnSkill
- x-twitter-scraper-cnSkill
- yuque-lakebook-export-cnSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. About 0 are common, 15 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈15
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use this skill to turn a brand brief into original logo directions through a compact designer board: public-source designer lenses, brand …
- Distinctive: line 12
Treat designer distillation as a method for extracting decision criteria, not as impersonation.
- Distinctive: line 16
Use this skill when the user wants to:
- Distinctive: line 20
Use distilled design thinking from public designers or studios to guide logo decisions.
- Distinctive: line 26
Do not use this skill as the primary workflow for:
- Distinctive: line 54
Ask at most three targeted questions when missing details would change the design direction.
- Distinctive: line 55
If the user wants speed, proceed with explicit assumptions and mark them as assumptions.
- Distinctive: line 56
Do not ask for a questionnaire when the brief is already enough to start.
- Distinctive: line 63
Add one optional lens only when useful:
- Distinctive: line 69
Use user-provided sources first: books, interviews, portfolios, talks, case studies, notes, or screenshots.
- Distinctive: line 70
If the user names a specific living or current designer and accuracy matters, gather current public sources before distilling.
- Distinctive: line 96
Create a table with each lens as a row and each concept as a column.
- Distinctive: line 98
Remove concepts that fail small-size recognition, one-color use, or category distinction.
- Distinctive: line 99
Use the rubric reference to score finalists when the user needs a recommendation.
- Distinctive: line 110
Use this structure for a full logo request:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Logo Design Board
Overview
Use this skill to turn a brand brief into original logo directions through a compact designer board: public-source designer lenses, brand strategy, concept generation, critique, scoring, and production handoff.
Treat designer distillation as a method for extracting decision criteria, not as impersonation. Never copy a designer's work, a client logo, or a protected mark.
When to Use
Use this skill when the user wants to:
- Design a logo, brand mark, wordmark, monogram, app icon, favicon, or visual identity direction.
- Turn project background, product positioning, or founder notes into logo concepts.
- Use distilled design thinking from public designers or studios to guide logo decisions.
- Compare logo directions, critique a generated mark, or improve a rough symbol.
- Produce image-generation prompts, vector construction notes, and brand-guide starter notes for a logo concept.
Do not use
Do not use this skill as the primary workflow for:
- Legal trademark clearance, infringement opinions, or final IP approval.
- Copying an existing logo, designer style, brand system, mascot, or protected character.
- General poster, illustration, landing-page, UI, or marketing image work where logo identity is not the core task.
- Producing final production files without human review, vector cleanup, optical correction, and legal checks.
Instructions
For full logo work, read both references before producing final recommendations:
references/designer-lens-framework.md: use when choosing or distilling designer lenses.references/logo-quality-rubric.md: use before scoring concepts or selecting finalists.
For small critique requests, use the workflow below directly and load the rubric reference only if a scored recommendation is needed.
Workflow
- Establish the brand brief:
- Brand or product name.
- Category and target audience.
- Core promise in one sentence.
- Brand personality with tensions, such as precise but warm, premium but approachable, playful but credible.
- Competitors and category visual codes.
- Required uses: app icon, favicon, website header, social avatar, packaging, merch, print, signage, or motion.
- Constraints: words that must appear, initials, symbols to avoid, color restrictions, cultural or accessibility constraints.
- Fill gaps conservatively:
- Ask at most three targeted questions when missing details would change the design direction.
- If the user wants speed, proceed with explicit assumptions and mark them as assumptions.
- Do not ask for a questionnaire when the brief is already enough to start.
- Set the designer board:
- Default board:
- Paul Rand lens: idea-led simplicity, memorable symbols, wit without clutter.
- Massimo Vignelli lens: discipline, grid, reduction, timeless systems, typographic restraint.
- Paula Scher lens: expressive typography, cultural energy, scale, attitude, category presence.
- Add one optional lens only when useful:
- Saul Bass for narrative symbols, motion-friendly silhouettes, and cinematic reduction.
- Michael Bierut for client context, implementation systems, and real-world usage ecology.
- Label these as public-method lenses. Do not claim to speak for the real person.
- Default board:
- Distill or adapt the lenses:
- Use user-provided sources first: books, interviews, portfolios, talks, case studies, notes, or screenshots.
- If the user names a specific living or current designer and accuracy matters, gather current public sources before distilling.
- Extract principles, recurring judgments, red flags, and design questions. Avoid extracting only surface style.
- Reject any lens that only produces a visual costume rather than design decisions.
- Define the logo strategy:
- State the logo's job: what it must signal, where it must work, and what it must avoid.
- Identify the category code to borrow and the category code to break.
- Convert vague adjectives into designable tensions.
- Decide whether the strongest route is a wordmark, monogram, pictorial symbol, abstract mark, mascot-like icon, or flexible identity system.
- Generate concept territories:
- Produce three to five directions, not one generic logo.
- For each direction include:
- Name of the territory.
- Strategic thesis.
- Mark type.
- Visual construction in plain language.
- Typography direction.
- Color direction and one-color behavior.
- Which designer lenses support it and which challenge it.
- Image-generation prompt for rough exploration.
- Vector construction notes for redrawing.
- Main risks and how to test them.
- Prompts must request original marks, flat/vector-friendly forms, simple geometry, clean edges, and no imitation of existing logos.
- Critique like a board:
- Create a table with each lens as a row and each concept as a column.
- Separate praise, risk, and required revision.
- Remove concepts that fail small-size recognition, one-color use, or category distinction.
- Use the rubric reference to score finalists when the user needs a recommendation.
- Prepare handoff:
- Recommend one or two finalists and explain the tradeoff.
- Provide final prompt language for image exploration.
- Provide vector redrawing notes, including grid, stroke, negative space, and optical correction concerns.
- Provide usage tests: 16 px favicon, 32 px app icon, 120 px social avatar, website header, black on white, white on black, grayscale, print, embroidery or stamp when relevant.
- State that raster output is concept art; final delivery requires vector cleanup and trademark search.
Output Format
Use this structure for a full logo request:
## Brand Read
[brief synthesis and assumptions]
## Designer Board
[selected lenses and why]
## Strategy
[logo job, category code, design tension]
## Concept Territories
[3-5 directions with prompts and vector notes]
## Board Critique
[lens-by-concept critique table]
## Recommendation
[top 1-2 directions, scoring summary, next iteration]
## Handoff
[prompt, vector notes, usage tests, legal/IP caveat]Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

