SureForge
SkillAn instruction-only skill that makes agents research before they ask, plan before they build, and verify before they call anything done.
- workflow
- verification
- quality
- skill
Turns Claude — or any agent that supports Agent Skills — into a disciplined identity designer: from brief and optical corrections to the 16 px pixel test, production-ready SVG and brand guidelines, with a 1,400+ real-world SVG logo reference library and dependency-free Python tools (MIT; library logos remain their owners' trademarks)
logo-design-skill is kaankiziltug's open-source logo-design skill (6,415 stars as of writing, 2026-11-10) that turns Claude — or any agent supporting Agent Skills, such as Gemini CLI, Codex CLI, Cursor or GitHub Copilot — into an identity designer with a disciplined process from the first brief to delivery. The process covers discovery and briefs, word mapping, choosing the mark type, concepting, geometric construction, optical corrections (overshoot, bone effect, irradiation and more), colour, typography, lockups, testing, presentation, delivery and redesigns: it drafts 8-12 one-line concepts, builds 3 in SVG, then runs the audit, the 16 px pixel test, one-colour, reversed, squint, mirror and competitor shelf tests, and always stops at the checkpoint — one overview image with a recommendation, and nothing else gets produced until you pick a direction and ask for the kit (colour, lockups, boards, icons, guidelines). The reference library holds 1,400+ real-world SVG logos classified by mark type, technique, geometry, subject, typography, mood and industry — searchable from the command line and browsable in a local gallery — to study construction and avoid look-alikes, never to copy. The tooling is dependency-free Python: audit an SVG against logo principles, build concept overview and test sheets, create client presentation boards with industry mockups, render PNGs and export a full favicon / app-icon / web-manifest set. CI runs a test workflow. Claude Code installs via the plugin marketplace; claude.ai and Claude Desktop take the zip from Releases.
For individuals and teams who need a real identity: one brief in, deliverable SVGs, a full favicon set and brand guidelines out, with tests and a checkpoint at every step. The 1,400+-logo classified library also serves anyone studying logo construction and category conventions.
# Claude Code - plugin marketplace (recommended): /plugin marketplace add kaankiziltug/logo-design-skill /plugin install logo-design@logo-design-skill # Claude Code - manual: git clone https://github.com/kaankiziltug/logo-design-skill.git cp -r logo-design-skill/skills/logo-design ~/.claude/skills/logo-design # claude.ai / Claude Desktop: upload logo-design.zip from Releases under Settings -> Capabilities -> Skills # (size limit? use logo-design-lite.zip - everything except the SVG files) # Gemini CLI: cp -r logo-design-skill/skills/logo-design ~/.gemini/skills/logo-design # Codex CLI: cp -r logo-design-skill/skills/logo-design ~/.codex/skills/logo-design
The MIT license covers skill text, scripts, templates and catalog data only — the logo files in assets/library/svg/ are trademarks of their respective owners, included for reference and education and NOT covered by MIT (see TRADEMARKS.md). The skill works best with a model that can view images, since it renders drafts to PNG and self-checks. The library rewards study but the README is explicit it is never for copying; the example brands in the docs are fictional briefs. claude.ai uploads hitting the size limit should switch to logo-design-lite.zip. MIT. 6,415 stars as of writing (2026-11-10).
Repository
kaankiziltug/logo-design-skillCharted
An instruction-only skill that makes agents research before they ask, plan before they build, and verify before they call anything done.
Guizang's agent skill turns your repo's recent updates into a finished promo video — real components, code-rendered animation, an original code-written soundtrack — no video editor involved.
An agent skill that geolocates a photo with nothing readable in it — OSM geometry, elevation skylines and satellite tiles turn “where was this taken?” into a measured answer with an error radius.