Bootstrap the initial CONTEXT.md glossary for a repository through deep multi-agent codebase exploration and a short sharpening interview, then lazily offer ADRs for load-bearing decisions surfaced along the way. Use when starting work in a repository that has no CONTEXT.md, when seeding the documentation layer that grill-with-docs and improve-codebase-architecture rely on, or when asked to initialize, bootstrap, or seed domain documentation.
Safely bump repository dependencies — discover manifests via parallel sub-agents, baseline build/typecheck/tests, anchor latest versions to the internet (never guess, never downgrade), present a gated plan, apply one bump at a time on a fresh branch, validate after each, and auto-resolve source-only regressions (never modifying tests, hard stop on test-framework breakage). Use when user wants to upgrade packages, runtimes, or Docker base images safely. Triggers include "bump deps", "upgrade dependencies", "safely update packages", "/bump-deps".
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Compact the current conversation into a handoff document for another agent to pick up.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Personal Claude Code skills, organised
into category buckets. Claude Code only discovers skills one level deep
(~/.claude/skills/<name>/SKILL.md), so scripts/link-skills.sh flattens the buckets
into symlinks there. See CLAUDE.md for the full convention.
Your own machine (skills load un-namespaced as personal skills):
git clone https://github.com/Pixxle/skills.git ~/repos/skills
~/repos/skills/scripts/link-skills.sh
Anywhere else (installs as a namespaced plugin from .claude-plugin/plugin.json):
npx skills@latest add Pixxle/skills
Run scripts/list-skills.sh to see everything, grouped by bucket.
CONTEXT.md glossary, then offer ADRs.npx claudepluginhub pixxle/skillsUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.