Topic: anthropic
9,221 skills in this topic.
-
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
vibeeval/vibecosystem 458
-
recall-reasoning
Search past reasoning for relevant decisions and approaches
vibeeval/vibecosystem 458
-
server-components
React Server Components, Suspense boundaries, streaming SSR, partial prerendering patterns for Next.js App Router.
vibeeval/vibecosystem 458
-
art-director
AI art direction system. Claude directs image generation models (Gemini, DALL-E, Flux) via structured prompts. Generate banners, diagrams, logos, screenshots, and social media visuals without leaving the terminal.
vibeeval/vibecosystem 458
-
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
vibeeval/vibecosystem 458
-
test
Comprehensive testing workflow - unit tests ∥ integration tests → E2E tests
vibeeval/vibecosystem 458
-
convergence
Problem-solving strategies for convergence in real analysis
vibeeval/vibecosystem 458
-
content-marketing
Icerik pazarlama ve SEO odakli yazi uretimi. AI slop temizleme (30+ pattern), icerik kalite skorlama (5 boyut), watermark temizleme, copywriting formulleri (AIDA, PAS, BAB), programmatic SEO ve icerik stratejisi.
vibeeval/vibecosystem 458
-
build
Workflow orchestrator that chains existing skills for feature development
vibeeval/vibecosystem 458
-
skill-evolution
Self-evolving skill system. Skills are scored after execution (0-100) on 5 dimensions. Score 90+ over 5 runs = crystallized (locked). Score below 30 = auto-repair attempted. Skills improve themselves through usage feedback.
vibeeval/vibecosystem 458
-
learn
vibeeval/vibecosystem 458
-
pint-compute
Unit-aware computation with Pint - convert units, dimensional analysis, unit arithmetic
vibeeval/vibecosystem 458
-
help
Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available
vibeeval/vibecosystem 458
-
research-external
External research workflow for docs, web, APIs - NOT codebase exploration
vibeeval/vibecosystem 458
-
experiment-loop
Autonomous experiment loop: hypothesize > modify > test > evaluate > keep/discard > repeat. Run N experiments automatically with measurable metrics. Works for performance optimization, A/B testing, prompt engineering, and any measurable improvement task.
vibeeval/vibecosystem 458
-
project-guidelines-example
Example template for project-specific skill files covering architecture, patterns, testing, and deployment.
vibeeval/vibecosystem 458
-
coding-standards
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
vibeeval/vibecosystem 458
-
mot
System health check (MOT) for skills, agents, hooks, and memory
vibeeval/vibecosystem 458
-
refactor
Code refactoring workflow - analyze → plan → implement → review → validate
vibeeval/vibecosystem 458
-
graceful-degradation
Graceful Degradation with Helpful Messages
vibeeval/vibecosystem 458
-
limits
Problem-solving strategies for limits in real analysis
vibeeval/vibecosystem 458
-
form-validation
React Hook Form + Zod integration, multi-step forms, optimistic validation, server-side error mapping, and file upload patterns.
vibeeval/vibecosystem 458
-
sub-agents
Create and configure Claude Code sub-agents with custom prompts, tools, and models
vibeeval/vibecosystem 458
-
phase-gated-commits
Break large features into phases where each phase follows implement -> review -> commit cycle. Use for multi-file features or refactoring that should have clean git history.
vibeeval/vibecosystem 458