All authors
Claude Skills by GadaaLabs
github.com/GadaaLabs24 skills0 installs17 views
- ArbiterUse when receiving code review feedback, before implementing any suggestion — requires technical verification and reasoned evaluation, not performative agreement or blind implementationVotes: 0GitHub stars: 68
- ArchitectYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.Votes: 0GitHub stars: 68
- AscendUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questionsVotes: 0GitHub stars: 68
- BlueprintUse when you have a spec or requirements for a multi-step task, before touching codeVotes: 0GitHub stars: 68
- ChronicleStore and retrieve patterns from past work using semantic search; adds self-learning capability to SuperpowersVotes: 0GitHub stars: 68
- CommanderUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesVotes: 0GitHub stars: 68
- ExodusUse when you have a written implementation plan to execute in a completely fresh isolated session — no context inheritance, clean slate execution with review checkpointsVotes: 0GitHub stars: 68
- ForgeUse when implementing any feature or bugfix, before writing implementation codeVotes: 0GitHub stars: 68
- GradientML-specific patterns for data pipelines, model training, MLOps, and evaluation — domain expertise for machine learning engineersVotes: 0GitHub stars: 68
- HorizonManage context window budget across long sessions — when to compress, what to give subagents, when to start fresh. Prevents silent quality degradation as conversations grow.Votes: 0GitHub stars: 68
- HunterUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesVotes: 0GitHub stars: 68
- IroncoreState machines, ISRs, RTOS, hardware abstraction, and timing analysis — domain expertise for electrical and embedded systems engineersVotes: 0GitHub stars: 68
- LegionSelect optimal subagent topology (hierarchical, mesh, ring, star) based on task structure; adds Ruflo-style swarm intelligence to SuperpowersVotes: 0GitHub stars: 68
- NexusRAG architectures, agent design patterns, prompt engineering, and LLM evaluation — domain expertise for AI application engineersVotes: 0GitHub stars: 68
- OraclePre-task intelligence layer — classify complexity, select skill chain, search patterns, assign model tier. Run BEFORE any non-trivial task begins. Turns the system from reactive to proactive.Votes: 0GitHub stars: 68
- PathfinderStructured first-pass exploration of an unfamiliar codebase — what to read, in what order, what to map, what traps to find. Use when entering any new or inherited project before writing code.Votes: 0GitHub stars: 68
- PhantomUse when executing implementation plans with independent tasks in the current sessionVotes: 0GitHub stars: 68
- PrismUI/UX design intelligence, accessibility, performance, SEO, and data visualization — domain expertise for web and app developers. Includes 67 UI styles, 25 chart types, font pairing, and UX guidelines.Votes: 0GitHub stars: 68
- SculptorUse when creating new skills, editing existing skills, or verifying skills work before deployment — applies TDD to process documentation with the same Iron Law as FORGEVotes: 0GitHub stars: 68
- SealUse when implementation is complete and all tests pass — guides branch completion through four structured options (merge, PR, keep, discard) with verification and worktree cleanupVotes: 0GitHub stars: 68
- SentinelUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysVotes: 0GitHub stars: 68
- TribunalUse when completing tasks, implementing major features, or before merging to verify work meets requirementsVotes: 0GitHub stars: 68
- VaultUse when starting feature work that needs isolation from the current workspace, or before executing implementation plans — creates isolated git worktrees with smart directory selection and safety verificationVotes: 0GitHub stars: 68
- VectorSelect optimal AI model by task complexity — route to cheap/fast models for simple tasks, capable models for complex reasoningVotes: 0GitHub stars: 68