multimodal-rag
CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images, implementing visual search, or hybrid retrieval.
Découvrez les skills Contenu et médias, comparez leurs dépôts et consultez leurs instructions.
CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images, implementing visual search, or hybrid retrieval.
Full-power feature implementation with parallel subagents, skills, and MCPs. Use when implementing features, building features, creating features, or developing features.
LangGraph checkpointing and persistence. Use when implementing fault-tolerant workflows, resuming interrupted executions, debugging with state history, or avoiding re-running expensive operations.
Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes.
Multi-agent frameworks beyond LangGraph. CrewAI crews, Microsoft Agent Framework, OpenAI Agents SDK. Use when building multi-agent systems, choosing frameworks.
Use when creating or developing anything, before writing code or implementation plans. Brainstorming skill refines ideas through structured questioning and alternatives.
Real-time Constitution compliance checker for devflow documents. Blocks partial implementations and hardcoded secrets during file editing.
Enforces TDD order in TASKS.md - Tests MUST be marked complete before Implementation tasks. Blocks violations in real-time.
Handle code review feedback with technical rigor. Don't blindly agree - verify before implementing.
Use this skill when systematically debugging issues, investigating bugs, troubleshooting problems, or tracking down errors with persistent state across context resets. Triggers include "debug", "investigate bug...
Use this skill when executing small ad-hoc tasks with Kata guarantees, running quick tasks without full planning, or handling one-off work outside the roadmap. Triggers include "quick task", "quick mode", "quic...
Use this skill when initialize a new project with deep context gathering and project.md. Triggers include "new project", "start project", "initialize project", "create project", "begin project", "setup project"...
Use this skill when surfacing Claude's assumptions about a phase approach before planning, checking what Claude thinks, or validating understanding before planning. Triggers include "list assumptions", "what ar...
Use this skill when switch model profile for kata agents (quality/balanced/budget). Triggers include "set profile", "set profile".
Use this skill when resuming work from a previous session, restoring context after a break, continuing work after /clear, or picking up where you left off. Triggers include "resume work", "continue work", "pick...
Use this skill when showing available Kata commands, displaying the usage guide, explaining command reference, or when the user asks for help with Kata. Triggers include "help", "show commands", "list commands"...
Use this skill when remove a future phase from roadmap and renumber subsequent phases. Triggers include "remove phase", "remove phase".
Use this skill when create detailed execution plan for a phase (plan.md) with verification loop. Triggers include "plan phase", "plan phase".
Use this skill to verify milestone achievement against its definition of done, checking requirements coverage, cross-phase integration, and end-to-end flows. Triggers include "audit milestone", "verify mileston...
Use this skill to add planned work discovered during execution to the end of the current milestone in the roadmap. This skill appends sequential phases to the current milestone's phase list, automatically calcu...
Use this skill when reviewing pending todos, selecting a todo to work on, filtering todos by area, or deciding what to work on next. Triggers include "check todos", "list todos", "what todos", "pending todos",...
Use this skill when creating a context handoff file, pausing work mid-phase, stopping work temporarily, or creating a checkpoint for session resumption. Triggers include "pause work", "stop work", "create hando...
Use this skill when create phases to close all gaps identified by milestone audit. Triggers include "plan milestone gaps", "plan gaps".
Use this skill when archiving a completed milestone, preparing for the next version, marking a milestone complete, shipping a version, or wrapping up milestone work. Triggers include "complete milestone", "fini...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.