GitHub
idea-generation
Product idea generation and business validation specialist. Use when brainstorming ideas, validating business concepts, analyzing market opportunities, or evaluating product-market fit. Triggers on "idea genera...
Skills IA research llm ai
Découvrez les skills research llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: research llm ai
research llm ai Effacer les filtres
Explorer
GitHub
intern
Delegate tasks to the "intern" agent via ACP. Use when user says "use the intern", "ask the intern", "delegate to the intern", or similar. The intern can read files, write code, run commands, and complete devel...
GitHub
codex-cli-reference
This skill should be used when the user asks about "codex CLI options", "codex flags", "codex exec command", "codex session management", "codex sandbox modes", or needs reference information about invoking the...
GitHub
create-feature
Initialize a new feature area for exploration and decision-making. Use when user says "create feature {feature-name}" or "new feature {feature-name}". Creates folder structure with readme.md and investigations...
GitHub
open-responses-agent-dev
Build autonomous agents using Open Responses API via HuggingFace Inference Providers. Single unified endpoint with multi-provider routing via model suffixes. Use the OpenAI SDK with custom base_url for seamless...
GitHub
metaskill-packaging
Package skills, agents, commands, and hooks as Claude Code plugins. Use when creating plugins, packaging skills for distribution, setting up plugin structure, dogfooding plugins, or when user mentions "plugin s...
GitHub
metaskill-grouping
Create skill groups (multiple related skills packaged as a plugin). Use when creating plugins, organizing multiple related skills, building skill families, packaging tools together, or when user mentions "plugi...
GitHub
metaskill-naming
Brainstorm and validate names for plugins, skills, agents, and commands. Use when naming a new plugin, choosing atom names, validating naming conventions, or when user mentions "name plugin", "name skill", "nam...
GitHub
metaskill-authoring
Write Claude Code skills and SKILL.md files. Use when creating new skills, writing skill content, structuring SKILL.md, organizing skill directories, or when user mentions "write skill", "create skill", "author...
GitHub
metaskill-triggering
Optimize skill triggers and descriptions for reliable activation. Use when skill is not triggering, optimizing trigger keywords, writing frontmatter, debugging activation, or when user mentions "trigger", "fron...
GitHub
go-temporal
Expert guidance for building workflows and activities with Temporal in Go. Use when working with Temporal SDK, designing durable workflows, handling retries, implementing saga patterns, or debugging Temporal ap...
GitHub
sonnet
Override default model selection for specific subagents to use Sonnet instead of Opus. Use ONLY when the user explicitly requests to use Sonnet model for Plan, code-reviewer, code-simplifier, or Resolve Conflic...
GitHub
context-llm-pipeline
RAG pipeline, embeddings, LLM interactions, and flow orchestration.
GitHub
codex-qa
Use OpenAI Codex CLI to answer questions about code, analyze files, or perform read-only codebase exploration. Invoke this skill when the user asks to use Codex, wants a second opinion from another AI agent, or...
GitHub
gemini-qa
Use Google Gemini CLI to answer questions about code, analyze files, or perform codebase exploration. Invoke this skill when the user asks to use Gemini, wants a second opinion from another AI, or wants to comp...
GitHub
ulw
ULTRAWORK MODE - Maximum capability activation. Use when you need parallel agent orchestration, strict verification, and zero tolerance for incomplete work. Triggers automatically on 'ultrawork' or 'ulw' in mes...
GitHub
search-mode
Maximum search effort mode. Launch multiple parallel agents for exhaustive codebase and documentation search. Use when you need comprehensive search results.
GitHub
analyze-mode
Deep analysis mode. Gather comprehensive context before diving deep. Use for investigation, debugging, and understanding complex systems.
GitHub
mcp-economy
Enforce cost-aware MCP usage. Use when a task might trigger heavy external tools, web search, or broad context expansion. Prevents token burn by ensuring MCPs are only used when local context is insufficient.
GitHub
context-engineering
Token optimization and context window management strategies. Load for long sessions, complex tasks, or when approaching context limits.
GitHub
remembering-conversations
Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search
GitHub
pact-memory
Persistent memory for PACT agents. Save context, goals, lessons learned, decisions, and entities. Semantic search across sessions. Use when: saving session context, recalling past decisions, searching lessons....
GitHub
e2e-testing
Execute comprehensive end-to-end tests for the Meal Planner application using Claude in Chrome browser automation. Supports regression testing (checklist-based) and exploratory testing (discovery-focused). Use...
GitHub
verified-information-generator
Verified information generation and validation
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.