GitHub
slicing-long-contexts
Use when a prompt or corpus is long/dense (multi-docs, logs, codebases) and you want a reproducible map/reduce pipeline. Trigger this skill to slice inputs, run per-slice codex/gemini subcalls, and aggregate re...
Skills IA content media llm ai
Découvrez les skills content media llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: content media llm ai
content media llm ai Effacer les filtres
Explorer
GitHub
creating-skills
General skill authoring and improvement. Use when creating or updating any skill (with or without MCP), selecting structure, generating scaffolds, or packaging resources (scripts/references/assets/templates) th...
GitHub
eval-harness-kit
Build and run deterministic evaluation suites for agent workflows (single-turn or agentic). Use when you need reproducible eval runs with manifests, graders, metrics, and JSONL logs for capability or regression...
GitHub
inspecting-the-environment
Fast environment briefing for agents and subagents. Use at session start to learn OS/shell, container/WSL/VM status, git repo + upstream + dirty state, Python venv status/locations, markdown folders to read, an...
GitHub
pincer-planning
Bidirectional planning for ambiguous or design-heavy tasks. Use when the user requests help breaking down a problem or formulating a plan, and also when an existing plan has too many gaps or needs refinement; c...
GitHub
tool-quality-audit
Audit tool integrations for deterministic behavior, error contracts, and logging before agents depend on them. Use when adding or updating tools or MCP servers.
GitHub
agent-workflow-playbook
Guide plan → instrument → execute → validate with explicit checkpoints and questions. Use for ambiguous tasks or when enforcing a consistent agent workflow.
GitHub
prompt-engineering
Generates optimized prompts for AI professional developers through interactive clarification. Asks targeted questions to refine requirements, saves tokens, and ensures reliable outputs. Use when seeking the bes...
GitHub
conda-env-setup
This skill should be used when the user asks to "setup conda environment", "configure Python environment", "activate conda automatically", "set conda environment for workspace", or mentions conda environment ac...
GitHub
implement
Generate clean C# code, Markdown files, agents, prompts, skills in MacroFlow.
GitHub
clarify
Refine user intent through questions and context gathering in MacroFlow.
GitHub
macroflow-network
Orchestrate MacroFlow as a flow network for dynamic AI orchestration.
GitHub
tools
Get information about available tools
GitHub
creating-agent-skills
Creates Agent Skills for Claude Code following official standards. Use when the user wants to create a Skill, teach Claude new capabilities, add specialized knowledge, or create reusable instructions. Keywords:...
GitHub
hemingwayesque
Ruthless concision for AI prompts and context - "Not One Word Wasted"
GitHub
workflow-design
Design, discover, and refactor multi-command workflows for Claude Code
GitHub
pentarchy
Multi-disciplinary strategy council with 5 expert personas. Use for strategic analysis, impact assessment, complex decisions requiring diverse expertise. Includes cross-examination to identify contradictions be...
GitHub
forge
Lean code implementation pair. Claude (Smith) writes code, Gemini (Temper) reviews for bugs, security, and edge cases. ~2x token cost for high-quality code output.
GitHub
cartographer
Tree of Thoughts exploration for brainstorming and finding unknown unknowns. Recursively branches hypotheses, ranking by NOVELTY not probability. Use for idea generation, creative unblocking, exploring possibil...
GitHub
red-team-research
Adversarial research validation using Red Team/Blue Team methodology. Use when researching complex topics, fact-checking claims, or producing research reports. Validates outputs through Gemini 3 Pro critic befo...
GitHub
gemini-cli-model
Instructions for selecting and configuring Gemini 3 Pro Preview model in Gemini CLI. Use when the user asks about switching models in Gemini CLI, enabling Gemini 3, or configuring Gemini CLI model settings.
GitHub
triumvirate
3x3 Parallel Debate system for high-confidence research. Spawns 9 agent instances (3 Proposer/Skeptic/Judge cohorts) to argue, critique, and adjudicate claims. Use for complex queries, controversial topics, or...
GitHub
weaver
Map-Reduce system for comprehensive reports and literature reviews. Breaks topic into chapters, researches each in parallel, then weaves into unified document. Use for deep research, reports, and synthesis.
GitHub
foundry
Three-stage code implementation with planning. Gemini (Engineer) plans, Claude (Caster) implements, Gemini (Inspector) verifies. ~3x token cost for complex, multi-file changes.
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.