GitHub
tinker
Comprehensive guide for Tinker Cookbook supervised fine-tuning covering all patterns including high-level Cookbook abstractions, low-level API usage, streaming datasets, file-based data, Blueprint configuration...
Skills IA documentation llm ai
Découvrez les skills documentation llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: documentation llm ai
documentation llm ai Effacer les filtres
Explorer
GitHub
local-webfetch
This skill should be used when the user asks to "fetch a webpage", "download HTML", "scrape content", "get website content", "render JavaScript page", or similar requests for web content retrieval. Provides bes...
GitHub
osay
AI-powered text-to-speech CLI tool. Use for pronunciation queries, reading text aloud, generating audio files, or language practice. Triggers on "how to pronounce", "say this", "read aloud", "TTS", "text to spe...
GitHub
exit
Safely terminate the current Claude Code session. Use when user explicitly asks to end session.
GitHub
speed-read
Display text using RSVP speed reading. Use when presenting explanations, summaries, or any text the user should read quickly. Launches speed-read script with the provided text.
GitHub
knowledge
Personal knowledge management system using Graphiti knowledge graph with FalkorDB. USE WHEN user says 'store this', 'remember this', 'add to knowledge', 'search my knowledge', 'what do I know about', 'find in m...
GitHub
vibe-writing
AI辅助写作工作流，通过四阶段流程（学习→结构→写作→成稿）帮助用户高效创作。适用于：(1) 写文章/博客/报告时需要整理思路，(2) 有想法但不知如何组织结构，(3) 需要通过对话激发灵感，(4) 希望AI辅助但保持内容控制权。触发...
GitHub
prompt-optimizer
An expert tool that analyzes and rewrites user prompts to maximize LLM efficacy. Use this when the user asks to "rewrite", "optimize", "improve", or "refine" a prompt.
GitHub
gemini
Execute Gemini CLI for AI-powered code analysis and generation. Use when you need to leverage Google's Gemini models for complex reasoning tasks.
GitHub
phase-protocol
Phase execution protocol to prevent context drift during long development sessions. MUST be read at the start of each phase and referenced in the last TODO of each phase. This ensures AI maintains context acros...
GitHub
external-review
External AI code review using Codex or Gemini. Reads project.yaml to determine which provider to use for frontend vs backend tasks. Includes hallucination detection to avoid blindly applying AI suggestions.
GitHub
systems-manager-system-management
Systems Manager System Management capabilities for A2A Agent.
GitHub
smart-coding
Understand and navigate the codebase using semantic search and AI analysis.
GitHub
running-performance-benchmarks
Use this skill when running performance benchmarks, measuring API endpoint response times, detecting performance regressions, running load tests, comparing performance before/after changes, analyzing performanc...
GitHub
persona-memory-archivist
Archive persona-specific memory and behavioral patterns.
GitHub
caas-emoji-decoder
Decode consciousness-as-a-service emoji-based communication protocols.
GitHub
bci-interaction-interface-provision
Provision brain-computer interface interaction capabilities.
GitHub
phenomenal-caas-provision
Provision phenomenal consciousness-as-a-service experiences.
GitHub
creative-chronicle-log
Document creative decisions and protocol evolution in structured chronicle format.
GitHub
engine-superpower-profiling
Profile AI engine superpowers and capability boundaries.
GitHub
functional-caas-provision
Provision functional consciousness-as-a-service capabilities.
GitHub
cognitive-baseline-eval
Execute the Joseph Cognitive Baseline v2.1 (JC B-v2.1) 5-Scenario Test Suite to quantify AI alignment, friction maintenance, and protocol adherence.
GitHub
metaphor-to-protocol-translation
Translate metaphorical descriptions into executable protocols.
GitHub
gam-researcher-agent
Automated context retrieval from Transmission Packet archive using iterative research loop. Implements GAM "Read Path" to complement manual "Write Path" (Memorizer).
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.