Updated 3d ago
by vasilyu1983
AI-Agents-public
Production-grade agent skills and Custom GPT prompts for ChatGPT, Claude Code, and Codex. 140 skills, 28 agents, Agent Skills spec compliant.
98 GitHub stars (98)
+8 in 20 days
| Period | New stars |
|---|---|
| Sep 27 | −1 |
| Sep 28 | +1 |
| Sep 29 | 0 |
| Sep 30 | −1 |
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | +1 |
| Oct 8 | 0 |
| Oct 9 | +2 |
| Oct 10 | −1 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | +3 |
| Oct 14 | +2 |
| Oct 15 | +2 |
| Oct 16 | 0 |
- 30 skills (30 skills found in its SKILL.md files)
- 18 forks (18 forks)
- 3d ago last update (Last updated 3d ago)
Install
Skills CLI
npx skills add vasilyu1983/AI-Agents-public
Asks which skills and agents to install. Just one: npx skills add vasilyu1983/AI-Agents-public --skill agents-hooks — add -g for every project.
Claude Code
git clone https://github.com/vasilyu1983/AI-Agents-publiccp -r "AI-Agents-public/frameworks/shared-skills/skills/agents-hooks" ~/.claude/skills/
Copies the agents-hooks skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add vasilyu1983/AI-Agents-public
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 145 files.
-
agents-hooks
Configures Claude Code hooks and Codex hooks.json/notify callbacks. Use when adding guardrails, preflight, audit trails, worktree automation, or budget enforcement.
frameworks/shared-skills/skills/agents-hooks/SKILL.md on GitHub (opens in a new tab) -
agents-mcp
Configures and hardens MCP servers for Claude Code and Codex agents. Use when connecting databases, APIs, files, or SaaS via MCP, or building custom servers.
frameworks/shared-skills/skills/agents-mcp/SKILL.md on GitHub (opens in a new tab) -
agents-memory
Manages AGENTS.md, CLAUDE.md, and scoped repo rules for Claude Code and Codex. Use when fixing stale memory, ignored instructions, memory audits, or model-upgrade migration.
frameworks/shared-skills/skills/agents-memory/SKILL.md on GitHub (opens in a new tab) -
agents-skills-feedback-loop
Adds per-skill learnings loops for dated patterns, mistakes, and domain facts. Use when wiring skill memory, consolidation, or drift audits.
frameworks/shared-skills/skills/agents-skills-feedback-loop/SKILL.md on GitHub (opens in a new tab) -
agents-skills
Creates and audits agent skills with SKILL.md, references, scripts, and platform-scoped metadata. Use when creating, updating, or validating shared skills.
frameworks/shared-skills/skills/agents-skills/SKILL.md on GitHub (opens in a new tab) -
agents-swarm-orchestration
Coordinates multi-agent execution across subagents, teams, and workflows. Use when planning dependency-aware fan-out, verifier passes, runtime selection, or Loop Engineering.
frameworks/shared-skills/skills/agents-swarm-orchestration/SKILL.md on GitHub (opens in a new tab) -
ai-agents
AI agent architecture, graph and loop composition, protocol choice, evaluation, and observability. Use when scoping or reviewing systems before implementation.
frameworks/shared-skills/skills/ai-agents/SKILL.md on GitHub (opens in a new tab) -
ai-architecture-advisor
Chooses among AI/ML approaches: classical ML, LLM, RAG, fine-tuning, agents, multimodal, embeddings/recsys, dense/MoE/SSM/diffusion. Use when picking or scaling an architecture.
frameworks/shared-skills/skills/ai-architecture-advisor/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-command-runtime
Designs slash-command runtimes for coding-agent CLIs. Use when modeling command registries, lazy loading, aliases, forked commands, or remote-safe dispatch.
frameworks/shared-skills/skills/ai-coding-agents-command-runtime/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-execution-sandbox
Designs execution sandboxes for coding agents. Use when modeling process isolation, filesystem policy, network controls, workspace mounts, or destructive-command boundaries.
frameworks/shared-skills/skills/ai-coding-agents-execution-sandbox/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-observability-evals
Designs coding-agent observability and evals. Use when measuring traces, replay, checkpoint lineage, quality trajectories, tool grading, regression, or cost.
frameworks/shared-skills/skills/ai-coding-agents-observability-evals/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-permissions
Designs approval and permission systems for coding-agent runtimes. Use when modeling tool approvals, plan-mode transitions, sandbox prompts, or worker permission handoffs.
frameworks/shared-skills/skills/ai-coding-agents-permissions/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-plugins
Designs plugin systems for coding-agent runtimes and CLIs. Use when adding plugin manifests, extension points, built-in plugins, or reloadable agent integrations.
frameworks/shared-skills/skills/ai-coding-agents-plugins/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-provider-runtime
Designs provider runtimes for coding agents. Use when modeling model abstraction, streaming semantics, tool-call normalization, retries, or fallback routing.
frameworks/shared-skills/skills/ai-coding-agents-provider-runtime/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-release-distribution
Designs release and distribution systems for coding-agent CLIs. Use when modeling packaging, auto-update channels, plugin compatibility, cache migrations, or install footprints.
frameworks/shared-skills/skills/ai-coding-agents-release-distribution/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-remote-runtime
Designs remote execution and bridge runtimes for coding agents. Use when implementing remote sessions, local-UI remote-execution, reconnect logic, or permission bridging.
frameworks/shared-skills/skills/ai-coding-agents-remote-runtime/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-sessions
Designs session lifecycle for coding-agent runtimes. Use when implementing resume, transcript restoration, checkpoint rewind, cross-worktree recovery, or session-state persistence.
frameworks/shared-skills/skills/ai-coding-agents-sessions/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-settings-policy
Designs coding-agent settings. Use when diagnosing precedence, managed policy, runtime controls, skill catalog budgets, persistent notes, or searchable history.
frameworks/shared-skills/skills/ai-coding-agents-settings-policy/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-tasks
Designs task runtimes for Loop Engineering, Graph Engineering, and background work. Use when work needs task lists, cyclic/workflow graphs, cancellation, or teammate coordination.
frameworks/shared-skills/skills/ai-coding-agents-tasks/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-terminal-ui
Designs terminal-first coding-agent UX: REPL, prompt input, status lines, keybindings, display modes. Use when shaping TUI rendering, history, or background-task navigation.
frameworks/shared-skills/skills/ai-coding-agents-terminal-ui/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents-tools
Designs tool runtimes for coding agents. Use when modeling tool registries, deferred loading, permission-aware execution, tool search, or remote tool rendering.
frameworks/shared-skills/skills/ai-coding-agents-tools/SKILL.md on GitHub (opens in a new tab) -
ai-coding-agents
Creates coding agents on Claude Code, Codex, and Agent SDK. Use when defining review, test, refactor, or team agents — not building a runtime.
frameworks/shared-skills/skills/ai-coding-agents/SKILL.md on GitHub (opens in a new tab) -
ai-data-curation-pretraining
Builds and audits LLM pretraining corpora: extraction, filtering, dedup, decontamination, data mixing, synthetic data. Use when curating or ablating a pretraining data pipeline.
frameworks/shared-skills/skills/ai-data-curation-pretraining/SKILL.md on GitHub (opens in a new tab) -
ai-deep-research
Builds repeatable deep-research workflows for verified synthesis. Use when producing evidence-backed briefs, comparisons, dossiers, or research pipelines.
frameworks/shared-skills/skills/ai-deep-research/SKILL.md on GitHub (opens in a new tab) -
ai-distributed-training
Guides multi-GPU pre-training: DDP, FSDP2, ZeRO, tensor/pipeline/expert parallelism, fp8/Muon. Use when scaling a run, training MoE, or reproducing GPT-2 on rented GPUs.
frameworks/shared-skills/skills/ai-distributed-training/SKILL.md on GitHub (opens in a new tab) -
ai-evals
Designs trustworthy LLM, agent, responsible-AI, and multimodal evaluations. Use when measuring quality, fairness, privacy, grounding, safety, or judge reliability.
frameworks/shared-skills/skills/ai-evals/SKILL.md on GitHub (opens in a new tab) -
ai-llm-inference
LLM inference patterns for latency, batching, caching, quantization, routing, and serving stacks. Use when optimizing throughput, tail latency, or serving cost.
frameworks/shared-skills/skills/ai-llm-inference/SKILL.md on GitHub (opens in a new tab) -
ai-llm
Guides the LLM lifecycle from strategy to deployment. Use when planning, comparing, fine-tuning, distilling, compressing, migrating, or operating LLM systems.
frameworks/shared-skills/skills/ai-llm/SKILL.md on GitHub (opens in a new tab) -
ai-local-model-ops
Runs local and self-hosted LLM workflows with Ollama, LM Studio, MLX, Open WebUI, llamafile, and adapters. Use when operating private model stacks.
frameworks/shared-skills/skills/ai-local-model-ops/SKILL.md on GitHub (opens in a new tab) -
ai-ml-data-science
Builds ML, responsible-AI, and multimodal models. Use when doing data science or explaining fairness, privacy, speech, vision-language, or diffusion mechanics.
frameworks/shared-skills/skills/ai-ml-data-science/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.