agentsclimarketplace

Context & AI engineering

25,745 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Maintain contract

    odere-pro/claude-wiki-pages-plugin/skills/maintain-contract Skill

    1★ repo

    The workflow contract for any agent that ingests, retrieves from, or maintains a claude-wiki-pages vault. Documents the safe ordering — ground → judge → verify — checkpoint discipline, retrieval grounding, and the immutability rules, so an external agent can drive the wiki correctly without re-reading the whole spec. Trigger when an agent or user asks "how should I maintain the wiki", "what is the safe ingest/retrieve order", "how do other agents use this", or invokes /claude-wiki-pages:maintain-contract. Reference, not action.

  • Obsidian vault

    odere-pro/claude-wiki-pages-plugin/skills/obsidian-vault Skill

    1★ repo

    Guard contract for driving the Obsidian CLI safely — always scope every invocation to the resolved vault, never operate on arbitrary vaults or paths. Trigger when an agent is about to run `obsidian` commands, or asks "how do I call the Obsidian CLI", "which vault am I writing to", or invokes /claude-wiki-pages:obsidian-vault. Reference material that complements the enforced firewall hook (`scripts/firewall.sh`).

  • Search

    odere-pro/claude-wiki-pages-plugin/skills/search Skill

    1★ repo

    Find wiki pages by keyword with a deterministic, reproducible ranking and [[wikilink]]-ready results. Trigger when the user or an agent wants to locate pages ("find pages about X", "which pages mention Y", "list notes tagged Z") or needs a candidate set before a deeper query/synthesis. Backed by the engine `search` command; read-only. For a cited natural-language answer, use /claude-wiki-pages:query instead. Tier-2 recall: synonym expansion via _vocabulary.md and Porter stemming eliminate zero-overlap misses without embeddings.

  • Voice

    odere-pro/claude-wiki-pages-plugin/skills/voice Skill

    1★ repo

    The house writing voice for claude-wiki-pages — how to write prose that a newcomer actually wants to read and an engineer can trust. Defines two registers (explanatory and engineer), the rule for choosing between them, the LLM-artifact blocklist, the vocabulary and register-separation rules the doc gate enforces, and how to write a wiki page. Trigger when writing or editing any doc, README, guide, or wiki page, or when an agent asks "what voice should I write in", "how should this note read", or invokes /claude-wiki-pages:voice. Reference, not action — it teaches how to write, it does not write for you.

  • Cross eval

    timdevai/proteus/skills/community/from-alireza/c-level-advisor/c-level-agents/skills/cross-eval Skill

    1★ repo

    /cs:cross-eval <memo> — Multi-model consensus on a board memo or strategy brief. Claude + Codex + Gemini cross-review with graceful degradation.

  • Agent protocol

    timdevai/proteus/skills/community/from-alireza/c-level-advisor/skills/agent-protocol Skill

    1★ repo

    Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with multiple agent roles.

    The same file is in 1 other repository

  • C level skills

    timdevai/proteus/skills/community/from-alireza/c-level-advisor/skills/c-level-skills Skill

    1★ repo

    10 C-level advisory agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO, Executive Mentor. Multi-role board meetings, strategy routing, structured recommendations. For founders needing executive-level decision support.

    The same file is in 1 other repository

  • Promote

    timdevai/proteus/skills/community/from-alireza/engineering-team/self-improving-agent/skills/promote Skill

    1★ repo

    Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement.

    The same file is in 1 other repository

  • Self improving agent

    timdevai/proteus/skills/community/from-alireza/engineering-team/self-improving-agent/skills/self-improving-agent Skill

    1★ repo

    Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.

    The same file is in 1 other repository

  • Engineering skills

    timdevai/proteus/skills/community/from-alireza/engineering-team/skills/engineering-skills Skill

    1★ repo

    23 engineering agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more tools. Architecture, frontend, backend, QA, DevOps, security, AI/ML, data engineering, Playwright, Stripe, AWS, MS365. 30+ Python tools (stdlib-only).

    The same file is in 1 other repository

  • Senior prompt engineer

    timdevai/proteus/skills/community/from-alireza/engineering-team/skills/senior-prompt-engineer Skill

    1★ repo

    This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.

    The same file is in 2 other repositories

  • Agenthub

    timdevai/proteus/skills/community/from-alireza/engineering/agenthub/skills/agenthub Skill

    1★ repo

    Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

    The same file is in 4 other repositories

  • Eval

    timdevai/proteus/skills/community/from-alireza/engineering/agenthub/skills/eval Skill

    1★ repo

    Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

    The same file is in 1 other repository

  • Autoresearch agent

    timdevai/proteus/skills/community/from-alireza/engineering/autoresearch-agent/skills/autoresearch-agent Skill

    1★ repo

    Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

    The same file is in 4 other repositories

  • Handoff

    timdevai/proteus/skills/community/from-alireza/engineering/handoff/skills/handoff Skill

    1★ repo

    Compact the current conversation into a handoff document for another agent to pick up. References existing artifacts (PRDs, plans, ADRs, issues, commits, diffs) by path or URL instead of duplicating them. Use when user wants to hand off the conversation to a fresh agent or starts a new session that picks up prior work.

    The same file is in 1 other repository

  • Llm cost optimizer

    timdevai/proteus/skills/community/from-alireza/engineering/llm-cost-optimizer/skills/llm-cost-optimizer Skill

    1★ repo

    Use proactively whenever LLM API costs come up -- or should. Triggers include: 'my AI costs are too high', 'optimize token usage', 'which model should I use', 'LLM spend is out of control', 'implement prompt caching', 'we're about to launch an AI feature', 'build me an AI endpoint'. Don't wait for an explicit cost complaint -- if someone is building an AI feature, designing an LLM endpoint, or choosing between models, cost architecture belongs in the conversation. Apply immediately when any of these are true: a system prompt appears that exceeds a few hundred tokens, all requests are hitting the same model, max_tokens is not set, or no per-feature cost logging exists. NOT for RAG pipeline design (use rag-architect). NOT for improving prompt quality or effectiveness (use senior-prompt-engineer).

    The same file is in 3 other repositories

  • Llm wiki

    timdevai/proteus/skills/community/from-alireza/engineering/llm-wiki/skills/llm-wiki Skill

    1★ repo

    Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

    The same file is in 1 other repository

  • Prompt governance

    timdevai/proteus/skills/community/from-alireza/engineering/prompt-governance/skills/prompt-governance Skill

    1★ repo

    Use when managing prompts in production at scale: versioning prompts, running A/B tests on prompts, building prompt registries, preventing prompt regressions, or creating eval pipelines for production AI features. Triggers: 'manage prompts in production', 'prompt versioning', 'prompt regression', 'prompt A/B test', 'prompt registry', 'eval pipeline'. NOT for writing or improving individual prompts (use senior-prompt-engineer). NOT for RAG pipeline design (use rag-architect). NOT for LLM cost reduction (use llm-cost-optimizer).

    The same file is in 4 other repositories

  • Agent designer

    timdevai/proteus/skills/community/from-alireza/engineering/skills/agent-designer Skill

    1★ repo

    Use when the user asks to design multi-agent systems, create agent architectures, define agent communication patterns, or build autonomous agent workflows.

    The same file is in 1 other repository

  • Agent workflow designer

    timdevai/proteus/skills/community/from-alireza/engineering/skills/agent-workflow-designer Skill

    1★ repo

    Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs.

    The same file is in 3 other repositories

  • Command guide

    timdevai/proteus/skills/community/from-alireza/engineering/skills/command-guide Skill

    1★ repo

    Claude Code Command Selection Guide - Automatically recommend and select the right commands, agents, and skills in Claude Code. Use when: (1) user is unsure which command or tool to use, (2) needs to decide which agent/skill best fits the current task, (3) querying usage scenarios for /plan, /tdd, /compact, /loop and other commands, (4) understanding when to invoke planner, code-reviewer, build-error-resolver and other agents, (5) needs command cheat sheet or decision flowchart. Triggers: "which command to use", "which agent", "command selection", "how to use /plan", "when to use /compact", "agent selection guide", "command cheat sheet", "skill recommendation".

  • Engineering advanced skills

    timdevai/proteus/skills/community/from-alireza/engineering/skills/engineering-advanced-skills Skill

    1★ repo

    25 advanced engineering agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Agent design, RAG, MCP servers, CI/CD, database design, observability, security auditing, release management, platform ops.

    The same file is in 1 other repository

  • Git worktree manager

    timdevai/proteus/skills/community/from-alireza/engineering/skills/git-worktree-manager Skill

    1★ repo

    Run parallel feature work safely with Git worktrees. Standardizes branch isolation, port allocation, environment sync, and cleanup so each worktree behaves like an independent local app. Optimized for multi-agent workflows where each agent or terminal session owns one worktree. Use when running multiple feature branches simultaneously, isolating experimental work, or coordinating multi-agent development across the same repo.

    The same file is in 3 other repositories

  • Mcp server builder

    timdevai/proteus/skills/community/from-alireza/engineering/skills/mcp-server-builder Skill

    1★ repo

    Design and ship production-ready MCP (Model Context Protocol) servers from OpenAPI contracts instead of hand-written tool wrappers. Python and TypeScript support, schema validation, safe evolution. Use when exposing an existing API as an MCP server, building tool integrations for Claude or Codex or Cursor, or scaffolding an MCP project from scratch.

  • Rag architect

    timdevai/proteus/skills/community/from-alireza/engineering/skills/rag-architect Skill

    1★ repo

    Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.

    The same file is in 1 other repository

  • Self eval

    timdevai/proteus/skills/community/from-alireza/engineering/skills/self-eval Skill

    1★ repo

    Honestly evaluate AI work quality using a two-axis scoring system. Use after completing a task, code review, or work session to get an unbiased assessment. Detects score inflation, forces devil's advocate reasoning, and persists scores across sessions.

    The same file is in 5 other repositories

  • Skill security auditor

    timdevai/proteus/skills/community/from-alireza/engineering/skills/skill-security-auditor Skill

    1★ repo

    Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. Triggers: "audit this skill", "is this skill safe", "scan skill for security", "check skill before install", "skill security check", "skill vulnerability scan".

    The same file is in 1 other repository

  • Terraform patterns

    timdevai/proteus/skills/community/from-alireza/engineering/terraform-patterns/skills/terraform-patterns Skill

    1★ repo

    Terraform infrastructure-as-code agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Covers module design patterns, state management strategies, provider configuration, security hardening, policy-as-code with Sentinel/OPA, and CI/CD plan/apply workflows. Use when: user wants to design Terraform modules, manage state backends, review Terraform security, implement multi-region deployments, or follow IaC best practices.

    The same file is in 1 other repository

  • Write a skill

    timdevai/proteus/skills/community/from-alireza/engineering/write-a-skill/skills/write-a-skill Skill

    1★ repo

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.

    The same file is in 3 other repositories

  • Finance skills

    timdevai/proteus/skills/community/from-alireza/finance/skills/finance-skills Skill

    1★ repo

    Financial analyst agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Ratio analysis, DCF valuation, budget variance, rolling forecasts. 4 Python tools (stdlib-only).

    The same file is in 1 other repository

  • Ai seo

    timdevai/proteus/skills/community/from-alireza/marketing-skill/skills/ai-seo Skill

    1★ repo

    Optimize content to get cited by AI search engines — ChatGPT, Perplexity, Google AI Overviews, Claude, Gemini, Copilot. Use when you want your content to appear in AI-generated answers, not just ranked in blue links. Triggers: 'optimize for AI search', 'get cited by ChatGPT', 'AI Overviews', 'Perplexity citations', 'AI SEO', 'generative search', 'LLM visibility', 'GEO' (generative engine optimization). NOT for traditional SEO ranking (use seo-audit). NOT for content creation (use content-production).

    The same file is in 1 other repository

  • Marketing skills

    timdevai/proteus/skills/community/from-alireza/marketing-skill/skills/marketing-skills Skill

    1★ repo

    42 marketing agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more coding agents. 7 pods: content, SEO, CRO, channels, growth, intelligence, sales. Foundation context + orchestration router. 27 Python tools (stdlib-only).

    The same file is in 1 other repository

  • Prompt engineer toolkit

    timdevai/proteus/skills/community/from-alireza/marketing-skill/skills/prompt-engineer-toolkit Skill

    1★ repo

    Analyzes and rewrites prompts for better AI output, creates reusable prompt templates for marketing use cases (ad copy, email campaigns, social media), and structures end-to-end AI content workflows. Use when the user wants to improve prompts for AI-assisted marketing, build prompt templates, or optimize AI content workflows. Also use when the user mentions 'prompt engineering,' 'improve my prompts,' 'AI writing quality,' 'prompt templates,' or 'AI content workflow.'

    The same file is in 1 other repository

  • Research summarizer

    timdevai/proteus/skills/community/from-alireza/product-team/research-summarizer/skills/research-summarizer Skill

    1★ repo

    Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation. Extracts key findings, generates comparative analyses, and produces properly formatted citations. Use when: user wants to summarize a research paper, compare multiple sources, extract citations from documents, or create structured research briefs. Plugin for Claude Code, Codex, Gemini CLI, and OpenClaw.

    The same file is in 2 other repositories

  • Pm skills

    timdevai/proteus/skills/community/from-alireza/project-management/skills/pm-skills Skill

    1★ repo

    6 project management agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Senior PM, scrum master, Jira expert (JQL), Confluence expert, Atlassian admin, template creator. MCP integration for live Jira/Confluence automation.

    The same file is in 1 other repository

  • Ra qm skills

    timdevai/proteus/skills/community/from-alireza/ra-qm-team/skills/ra-qm-skills Skill

    1★ repo

    12 regulatory & QM agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. ISO 13485 QMS, MDR 2017/745, FDA 510(k)/PMA, ISO 27001 ISMS, GDPR/DSGVO, risk management (ISO 14971), CAPA, document control, auditing. Python tools (stdlib-only).

    The same file is in 1 other repository

  • Claude memory kit

    timdevai/proteus/skills/community/from-rohitg00/claude-memory-kit Skill

    1★ repo

    Persistent memory system for Claude Code. Two-layer architecture (hot cache + knowledge wiki), safety hooks, /close-day end-of-day synthesis. Zero external dependencies.

  • Deep dive

    timdevai/proteus/skills/community/from-rohitg00/deep-dive Skill

    1★ repo

    Claude-native deep research using DAG-based query planning, parallel subagent execution, and gap-driven iteration. No external API needed.

    The same file is in 1 other repository

  • Llm integration

    timdevai/proteus/skills/community/from-rohitg00/llm-integration Skill

    1★ repo

    LLM integration patterns including API usage, streaming, function calling, RAG pipelines, and cost optimization

  • Manage skills

    timdevai/proteus/skills/community/from-rohitg00/manage-skills Skill

    1★ repo

    Discover, list, create, edit, toggle, copy, move, and delete AI agent skills across 11 tools (Cursor, Claude, Agents, Windsurf, Copilot, Codex, Cline, Aider, Continue, Roo Code, Augment)

  • Mcp development

    timdevai/proteus/skills/community/from-rohitg00/mcp-development Skill

    1★ repo

    MCP server development including tool design, resource endpoints, prompt templates, and transport configuration

  • Prompt engineering

    timdevai/proteus/skills/community/from-rohitg00/prompt-engineering Skill

    1★ repo

    Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt design

  • Mcp finder

    timdevai/proteus/skills/mcp-finder Skill

    1★ repo

    Always-on multi-agent AI workstation for Claude Code. 142 specialist agents (ML, security, K8s, backend, frontend) · 366 curated skills · 200+ prompt templates · auto prompt-matcher · auto skill-matcher · MCP support · token router cuts Anthropic bill 6x via Kimi/Haiku/Ollama. LiteLLM · BYOK · MIT + Apache. One-line install.

  • Prompt matcher

    timdevai/proteus/skills/prompt-matcher Skill

    1★ repo

    Always-on multi-agent AI workstation for Claude Code. 142 specialist agents (ML, security, K8s, backend, frontend) · 366 curated skills · 200+ prompt templates · auto prompt-matcher · auto skill-matcher · MCP support · token router cuts Anthropic bill 6x via Kimi/Haiku/Ollama. LiteLLM · BYOK · MIT + Apache. One-line install.

  • Improving instructions

    pgoell/pgoell-claude-tools/plugins/agent-system-management/skills/improving-instructions Skill

    1★ repo

    Audit and improve AGENTS.md and CLAUDE.md files across project and user scopes.

  • Claude codex bridge

    pgoell/pgoell-claude-tools/plugins/runtime-bridge/skills/claude-codex-bridge Skill

    1★ repo

    Align Claude Code and Codex project files, settings, hooks, agents, and plugins.

  • Copilot

    pgoell/pgoell-claude-tools/plugins/workbench/skills/copilot Skill

    1★ repo

    Use when the user wants semi-autonomous, human-in-the-loop feature shipping where the user drives the brainstorm and spec by hand and the agent (the copilot) automates the plan, implementation, docs, audit, and PR using .workbench/autopilot.md. The interactive sibling of workbench:autopilot.

  • Dispatching parallel agents

    pgoell/pgoell-claude-tools/plugins/workbench/skills/dispatching-parallel-agents Skill

    1★ repo

    Use when facing two or more independent tasks that can be worked on concurrently without shared state or sequential dependencies.

  • Subagent driven development

    pgoell/pgoell-claude-tools/plugins/workbench/skills/subagent-driven-development Skill

    1★ repo

    Collection of my personal claude skills

  • Oatda vision analysis

    devcsde/oatda-skills/skills/oatda-vision-analysis Skill

    1★ repo

    Use when the user wants to analyze images using vision-capable AI models through OATDA's unified API. Supports OpenAI GPT-4o, Anthropic Claude, and Google Gemini vision models.

  • Repo safety audit

    beginnersinai/claude-skills-marketplace/plugins/repo-safety-audit/skills/repo-safety-audit Skill

    no license1★ repo

    Audit a GitHub repository, Claude Code skill, plugin, or npm package for prompt injection, code exfiltration, and supply-chain risk before trusting or installing it. Use when the user pastes a GitHub URL and asks whether it's safe, wants to evaluate a skill/plugin before installing, says "audit this repo", "is this safe", "should I install", "check this github", "vet this plugin", "review this repo", or similar vetting requests. Also use proactively immediately after installing any third-party skill, plugin, or MCP server from a source the user hasn't used before.

  • Subagent research reliability

    MrBinnacle/skills/skills/orchestration/subagent-research-reliability Skill

    1★ repo

    Reliability checks for web-research subagents. Pre-dispatch, verify the agent's tool grant actually includes web tools (else it no-ops or fabricates). Post-return, verify every citation before acting.

  • Prompt mx

    migaceta/skills-claude-derecho-mx/prompt-mx Skill

    no license1★ repo

    Convierte una petición vaga sobre una tarea legal mexicana en un prompt CPTF (Contexto + Persona + Tarea + Formato) bien estructurado. Pregunta lo que falta antes de generar el prompt final. Usar cuando el usuario describe una tarea legal en términos genéricos ("redáctame una contestación", "ayúdame con un amparo", "revisa este contrato") y necesita convertirla en una instrucción precisa para Claude, ChatGPT o Gemini.

  • Llm wiki

    fralapo/awesome-agent-skills/skills/llm-wiki Skill

    1★ repo

    Use when user wants to build/maintain a personal knowledge base in Obsidian using the LLM Wiki pattern (Andrej Karpathy). Triggers on "obsidian", "llm wiki", "/llm-wiki", "init wiki", "ingest sources", "compile knowledge base", "inizializza wiki", "second brain", "pkm", or when working in a directory containing an Obsidian vault (`.obsidian/` folder) and user references knowledge-base, research-notes, or wiki accumulation work. Also use when user asks about RAG alternatives for curated personal corpora.

  • Si live

    bfowle/spirit-island/skills/si-live Skill

    no license1★ repo

    Launch + interact with the interactive Spirit Island board-state tool. State lives at data/current-game.json and is shared between the web UI, this skill, and (Phase B onward) the MCP server.

  • Fleet

    thepictishbeast/claude-tools/skills/fleet Skill

    1★ repo

    Orchestrate the PlausiDen agent fleet (Conductor + worker swarm). Validate a multi-agent plan's scope-disjointness, dispatch a run, run the verify/burn gates, inspect live status or an individual worker, and engage/clear the global STOP. Use when the user wants to run, plan, gate, inspect, or stop the fleet, or open the fleet console. Heavy ops defer to the `fleet` MCP server.

  • Forge

    thepictishbeast/claude-tools/skills/forge Skill

    1★ repo

    Build, audit, deploy, and reason about the Forge + Loom + Crawler substrate. Token-efficient subcommand surface, structured JSON output; reach for these before bash/grep. Use in any tenant or substrate repo. Heavy ops defer to the `forge` MCP server.

  • Prompt injection

    sunilgentyala/OmniRed/skills/ai-native/prompt-injection Skill

    no license1★ repo

    Expert methodology for testing direct and indirect prompt injection vulnerabilities in LLM-powered applications, agents, and pipelines. Covers payload construction, context manipulation, cross-agent propagation, and exfiltration triggers.

  • System prompt extraction

    sunilgentyala/OmniRed/skills/ai-native/system-prompt-extraction Skill

    no license1★ repo

    Methodology for recovering hidden system prompts from LLM-based products. Covers direct extraction, differential probing, and reconstruction from partial leaks. Relevant for competitive intelligence assessments and prompt confidentiality evaluations.

  • Embedding attacks

    sunilgentyala/OmniRed/skills/llm-pipeline/embedding-attacks Skill

    no license1★ repo

    Adversarial embedding manipulation techniques for attacking vector search, semantic similarity systems, and embedding-based security controls. Covers nearest-neighbour poisoning, semantic collision, and bypass of embedding-based filters.