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

  • Rag poisoning

    sunilgentyala/OmniRed/skills/llm-pipeline/rag-poisoning Skill

    no license1★ repo

    Expert methodology for attacking Retrieval-Augmented Generation (RAG) pipelines through document poisoning, index corruption, adversarial queries, and retrieval manipulation. For authorized red team assessments of AI search and Q&A systems.

  • Context injection

    sunilgentyala/OmniRed/skills/mcp/context-injection Skill

    no license1★ repo

    Methodology for injecting malicious content into MCP tool return values and resource outputs to manipulate connected LLM agent behaviour. Covers cross-server propagation and multi-agent pipeline compromise.

  • Rug pull

    sunilgentyala/OmniRed/skills/mcp/rug-pull Skill

    no license1★ repo

    Methodology for testing rug pull attacks against MCP servers — capability changes after initial attestation that the connected LLM cannot detect. Covers detection, reproduction, and impact assessment.

  • Insight clarity

    natthasath/natthasath-marketplace/plugins/insight/skills/insight-clarity Skill

    1★ repo

    A Claude Code plugin marketplace bundling 12 plugins and 54 skills across PKM, project planning, DevOps, content writing, language, design, and productivity — install with a single command and start using slash commands right away.

  • Orchestrator

    HumanBean17/agent-mindset-skills/orchestrator Skill

    no license1★ repo

    Use for long-running sessions with large amounts of parallelizable work.

  • Ai agent skills update

    whobat/AI-Agent-skills/skills/repo-tooling/ai-agent-skills-update Skill

    1★ repo

    Update skills installed FROM THE AI-Agent-skills GitHub REPO (github.com/whobat/AI-Agent-skills) to their latest published versions — it does not touch skills from any other source (plugins, other repos, hand-written skills). Runs the repo installer in update mode across Claude Code, Codex, and OpenCode, installs nothing new, and preserves local config.json files. Use when the user says "update my AI-Agent-skills", "update my skills from the repo", "opdater skills", "are my skills up to date?", or after being told a skill from this repo has a new version.

  • Viral hook generator

    calebvbi/creator-skills-samples/skills/viral-hook-generator Skill

    no license1★ repo

    Get 5 scroll-stopping hooks for any video topic in under 2 minutes. Built on 12 proven archetypes for Shorts, Reels, and TikToks.

  • Prompt alignment audit

    itzTiru/claude-code-skills-fable5/prompt-alignment-audit Skill

    no license1★ repo

    Use when reviewing, auditing, or optimizing any LLM prompt (system prompt, extraction prompt, template) against provider guidance — when a prompt underperforms, after a model upgrade or version switch, before shipping a new production prompt, or when asked whether a prompt follows current Anthropic/OpenAI/Gemini best practices. Also use when asked to "check my prompt", "improve this prompt", or fetch the latest prompting guidance (--refresh).

  • Cdx sol

    dT-Tb-labs/babel-orchestration/skills/cdx-sol Skill

    1★ repo

    Use when the user invokes /cdx-sol or wants to send a task to GPT-5.6-SOL (OpenAI's Codex model) from Claude Code stably and token-efficiently. Wraps codex-companion via cdx-sol.mjs — background+poll for 120s-timeout safety, read-only by default, effort-tier + terse-output token control. Runs on the ChatGPT subscription (no per-token API billing).

  • Memory onboard

    tmj-90/gaffer/packages/memory/skills/memory-onboard Skill

    1★ repo

    Use this skill when the user types `/memory-onboard` (or asks "set up memory for this repo" / "onboard this repo to memory" / "what should be in lore for this repo?"). It runs a repo-aware onboarding interview that produces DRAFT lore records grounded in concrete repo signals (README, ADRs, recent commits, deprecation markers, in-flight migrations). Requires the memory-mcp MCP server to be configured. Uses these MCP tools: search_lore / get_lore / suggest_lore (core), and optionally report_conflict (when a candidate item contradicts existing lore) and record_absence (when the user confirms a topic has no team policy yet). All suggest_lore / report_conflict output lands as drafts — the human approves via `memory review` afterwards. record_absence markers self-expire (default 14 days) and don't need review.

  • Aeo

    tmj-90/gaffer/runner/skills/aeo Skill

    1★ repo

    Use when optimising content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini) as an authoritative source — distinct from SEO. Triggers on "AEO audit", "optimize for ChatGPT", "get cited by Perplexity", "LLM citation strategy", "answer engine optimization", "content for AI search", or "E-E-A-T audit". For click-through SEO, use `seo-audit`. For structured data, use `schema-markup`.

  • Multi agent batch campaigns

    HamzaYM/reliable-ai-skills/skills/campaign-execution/multi-agent-batch-campaigns Skill

    1★ repo

    Use when executing a large backlog of review findings or a multi-part feature as coordinated batches across parallel agents or sessions, planning waves, avoiding file-contention collisions, and resuming a campaign that a previous session left mid-way through.

  • Llm eval harness and scoring pipeline

    HamzaYM/reliable-ai-skills/skills/evals-and-scoring/llm-eval-harness-and-scoring-pipeline Skill

    1★ repo

    Use when building or changing a pipeline that scores, grades, or extracts structured output from an LLM in production: composite/aggregate scoring math, partial-failure handling when one sub-call fails, prompt versioning, an eval harness that makes real model calls, or comparing a candidate model/prompt against production without flipping it live.

  • Llm red team

    fevziegeyurtsevenler/llm-security-skills/skills/llm-red-team Skill

    1★ repo

    Systematic LLM red-teaming across the OWASP LLM Top 10 (2025). Use when assessing an LLM app, chatbot, RAG pipeline, or agent for prompt injection, data leakage, output-handling flaws, excessive agency, or unbounded consumption, and when producing a structured, evidence-backed red-team report.

  • Mcp security review

    fevziegeyurtsevenler/llm-security-skills/skills/mcp-security-review Skill

    1★ repo

    Agent Skills that turn your AI coding agent into an LLM security reviewer — prompt-injection testing, OWASP LLM Top 10 audits, MCP & RAG review, KVKK/PII checks. English + Turkish.

  • Owasp llm top10 audit

    fevziegeyurtsevenler/llm-security-skills/skills/owasp-llm-top10-audit Skill

    1★ repo

    Audit an LLM application against the OWASP Top 10 for LLM Applications (2025) using a per-item checklist that records what to check, the evidence to collect, and a concrete mitigation. Use when reviewing an LLM/agent/RAG feature before launch, during a security review, or when asked to produce an OWASP-mapped risk report for an AI system.

  • Prompt injection tester

    fevziegeyurtsevenler/llm-security-skills/skills/prompt-injection-tester Skill

    1★ repo

    Systematically tests an LLM app, agent, RAG pipeline, or endpoint for prompt injection (direct + indirect) using English and Turkish payload families, separates real attack success from over-refusal, and maps every finding to OWASP LLM01 and MITRE ATLAS. Use when auditing a chatbot, tool-using agent, or LLM-backed API for injection and system-prompt-leakage resistance before or after deployment.

  • Rag security review

    fevziegeyurtsevenler/llm-security-skills/skills/rag-security-review Skill

    1★ repo

    Audits a Retrieval-Augmented Generation (RAG) pipeline for indirect prompt injection (OWASP LLM01), knowledge-base/data poisoning (LLM04), retrieval access-control and tenant-isolation gaps (LLM02/LLM08), and citation/grounding integrity (LLM09). Use when auditing, designing, threat-modeling, or hardening any system that retrieves documents and places their text into an LLM's context window — chatbots over internal docs, agentic search, customer-support assistants, code/knowledge assistants.

  • Executor

    makieali/claude-code-engineer/skills/executor Skill

    1★ repo

    Implements a plan created by /architect. Reads the plan, claims a phase, works one task at a time in an isolated branch or worktree, verifies externally, commits, and records state in its own single-writer file. Designed for multi-agent parallel execution. Trigger: "execute the plan", "implement phase", "continue the plan", "work on next task", "pick up where we left off".

  • Handoff

    makieali/claude-code-engineer/skills/handoff Skill

    1★ repo

    Writes a session handoff to disk before a context reset — what's done, what changed, what was decided, what was ruled out, and the single next step — then tells you whether to /clear or /compact. Use when a session is getting long or slow, before compacting, at the end of a work block, or when handing work to another person or session. Trigger: "write a handoff", "save progress", "save state", "session is getting slow", "before I compact", "wrap up", "I'm stopping here".

  • Workflow orchestrator

    FarzamMohammadi/dev-toolbox/ai/claude-code/skills/workflow-orchestrator Skill

    no license1★ repo

    Take on a substantial, multi-step effort as a strategic orchestrator — intake the goal, research and plan it solo, execute it through parallel/sequential agent workflows, then personally verify the result end to end. Use this whenever the user wants to tackle something big or ambitious: a large feature, a cross-cutting refactor, a migration, a codebase-wide audit, a "do all of X / sync everything / overhaul Y" task, or any effort that won't fit in one pass and needs to be planned and orchestrated with rigor. Trigger when the user invokes it by name, says things like "orchestrate this / run a workflow / use subagents / plan and build this / take this on end to end," OR simply describes a meaty multi-part task and wants it done thoroughly and efficiently — even if they never say the words "workflow" or "orchestrate." Do NOT use it for small, single-step tasks that one pass handles directly.

  • Skill

    morganmuli/metaskill/skill Skill

    1★ repo

    The meta-skill: create AI agent teams, individual agents, or custom skills for any project. Use when the user wants to generate a complete .claude/ agent team, create a single agent, or create a single skill.

    The same file is in 1 other repository

  • Spec driven prompt

    vintagedon/claude-skills-cookbook/skills/spec-driven-prompt Skill

    no license1★ repo

    Generate bounded work unit specs for agent execution on ML01. Use when orchestrator (Claude) has completed RAV discussion and is ready to hand off a discrete coding or infrastructure task. Produces spec-driven prompts with deliverable/validation pairs that give the agent implementation freedom within clear boundaries. Specs live at /opt/agents/spec/ and produce matching worklogs at /opt/agents/work-logs/. Works with any executor (Codex, Claude Code, OpenCode, Gemini) but defaults toward Codex workflows.

  • Shipkit claude md

    stefan-stepzero/shipkit/install/skills/shipkit-claude-md Skill

    1★ repo

    Update CLAUDE.md with learnings, preferences, or project context. Use when user says "update claude.md", "add to claude.md", or wants to persist something.

  • Shipkit prompt audit

    stefan-stepzero/shipkit/install/skills/shipkit-prompt-audit Skill

    1★ repo

    Audit LLM prompt pipeline architecture — decomposition, parallelization, chain integrity, schema validation, fallback paths. Finds structural issues no linter catches.

  • Shipkit work memory

    stefan-stepzero/shipkit/install/skills/shipkit-work-memory Skill

    1★ repo

    Log session progress and save resume state. Infers from conversation and git. Triggers: 'log progress', 'session summary', 'checkpoint', 'save progress', 'end session'.

  • Claude code cli integration

    wrm3/ai_project_template/.claude/skills/claude-code-cli-integration Skill

    1★ repo

    Enable Claude Code to leverage its own CLI for unrestricted system access, bypassing VS Code extension permission limitations

  • Computer use agent

    wrm3/ai_project_template/.claude/skills/computer-use-agent Skill

    1★ repo

    AI-powered desktop automation using screenshots and vision-guided actions to control any desktop application

  • Hanx knowledge base

    wrm3/ai_project_template/.claude/skills/hanx-knowledge-base Skill

    1★ repo

    Document ingestion and semantic search with RAG capabilities. Supports PDF, DOCX, MD, TXT, CSV, HTML, and JSON. Combines intelligent chunking, vector embeddings, and persistent storage for building searchable knowledge bases.

  • Mcp builder

    wrm3/ai_project_template/.claude/skills/mcp-builder Skill

    1★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

    The same file is in 18 other repositories

  • Skill creator

    wrm3/ai_project_template/.claude/skills/skill-creator Skill

    1★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

  • Youtube rag storage

    wrm3/ai_project_template/.claude/skills/youtube-rag-storage Skill

    1★ repo

    Ingest YouTube content into vector database with embeddings for semantic search and RAG. Combines video download, transcription, chunking, embedding generation, and Supabase storage for intelligent content retrieval.

  • Hanx knowledge base

    wrm3/ai_project_template/plugins/fstrent-research-toolkit/skills/hanx-knowledge-base Skill

    1★ repo

    Document ingestion and semantic search with RAG capabilities. Supports PDF, DOCX, MD, TXT, CSV, HTML, and JSON. Combines intelligent chunking, vector embeddings, and persistent storage for building searchable knowledge bases.

  • Youtube rag storage

    wrm3/ai_project_template/plugins/fstrent-research-toolkit/skills/youtube-rag-storage Skill

    1★ repo

    Ingest YouTube content into vector database with embeddings for semantic search and RAG. Combines video download, transcription, chunking, embedding generation, and Supabase storage for intelligent content retrieval.

  • Computer use agent

    wrm3/ai_project_template/plugins/fstrent-web-toolkit/skills/computer-use-agent Skill

    1★ repo

    AI-powered desktop automation using screenshots and vision-guided actions to control any desktop application

  • Claude code plugins

    JamesPrial/claude-plugins/claude-code-guide/skills/claude-code-plugins Skill

    1★ repo

    Contains all relevant documentation for Claude Code Plugins. ALWAYS PROACTIVELY use when working on or with plugins, hooks, skills, MCP servers, or settings.

  • Claude code slash commands

    JamesPrial/claude-plugins/slash-command-guide/skills/claude-code-slash-commands Skill

    1★ repo

    Create custom slash commands for Claude Code. Use when the user wants to create, generate, or build a slash command (.md file) for Claude Code, or when they ask about slash command syntax, frontmatter options, argument handling, or want help organizing their commands. Triggers on phrases like "make a slash command", "create a command for Claude Code", "write a /command", or questions about $ARGUMENTS, allowed-tools, or command frontmatter.

    The same file is in 3 other repositories

  • Claude md optimizer

    Goodsmileduck/claude-registry/plugins/claude-md-optimizer/skills/claude-md-optimizer Skill

    1★ repo

    Analyzes and optimizes CLAUDE.md files following Anthropic's official best practices. Use when reviewing existing CLAUDE.md for improvements, or when user mentions CLAUDE.md is too long or ineffective.

  • Cloudflare access mcp

    Goodsmileduck/claude-registry/plugins/cloud-platform-skills/skills/cloudflare-access-mcp Skill

    1★ repo

    Adds OAuth/SSO to a remote MCP server using Cloudflare. Three paths — AI Controls MCP Portal (REST, fastest), self-hosted Access app with Managed OAuth (REST), and the same as Terraform (when IaC already exists) — with a decision matrix, REST recipes per path, Terraform templates for the IaC path, and a stdlib validator that lints a `terraform show -json` plan. Use when the user asks to put an MCP server behind Cloudflare, add OAuth/SSO to a remote MCP server, expose a private MCP server via Cloudflare Tunnel, register MCP servers with the AI Controls portal, enable Managed OAuth or DCR on an Access app, or wire Claude Desktop / claude.ai web / Claude Code to an internal MCP server.

  • Github security scanner hook

    nainishshafi/developer-productivity-skills/.github/skills/github-security-scanner-hook Skill

    1★ repo

    Use when the user asks to "scan for security vulnerabilities", "check for secrets in code", "set up a pre-commit security hook", "install security scanning", "scan staged files for secrets", "check for hardcoded credentials", "run a security scan before commit", "detect leaked API keys", "add a git commit hook for security", "security check before push", "scan for SQL injection", "check for XSS vulnerabilities", "detect injection flaws", or wants to prevent committing security issues to git.

  • Llm as judge

    nainishshafi/developer-productivity-skills/.github/skills/llm-as-judge Skill

    1★ repo

    Built-in LLM-as-Judge evaluation for Copilot/Claude. Score LLM responses, compare models, detect hallucinations, and verify quality—all within the agent context. No external APIs. Supports single-agent and multi-agent (sequential consensus) evaluation with improved sub-agent prompts for deeper reasoning. Use when comparing responses, validating output quality, checking for hallucinations, or performing model comparisons.

  • Skill creator

    nainishshafi/developer-productivity-skills/.github/skills/skill-creator Skill

    1★ repo

    Use when the user asks to "create a new skill", "add a skill", "write a skill", "scaffold a skill", "make a claude skill", "build a skill", or wants to create a reusable Claude Code skill from scratch. Also use when the user describes a repeatable workflow they want to package as a skill.

  • Bgskillz

    bjg4/bgskillz/bgskillz Skill

    1★ repo

    Create S-tier portable skills and agents with comprehensive quality guidance. Use when creating or improving skills, designing multi-agent orchestration workflows, auditing agent quality, running evals, or learning agent-building best practices. Covers the full lifecycle from use case definition through automated evaluation, review, and iteration. Do NOT use for general coding tasks, writing documentation unrelated to agents/skills, or building applications.

  • V4

    bjg4/bgskillz/versions/v4 Skill

    1★ repo

    Create S-tier portable skills and agents with comprehensive quality guidance. Use when creating or improving skills, designing multi-agent orchestration workflows, auditing agent quality, running evals, or learning agent-building best practices. Covers the full lifecycle from use case definition through automated evaluation, review, and iteration. Do NOT use for general coding tasks, writing documentation unrelated to agents/skills, or building applications.

  • V5

    bjg4/bgskillz/versions/v5 Skill

    1★ repo

    Create S-tier portable skills and agents with comprehensive quality guidance. Use when creating or improving skills, designing multi-agent orchestration workflows, auditing agent quality, running evals, or learning agent-building best practices. Covers the full lifecycle from use case definition through automated evaluation, review, and iteration. Do NOT use for general coding tasks, writing documentation unrelated to agents/skills, or building applications.

  • Delegate

    lklimek/claudius/skills/delegate Skill

    1★ repo

    Plugin with opinionated set of Claude Code agents nad skills

  • Grand admiral

    lklimek/claudius/skills/grand-admiral Skill

    1★ repo

    Plugin with opinionated set of Claude Code agents nad skills

  • Rewrite

    IamBiswajitSahoo/ClaudeSkills/plugins/bix-utils/skills/rewrite Skill

    1★ repo

    Rewrite prompts using proven prompt engineering frameworks — select from 20 curated frameworks or provide a custom template, then get a structured rewrite via a fast sub-agent.

  • Claude code standard

    nicholashidalgo/claude-skillforge/core/claude-code-standard Skill

    1★ repo

    Technical execution standard for all coding, data engineering, SQL, Python, and implementation work with Nicholas Hidalgo. Governs code generation, documentation rules, stack preferences, testing, and analytics engineering guidance. Layers on top of claude-operator-standard (which must be active) and does not repeat communication, troubleshooting, output format, or session behavior rules. Trigger this skill for any coding task, SQL query, Python script, dbt model, React component, data pipeline, BI logic, or technical implementation request.

  • Claude token watchdog

    nicholashidalgo/claude-skillforge/core/claude-token-watchdog Skill

    1★ repo

    Monitors conversation length to prevent context loss and token-limit exhaustion. Counts visible messages and fires at three thresholds: 15+ messages (soft, mention a handoff is available), 20+ messages (strong, recommend handoff before next task), 25+ messages (forced, automatically delegate to claude-session-handoff to generate the continuation brief). Triggers earlier (around 12 messages) when the conversation is technically dense: code, debugging, architecture decisions, file paths, repo work, terminal commands, or multi-step implementation plans. Manual command: /watchdog-check. Companion to claude-session-handoff: this skill watches and decides when, claude-session-handoff produces the actual brief. Output only at soft/strong tiers (notification text). At the forced tier, delegates to claude-session-handoff. Never creates files, runs commands, or modifies the repo.

  • Eval

    iabhisekbosepm/claude-god-setup/.claude/skills/eval Skill

    no license1★ repo

    Generate a complete Langfuse evaluation pipeline: auto-detect app type, create datasets, LLM-as-judge evaluators, scoring configs, and CI integration.

  • Claude api

    DROOdotFOO/agent-skills/skills/claude-api Skill

    1★ repo

    Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

  • Droo stack

    DROOdotFOO/agent-skills/skills/droo-stack Skill

    1★ repo

    Detailed coding patterns for a polyglot stack. TRIGGER when: working in Elixir, TypeScript, Go, Rust, Python, Lua, C, Zig, Shell/Bash, Noir, or chezmoi templates. Provides incorrect/correct examples that complement CLAUDE.md preferences. DO NOT TRIGGER when: working with Claude API or Anthropic SDK (use claude-api skill), Raxol TUI/agent framework patterns (use raxol skill), Solidity smart contracts (use solidity-auditor skill), ZK circuit domain questions (use noir skill -- this skill only covers Noir language syntax), NIF/SIMD domain questions for BEAM integration (use native-code skill -- this skill only covers C and Zig general syntax), or ffmpeg upstream / libav* assembly work (use ffmpeg-asm skill).

  • Git worktree manager

    DROOdotFOO/agent-skills/skills/git-worktree-manager Skill

    1★ repo

    Parallel development with git worktrees and deterministic port isolation. TRIGGER when: user wants to work on multiple branches simultaneously, run parallel agent sessions, manage worktree-based dev environments, or asks about port conflicts between concurrent services. DO NOT TRIGGER when: simple branch switching (use git checkout), or single-branch development with no parallelism needed.

  • Llm cost optimizer

    DROOdotFOO/agent-skills/skills/llm-cost-optimizer Skill

    1★ repo

    Analyze and reduce LLM API costs through model routing, caching, and prompt optimization. TRIGGER when: user asks about LLM costs, API spend reduction, token optimization, model routing, or prompt caching. DO NOT TRIGGER when: user asks about model quality comparison, fine-tuning, or general prompt engineering.

  • Mcp server builder

    DROOdotFOO/agent-skills/skills/mcp-server-builder Skill

    1★ repo

    Scaffold MCP servers from OpenAPI specs. TRIGGER when: user asks to build an MCP server, convert an OpenAPI/Swagger spec to MCP tools, generate MCP tool definitions, or scaffold a FastMCP/TypeScript MCP project. DO NOT TRIGGER when: user is configuring an existing MCP server, writing MCP clients, or working with Claude API directly (use claude-api skill).

  • Rag architect

    DROOdotFOO/agent-skills/skills/rag-architect Skill

    1★ repo

    Design RAG pipelines with informed chunking, embedding, retrieval, and evaluation decisions. TRIGGER when: user asks about RAG pipeline design, chunking strategies, embedding models, vector databases, or retrieval-augmented generation. DO NOT TRIGGER when: user asks about fine-tuning, prompt engineering without retrieval, or general LLM usage.

  • Raxol payments

    DROOdotFOO/agent-skills/skills/raxol-payments Skill

    1★ repo

    Agentic commerce for Raxol agents in Elixir: the raxol_payments + raxol_acp packages (Xochi/Riddler/MPP/Permit2/x402 protocols, agent wallets, spend limits, stealth + privacy tiers, ZKSAR trust scores, and the ACP job lifecycle). TRIGGER when: mix.exs lists :raxol_payments or :raxol_acp; code imports Raxol.Payments.* or Raxol.ACP.*; user asks about agent wallets, HTTP 402 auto-pay, Xochi/Riddler cross-chain transfers, stealth addresses / privacy tiers, ZKSAR attestations, spend gating, or the ACP (Agent Commerce Protocol) job state machine / offerings. DO NOT TRIGGER when: writing or auditing Solidity contracts (use solidity-auditor skill); general Ethereum tooling / RPC / explorer questions (use ethskills skill); ZK circuit design in Noir (use noir skill); the core Raxol agent/TUI framework (use raxol skill); the Symphony orchestrator (use raxol-symphony skill).

  • Raxol symphony

    DROOdotFOO/agent-skills/skills/raxol-symphony Skill

    1★ repo

    Symphony: the Raxol tracker-driven coding-agent orchestrator (raxol_symphony, pre-alpha). Turns tracker issues into autonomous agent runs in isolated workspaces, surfaces evidence (CI/PR/asciinema), and supports human-in-the-loop paused runs across six surfaces. TRIGGER when: mix.exs lists :raxol_symphony; code imports Raxol.Symphony.*; there is a WORKFLOW.md driving an orchestrator; user asks about tracker-driven agent orchestration, Symphony runners (RaxolAgent/Codex), evidence capture, or paused-run resume with Raxol. DO NOT TRIGGER when: building a single Raxol agent or the core framework (use raxol skill); agent payments / ACP job sessions (use raxol-payments skill); generic multi-agent system design without Symphony (use agent-designer skill); the Claude Agent SDK (use claude-api).

  • Raxol

    DROOdotFOO/agent-skills/skills/raxol Skill

    1★ repo

    Raxol terminal framework for TUI apps and AI agents in Elixir (v2.6, 15-package monorepo). TRIGGER when: code imports Raxol modules (Raxol.Agent, Raxol.Core, Raxol.MCP, Raxol.LiveView, Raxol.Workflow, Raxol.Headless), mix.exs lists :raxol / :raxol_agent / :raxol_core / :raxol_mcp as a dependency, user asks about building TUI apps or AI agents with Raxol, agent memory/self-improvement, the workflow engine, or Raxol headless/MCP tools. DO NOT TRIGGER when: general Elixir patterns (use droo-stack skill), Claude API / Anthropic SDK usage (use claude-api skill), agentic commerce / payments / ACP job sessions (use raxol-payments skill), the Symphony coding-agent orchestrator (use raxol-symphony skill), or other TUI frameworks (Scenic, Termbox, etc.).