agentsclimarketplace

Context & AI engineering

25,729 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

  • Sync skills

    timi-ty/agent-forge/skills/sync-skills Skill

    0★ repo

    Sync locally installed agent skills to match a branch of the cursor-forge repo. Works with both Cursor and Claude Code. Handles first-time installs and subsequent updates in one flow. Use when the user pastes a github.com/timi-ty/cursor-forge URL, or says "install skills", "update skills", "sync skills", or "install cursor skills".

  • Memory skill

    Mickos79/aria-skills/memory-skill Skill

    no license0★ repo

    Production AI agent skills for OpenClaw — extracted from a real personal AI OS. RAG memory, safety guards, cost tracking, architect agent and more.

  • Skill creator

    ThiagoPanini/aidriven/.claude/skills/skill-creator Skill

    0★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Skill creator

    ThiagoPanini/aidriven/.github/skills/skill-creator Skill

    0★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Agent memory mcp

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/agent-memory-mcp Skill

    no license0★ repo

    A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

    The same file is in 3 other repositories

  • Ai agents architect

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/ai-agents-architect Skill

    no license0★ repo

    Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling.

    The same file is in 3 other repositories

  • Autonomous agent patterns

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/autonomous-agent-patterns Skill

    no license0★ repo

    Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.

    The same file is in 3 other repositories

  • Context fundamentals

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/context-fundamentals Skill

    no license0★ repo

    This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.

    The same file is in 5 other repositories

  • Context window management

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/context-window-management Skill

    no license0★ repo

    Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context.

    The same file is in 3 other repositories

  • Dispatching parallel agents

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/dispatching-parallel-agents Skill

    no license0★ repo

    Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    The same file is in 15 other repositories

  • Evaluation

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/evaluation Skill

    no license0★ repo

    This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.

    The same file is in 4 other repositories

  • Filesystem context

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/filesystem-context Skill

    no license0★ repo

    This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.

    The same file is in 1 other repository

  • Llm app patterns

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/llm-app-patterns Skill

    no license0★ repo

    Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

    The same file is in 5 other repositories

  • Mcp builder

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/mcp-builder Skill

    no license0★ 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 42 other repositories

  • Memory systems

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/memory-systems Skill

    no license0★ repo

    Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for agents", "track entities over time", "add long-term memory", "choose a memory framework", or mentions temporal knowledge graphs, vector stores, entity memory, or memory benchmarks (LoCoMo, LongMemEval).

  • Multi agent patterns

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/multi-agent-patterns Skill

    no license0★ repo

    This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.

    The same file is in 4 other repositories

  • Project development

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/project-development Skill

    no license0★ repo

    This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.

    The same file is in 4 other repositories

  • Prompt engineer

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/prompt-engineer Skill

    no license0★ repo

    Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design.

    The same file is in 2 other repositories

  • Skill builder

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/skill-builder Skill

    no license0★ repo

    Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.

    The same file is in 2 other repositories

  • Sparc methodology

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/sparc-methodology Skill

    no license0★ repo

    SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration

    The same file is in 3 other repositories

  • Subagent driven development

    uncfreak1255-code/sawyer-skills-legacy/.claude/skills/subagent-driven-development Skill

    no license0★ repo

    Use when executing implementation plans with independent tasks in the current session

    The same file is in 7 other repositories

  • Project ui pattern memory

    AmrMohamad/figma-to-ios-ui/figma-to-ios-ui/subskills/project-ui-pattern-memory Skill

    no license0★ repo

    Inspect a target iOS codebase and derive a task-local UI pattern memory brief for `figma-to-ios-ui`, covering composition, design system, shared primitives, state ownership, navigation or presentation ownership, and SwiftUI or hybrid seams. Use when the repo needs project-specific adaptation but you do not want to bake static overlays into the public skill.

  • Skill builder

    sidtheone/claude-skill-template/skill-builder Skill

    0★ repo

    Guides building and testing conversational Claude skills. Use when creating a new skill, reviewing an existing skill, or iterating on skill design. Trigger when users say things like "create a new skill", "build a skill", "review this skill", or "make this skill better."

  • Context engineering

    idimsh/tdds-business-skills/context-engineering Skill

    no license0★ repo

    Design, audit, and optimize how AI agents receive and manage context. Use when writing, editing, or optimizing commands, skills, sub-agent prompts, project instruction files, or retrieval pipelines.

  • Prompt engineering

    idimsh/tdds-business-skills/prompt-engineering Skill

    no license0★ repo

    Use this skill when writing commands, hooks, skills for AI agents, sub-agent prompts, or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.

  • Use firecrawl

    arendon1/agent-skills/domain/use-firecrawl Skill

    0★ repo

    Spin a fully local containerized Firecrawl instance wired to OpenRouter for LLM + embeddings, verify Docker can mount it, and wire it to whatever harness the agent is running in (Hermes, Pi, OpenCode, or generic). Use when the user says "spin a local Firecrawl", "self-host Firecrawl", "give me web crawling", "set up web_search/web_extract locally", or wants crawling/scraping without paying Firecrawl SaaS. Defaults: deepseek/deepseek-v4-pro for LLM, qwen/qwen3-embedding-8b for embeddings — both via OpenRouter. Asks for the OpenRouter API key interactively. Detects the harness and writes the wiring to the right place.

  • Handoff

    arendon1/agent-skills/process/handoff Skill

    0★ repo

    Compact the current session into a handoff document so another agent (or a fresh session) can continue the work. Captures goal, state, decisions, next steps, and pointers to artifacts. Does not duplicate content already in artifacts. Use when ending a session mid-plan, or when handing work to another agent, or when the user says "handoff", "compact this", "I'm leaving", "pass this to another agent", "save state for later", "wrap up".

  • Orchestrator

    kkunkunya/academic-deweight-suite/plugins/academic-deweight-suite/skills/orchestrator Skill

    no license0★ repo

    学术降重主编排器。用于论文、学位论文、基金文本、技术报告的去 AI 味/降重流程;按短文本或长文路线强制执行文意锚定、全量模式扫描、真人写作实践卡绑定、锚点约束改写和残留验收。触发关键词:学术降重、论文降重、去 AI 味、AIGC 检测、academic deweight、母骨架诊断、长文扫描、真人写法锚点。不用于个人口语化改写(那是 deweight-suite:ai-deweight-personal)。

  • Rating prompt strategy

    appalize/aso-skills/skills/rating-prompt-strategy Skill

    0★ repo

    When the user wants to improve their app's star rating, increase ratings volume, optimize when and how they prompt users for a review, or recover from a bad rating period. Use when the user mentions "app rating", "star rating", "review prompt", "SKStoreReviewRequest", "In-App Review API", "ask for review", "low rating", "rating drop", "get more reviews", or "recover from 1-star". For responding to reviews, see review-management. For overall ASO health, see aso-audit.

    The same file is in 2 other repositories

  • Printr tokenized agent

    AIEngineerX/printr-agent-skills/printr-tokenized-agent Skill

    0★ repo

    Build a tokenized-agent revenue loop on a Printr POB token. Composes `printr-agent-payments` (accept user SOL/USDC for agent actions) with `printr-swap` (Jupiter buyback) and adds SPL `burn` plus a scheduled hourly cycle, all under the creator's own treasury. On Printr POB-model-1 tokens the buyback contributes to the DAMM v2 pool's LP-fee accrual, which Printr's POB program distributes to stakers asynchronously — the buyback both reduces supply and feeds the pool that downstream stakers draw from (second-order effect, not a per-swap hook). Triggers on "Printr tokenized agent", "agent revenue burn", "buyback and burn for a Printr POB token", "first tokenized agent on Printr", or when composing the `printr-swap` + `printr-agent-payments` skills into one loop.

  • Ai eval regression tester

    sisodiabhumca/agent-skills/skills/ai-eval-regression-tester Skill

    0★ repo

    Use to run a regression eval suite over an LLM application — fixed test cases with deterministic graders (exact match, JSON schema, regex, embedding similarity, LLM-as-judge). Compares the candidate model/prompt against a baseline and gates a release on pass rate + per-tag thresholds.

  • Ai prompt regression tracker

    sisodiabhumca/agent-skills/skills/ai-prompt-regression-tracker Skill

    0★ repo

    Vendor-neutral skill to track prompt regressions across model versions with tagged eval outcomes.

  • Oncall handoff summarizer

    sisodiabhumca/agent-skills/skills/oncall-handoff-summarizer Skill

    0★ repo

    Vendor-neutral skill to summarize on-call handoffs with open incidents, risks, and follow-up tasks.

  • Prompt injection risk linter

    sisodiabhumca/agent-skills/skills/prompt-injection-risk-linter Skill

    0★ repo

    Vendor-neutral skill to lint agent prompts and untrusted retrieved content for prompt-injection risk patterns and missing safety boundaries.

  • Cli agent patterns

    rynhardt-potgieter/sprint_workflow/plugins/sprint-workflow/skills/cli-agent-patterns Skill

    0★ repo

    Use this skill when building or guiding LLM agents that interact with CLI tools. Covers decision trees for matching tasks to commands, workflow patterns, anti-patterns (excessive tool calls, ignoring cached results), and token efficiency strategies. Trigger on any task involving agent-CLI integration, tool usage optimization, or agent workflow design.

  • Codex delegation

    rynhardt-potgieter/sprint_workflow/plugins/sprint-workflow/skills/codex-delegation Skill

    0★ repo

    Codex CLI delegation patterns — eligibility criteria, available commands (/codex:rescue, /codex:adversarial-review), context passing, focus string composition from skill tags, fix routing, and model selection. Use this skill when deciding whether to delegate a task to Codex or route it to a Claude agent.

  • Worktree handoff

    rynhardt-potgieter/sprint_workflow/plugins/sprint-workflow/skills/worktree-handoff Skill

    0★ repo

    Contract for moving code OUT of a git worktree (subagent or Codex thread) back into the orchestrator's branch without losing work or manually copying files. Use this skill any time an agent is launched with `isolation: worktree`, any time `/codex:rescue` or Codex Handoff produces a branch in a separate working tree, or any time the orchestrator is about to integrate work from one or more parallel agents. Defines the subagent-side exit contract (commit, verify, emit HANDOFF block) and the orchestrator-side integration contract (parse, fetch, merge, cleanup).

  • Mcporter

    zlliang/skills/skills/mcporter Skill

    0★ repo

    Inspect and call MCP server tools from the command line with MCPorter. Use when a task needs an MCP tool (search, docs, integrations) or when checking which MCP servers and tools are available.

  • Setup handoff

    WillowRyu/agent-handoff/skills/setup-handoff Skill

    0★ repo

    Use once per project before /plan, /execute, /verify. Auto-scans the repo (manifests, agent guidance, doc tree, toolchain) and runs a short interview to write .handoff/config.md. Pass --auto to skip the interview and accept all auto-detected values, falling back to interview only for items that auto-detection cannot resolve. Part of the agent-handoff bundle (4 skills) — install /setup-handoff, /plan, /execute, /verify together.

  • Local llm sessions

    qiaoruntao/skills/local-llm-sessions Skill

    no license0★ repo

    Read, list, search, and fetch local AI coding assistant conversation history from Claude Code, Codex CLI, Gemini CLI, OpenCode, Antigravity, Cline, Cursor, Aider, and ForgeCode. Use when Codex needs to inspect local LLM sessions, compare provider history, recover prior conversation content, list recent sessions, fetch message transcripts, or understand raw local session storage formats.

  • Session learning extraction

    qiaoruntao/skills/session-learning-extraction Skill

    no license0★ repo

    Use this skill when the user asks to read, review, analyze, compare, or learn from past Codex, Claude, or other LLM sessions to extract reusable lessons, bumpy interaction patterns, best practices, rules, checklists, or future skills. This skill owns the analysis workflow after session access is available; pair it with local-llm-sessions when local transcripts must be fetched.

  • Portless dev setup

    emaarco/hogwarts/plugins/felix-felicis/skills/portless-dev-setup Skill

    0★ repo

    Adopt portless for stable, git-worktree-aware .localhost dev URLs following its documented best practices (pinned devDependency + portless.json + dev/dev:app script split — never a hand-rolled slug or sh -c wrapper), then wire it into Conductor via .conductor/settings.toml. Detects the stack first, wraps ONLY the JS/TS frontend dev server, and researches per-workspace isolation for backends/DB/Docker that portless can't cover. Use when asked to set up portless, fix stable dev URLs across worktrees, or make a repo Conductor-friendly for parallel agents.

  • Worktree isolation

    0SxD/agent-plugin-skills-v01/skills/worktree-isolation Skill

    0★ repo

    Create and manage git worktrees for parallel coding agent isolation. Invoke when two independent coding tasks need to run simultaneously (max 2).

    The same file is in 2 other repositories

  • Session dispatch

    0SxD/github-curator-v01/github-curator-v0.1.0/skills/session-dispatch Skill

    no license0★ repo

    Use this skill when spawning a new chat session for a focused workstream that exceeds the current session's context budget, especially when the new session must run in any agent (Claude Code, Codex, Cursor, Aider, Gemini CLI) or any host (Claude.ai project, NotebookLM, custom Gem, custom GPT). Triggers: any request to write a handoff prompt, dispatch a workstream, spawn a sub-agent session, prepare a paste-ready bootstrap for a new chat, or generate a HANDOFF document at 75% context. The skill emits a single AGENTS.md-shaped bootstrap file plus an optional packet zip that the human pastes or drops into the new session. The handoff is host-neutral: the same file works in every supported environment because it conforms to the AGENTS.md standard. Do NOT use this skill for in-session task delegation (use the agent's own subagent feature), for resuming an existing session, or for arbitrary chat templates unrelated to workstream dispatch.

  • Scan accessibility

    web-DnA/navable-web-accessibility-skills/skills/scan-accessibility Skill

    0★ repo

    Scans a URL for WCAG 2.1 AA accessibility violations using Playwright and axe-core via the navable MCP server. Generates a prioritized fix plan with before/after code patterns and EN 301 549 mapping. Use this as the default skill for accessibility work: when the user asks to check, scan, or fix accessibility of a page or URL. (For structure-only audits, see audit-page-structure.)

  • Agent browser

    ploteddie-bit/skills/agent-browser Skill

    no license0★ repo

    A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

    The same file is in 2 other repositories

  • Coding agent

    ploteddie-bit/skills/coding-agent Skill

    no license0★ repo

    Coding workflow with planning, implementation, verification, and testing for clean software development.

  • Skill creator

    ploteddie-bit/skills/skill-creator Skill

    no license0★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

  • Skill creator

    MAHDTech/agent-skills/skills/authoring/skill-creator Skill

    0★ repo

    Use when creating a new skill or editing an existing one in this repo — how to name it, place it in the right category, write its frontmatter and description, and structure it with progressive disclosure. Covers model-invoked vs user-invoked skills, the six skill failure modes, and the lint/sync workflow to run after adding or renaming a skill.

  • Handoff

    MAHDTech/agent-skills/skills/planning/handoff Skill

    0★ repo

    Compact the current conversation into a handoff document for another agent to pick up.

  • Agent guidelines

    MAHDTech/agent-skills/skills/tooling/agent-guidelines Skill

    0★ repo

    Behavioural guidelines for AI agents to reduce common LLM coding mistakes. Use before and while implementing to avoid common LLM coding pitfalls — over-engineering, unrequested refactors, silent assumptions, and unverified changes.

  • Install skills

    MAHDTech/agent-skills/skills/tooling/install-skills Skill

    0★ repo

    Install, update, and manage agent skills from a GitHub-hosted collection with the skills.sh CLI (`npx skills add <owner>/<repo>`), across every runtime the collection targets — Claude Code, OpenCode, Goose, and Antigravity CLI. Use when adding skills to an agent, updating a stale copy, verifying an install, wiring the same collection into another runtime, or troubleshooting a skill that will not show up or that collides by name.

  • Hi fi spike handoff

    rema424/ai/skills/hi-fi-spike-handoff Skill

    0★ repo

    Use after a branch has been reclassified as a Hi-Fi Spike. Extracts lessons, test intent, failure patterns, design constraints, minimal whiteboard design, and creates a handoff document for autonomous clean-room production implementation from a base branch.

  • Youtube thumbnails

    biyearly-mesothelioma790/skills/youtube-thumbnails Skill

    no license0★ repo

    This skill should be used when the user asks to "create YouTube thumbnails", "generate thumbnails", "make video thumbnails", or needs AI-generated thumbnail images via Google Gemini for YouTube videos. Covers prompt engineering, image generation, compression, and upload to YouTube Studio.

  • Agent platform alert configuration

    h3y6e/agent-skills/.vendor/skills/agent-platform-alert-configuration Skill

    0★ repo

    Configures best-practice alerting policies for Google Cloud Vertex AI / Agent Platform agents on Agent Runtime. Use when analyzing, writing, or deploying alerting policies to monitor agent latency, error rates, and quality metrics (response quality, tool use, hallucination). Also use when provisioning online monitors for quality evaluation, or analyzing live metrics traffic footprints. NOTE: This skill currently only works for the Agent Runtime. Don't use for configuring general GCP alert policies or non-agent GCP alerting policies.

  • Agent platform deploy

    h3y6e/agent-skills/.vendor/skills/agent-platform-deploy Skill

    0★ repo

    Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check deployment status, verify serving endpoints, or clean up resources by undeploying models and deleting endpoints. Use when asked to deploy models on Agent Platform, list available Model Garden models, check if a model is deployable, query deployment cost, troubleshoot deployment errors (like quota limits), or undeploy/clean up endpoints. Also use when copying and deploying a 1P Tuned Model. Don't use for public Vertex AI deployments (use the `vertex-deploy` skill) or for running model evaluations (use the `agent-platform-eval` skill).

  • Agent platform endpoint management

    h3y6e/agent-skills/.vendor/skills/agent-platform-endpoint-management Skill

    0★ repo

    Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model evaluations.

  • Agent platform eval flywheel

    h3y6e/agent-skills/.vendor/skills/agent-platform-eval-flywheel Skill

    0★ repo

    Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on Agent Platform eval methodology — including dataset schema, LLM-as-judge scoring, and common failure causes. For fine-tuning, use agent-platform-tuning. For general production deployment, use agent-platform-deploy.

  • Agent platform inference

    h3y6e/agent-skills/.vendor/skills/agent-platform-inference Skill

    0★ repo

    Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when you need to generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or legacy Agent Platform SDK, configure base URLs and global/regional endpoints, or troubleshoot 429 Resource Exhausted (DSQ), 400 User Validation, or 404 Not Found errors. Don't use for deploying models to endpoints or for running model evaluations.

  • Agent platform migrate from ai studio

    h3y6e/agent-skills/.vendor/skills/agent-platform-migrate-from-ai-studio Skill

    0★ repo

    Guides agents and users through migrating from Gemini API in Google AI Studio to Gemini Enterprise Agent Platform (formerly Vertex AI). Use this skill when moving applications to Google Cloud, to leverage Cloud credits, or to unify inferencing with other Cloud infrastructure (IAM, billing, telemetry).