agentsclimarketplace

Context & AI engineering

25,864 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

  • Xxtrade agent

    Madwr1d/xxtrade-agent Skill

    no license0★

    Use to read xXTrade (Hyperliquid perps) market and account data from the terminal — top markets by open interest, a coin's mark price, and the open positions / account value for a wallet address. READ-ONLY (no trading). Use when an agent needs live perp prices, funding, OI, or to check a wallet's positions on xXTrade.

  • Agentic quality gates

    g-shevchenko/agentic-quality-skills/skills/agentic-quality-gates Skill

    0★ repo

    Use before non-trivial agentic, coding, workflow, tool, automation, release, or public-surface work, and when the user says quality gate, acceptance gate, red flags, risk gate, architecture gate, decision handoff, side-effecting workflow, contracts first prompts last, prompt-only fix, human gate, or release gate. Classifies risk, defines deterministic acceptance gates, catches red flags, and decides whether to proceed autonomously or ask a human.

  • Skill vetting reporter

    jovd83/skill-vetting-reporter Skill

    0★

    Security & trust vetting for an AgentSkill (folder, SKILL.md, zip, or single script) before it is installed or approved. Runs a mandatory open-source scanner gate (Cisco skill-scanner, NVIDIA SkillSpector, Snyk Agent Scan, sentry/skill-scanner), then static heuristics, and produces a draft review report — file inventory, executable surface, findings by severity, an OWASP Agentic Skills Top 10 (AST01-AST10) coverage map, a red-flag checklist, a suggested review tier (0-3), and reviewer sign-off blocks. Use this whenever someone asks "is this skill safe", "vet/review/scan this skill or SKILL.md or script", "run the vetting on skill X", "should I install this skill", or when a skill must pass the AgentSkills review flow. Also use it to re-vet an updated skill and diff the reports. It assists review and never approves anything on its own.

  • Claude code agent sdk

    ucsandman/claude-code-capability-primer/skills/claude-code-agent-sdk Skill

    0★ repo

    Use when building custom AI agents headlessly, embedding Claude Code tools in an app, or running scripted/cron agents—need SDK package names, setup, core API entry points, supported languages, and relation to Claude Code CLI and Messages...

  • Popperian reasoning

    calebikhuohon/popperian-reasoning/skills/popperian-reasoning Skill

    0★ repo

    Use Popperian critical rationalism to improve reasoning by falsification, risky tests, competing conjectures, and error elimination. Invoke implicitly in any agent harness when a task involves uncertainty, hypotheses, tradeoffs, claims, explanations, debugging, diagnosis, research evaluation, plan review, design choice, or improving an LLM answer by asking what would break it before asking what supports it. The user does not need to name this skill if the harness supports contextual skill selection.

  • Agent handoff kit

    claudette-agent/agent-handoff-kit Skill

    no license0★

    Lightweight handoff workflow for AI coding/research agents. Captures objective, state, constraints, next action, verification, and risks.

  • Design agent prompt loop

    WellDunDun/skills/skills/design-agent-prompt-loop Skill

    0★ repo

    Designs autonomous prompting loops that let coding agents drive their own next steps, handoffs, reviews, and verification prompts. Use when setting up agent workflows, reducing repeated user prompting, creating self-driving project instructions, designing prompt queues, or coordinating build, review, and handoff loops across agents.

  • Waitspin

    citedy/waitspin/skills/waitspin Skill

    0★ repo

    Use this skill for WaitSpin, the sponsored wait-state ads CLI and API. Trigger when a user wants to create or manage WaitSpin campaigns, buy prepaid impression blocks, inspect the public market, onboard with email OTP keys, install or check earning surfaces for VS Code, Cursor, Devin Desktop, Claude Code, Antigravity CLI, GitHub Copilot CLI, MiMo Code, OpenCode, Grok Code CLI, or Qoder CLI, inspect wallet/ledger/payout status, or reason about WaitSpin public API, trust boundary, privacy, and shipped vs not-shipped capabilities.

  • Agent workbench

    MuNeNiCK/agent-workbench/skills/agent-workbench Skill

    0★ repo

    Use when a coding agent needs durable work, design, review, evidence, interruption, recovery, and completion state through the native Agent Workbench CLI.

  • Agentic video analysis skill

    Nu424/agentic-video-analysis-skill/skills/agentic-video-analysis-skill Skill

    no license0★ repo

    動画をフレームタイル化し、aitool recognize-imageで反復的に解析するためのスキル。 動画解析、見どころ抽出、ハイライト候補探索、ゲーム実況分析、エージェンティックな動画理解を行うときに使用する。

  • Compact handoff

    codecraftersautomation/claude-code/plugins/ccp/skills/compact-handoff Skill

    no license0★ repo

    Emergency, fast handoff when the current Claude account is almost out of usage/tokens and there's no time for a full handoff. Use this when the user says they're "about to hit the limit", "running out", "almost out of usage", "quick handoff", "emergency handoff", or needs to switch to the other profile (claude-team <-> claude-max) immediately. Writes a short .claude/ccp/handoff/COMPACT_HANDOFF.md (~1000-1500 words) with objective, state, next 3 steps, risks, and an exact takeover prompt.

  • Context engineering

    mikulgohil/claude-skills/skills/ai-agents/context-engineering Skill

    0★ repo

    Understand and optimize how context is structured in agent systems — the components, mechanics, and constraints of an agent's context window. Use when writing or tuning commands, skills, and sub-agent prompts.

  • Session handoff

    taige221/session-handoff-skill/skills/session-handoff Skill

    0★ repo

    Use this skill when the user explicitly wants to summarize, wrap up, or hand off the current AI coding session into a concise Markdown document for a future session. Trigger phrases include: "session handoff", "handoff doc", "generate a handoff document", "summarize this session for the next session", "distill this session into a handoff md". Output to chat by default. Do not create persistent memory, auto-load context, sync sessions, or write files unless explicitly asked.

  • Nightcap

    tommylower/nightcap Skill

    0★

    Nightcap, a nightly agent journal. Reads recent Claude Code and Codex transcripts off disk, skips trivial sessions, and writes one first-person narrative journal entry per real session, like a handwritten end-of-day journal. Use when the user wants an agent session journal, a daily log of AI sessions, transcript summaries, "what did i work on today/this week", to set up or troubleshoot nightcap, or to customize its voice. Triggers: nightcap, journal, session journal, agent journal, daily log, summarize my sessions, what did i do today.

    The same file is in 1 other repository

  • Team memory capture

    meharajM/context-machine/packages/team-project-memory-skill/skills/team-memory-capture Skill

    0★ repo

    Capture a short reusable project learning after a non-obvious fix, failed approach, setup requirement, decision, or debugging path is verified and likely to save another agent time or tokens.

  • Setup graphify

    PabloViniegra/setup-graphify/skills/setup-graphify Skill

    no license0★ repo

    Trigger: set up graphify, add graphify, configure graphify, integrate graphify. Installs graphifyy, injects a marker-delimited Graphify section into every agent-instruction file present in the project (AGENTS.md always; CLAUDE.md, .github/copilot-instructions.md, GEMINI.md, Cursor rules, and others only if they already exist), adds graphify-out/ to all ignore files, installs post-commit + post-checkout git hooks, and runs the initial knowledge graph build. No hidden hook directories are created. Requires Python 3.12+.

  • Webmcp skill

    Blackie360/webmcp-skill/webmcp-skill Skill

    0★ repo

    Implements WebMCP (Web Model Context Protocol) on websites using document.modelContext.registerTool. Covers tool design, JSON Schema inputs, security annotations, origin isolation, and Chrome testing. Use when adding WebMCP tools to web apps, exposing page features to browser agents, or when the user mentions WebMCP, modelContext, or agent-ready web tools. Not for server-side MCP servers.

  • Docs product orchestrator

    satishTheLegend/docs-product-orchestrator Skill

    0★

    Runs a documentation site like a PRODUCT, not a pile of READMEs: detects the repo's stack and inventories doc gaps, defines reader personas and jobs, designs a Diataxis-correct information architecture (tutorials/how-to/reference/explanation without quadrant-mixing), scaffolds a real docs-as-code toolchain (MkDocs/Docusaurus/Starlight), auto-generates API reference FROM source so it never rots, tests every code sample and link as a hard gate, and installs a CI doc-drift gate that fails when public API/CLI/config changes are undocumented. It sequences these phases in dependency order with a deterministic, script-enforced gate between each, tracked in a ledger file, and delegates toolchain internals to specialist tools rather than reimplementing them. Use whenever the user wants to set up, build, restructure, fix, or maintain a documentation site or developer docs - even if they only say "our docs are a mess / out of date", "set up docs for this repo", "apply Diataxis", "generate API reference from our code / OpenAPI", "stand up MkDocs/Docusaurus/Starlight", or "make docs that don't go stale / catch docs drift in CI" - even if they don't explicitly ask for an orchestrator. Trigger on README sprawl, stale API docs, or a missing docs pipeline.

  • Notta mcp skill

    mindcruiser/notta-mcp-skill Skill

    no license0★

    Use Notta MCP to transcribe local audio/video files, check transcription status, retrieve transcript results, search Notta records, and list Notta records or folders through Claude Desktop, Smithery, Codex, or other MCP-capable agent environments.

  • Context handoff

    knowingrohan/ai/skills/context-handoff Skill

    0★ repo

    Before ending a session or switching agents, produce a structured hand-off note — what was done, what is pending, key decisions made, files changed, and a ready-to-paste resume prompt for the next session or agent. Use when the user says they are wrapping up, switching tools, handing off to a teammate, or starting a new session on the same project.

  • Nightshift

    shanemhamilton/nightshift Skill

    0★

    Audits and hardens recurring automations so they behave like reliable operators instead of stateless prompts — and composes coherent new automation suites per project from an adaptive pattern library — across Codex, Claude Code, Gemini CLI, and Cursor. Adds persistent memory, run ledgers, concurrency locks, tool preflight, change-detection, failure taxonomy, stop rules, a continuation loop that completes multiple bounded work-units per run, multi-agent execution, approval queues, and verified safe-merge closeout; wires new jobs into a coordinated fleet with one merge authority. Use when the user wants to create, review, standardize, optimize, or harden scheduled or recurring jobs — Codex automations (~/.codex/automations/*/automation.toml), Claude scheduled-tasks (~/.claude/scheduled-tasks/*/SKILL.md), Gemini cron jobs, Cursor cloud automations, nightly maintenance loops, repo-hygiene/QA/coverage/security/simplification jobs, integration-rescue jobs, or reminder/monitor prompts — or to propose what automations a project should have, see what's already installed across agents, or set them up to work together. Also triggers on requests to stop an automation duplicating work, make a job idempotent, give an automation memory, add a human-approval gate, or build a nightly automation suite.

  • Skill

    Azzaraell/agent-payments-x402/skill Skill

    0★ repo

    The money layer for AI agents on Solana. Lets an agent PAY for APIs/data/compute and other agents (x402 micropayments in USDC), GET PAID by monetizing its own APIs/MCP tools behind HTTP 402, and SPEND SAFELY behind non-custodial wallets with hard, enforced limits — never a raw god-mode private key. Covers x402 v2 (client + server + facilitator), Squads v4 spending limits, Privy/Turnkey/Coinbase-CDP/Crossmint agent wallets, AP2 mandates, and USDC settlement. Use when building agents that transact, paywalling an API/MCP for agent consumers, or hardening an agent's spending controls.

  • Airtable mcp

    0xgetz/xi-agent-skills/mcp-skills/airtable-mcp Skill

    no license0★ repo

    Use the Airtable MCP integration to read and write Airtable bases and tables. Activate when the user wants to read and write Airtable bases and tables via Airtable, including discovering the right tool, building parameters, and handling results.

  • Authoring skills and rules

    balacodeio/balakit/skills/authoring-skills-and-rules Skill

    0★ repo

    Author Skills (SKILL.md) and rules/instructions across Claude Code, Cursor, OpenCode, Codex, and GitHub Copilot. Covers frontmatter, file layout, activation model, cross-platform mirroring, and the universal craft: progressive disclosure, trigger-rich descriptions (context pointers), leading words, token budget, naming, and what to leave out. Use when the user asks to write, scaffold, refactor, port, or review a Skill, Cursor rule (.mdc), AGENTS.md, copilot-instructions, or prompt file — or to make one Skill/rule work across multiple agents.

  • Igapyon miku prompt lint

    igapyon/miku-prompt-lint-skills/skills/igapyon-miku-prompt-lint Skill

    0★ repo

    Use only when the user explicitly names miku-prompt-lint or igapyon-miku-prompt-lint, or asks to lint, audit, or diagnose an LLM prompt, AI-agent context package, Agent Skill, or supplied Agent Skill repository/harness for prompt/context-engineering quality risks. Do not activate for generic code review, document review, prose editing, source-code templates, or generic repository review unless explicitly named. Review the artifact itself; do not infer whether the author was human or generated AI.

  • Primitive chat

    primitivedotdev/codex-plugin/plugins/primitive/skills/primitive-chat Skill

    0★ repo

    Reach a person or another agent over email and wait for the threaded reply. Use REACTIVELY when the user gives you a mailto link, pastes a contact address, or asks you to send a message. Use PROACTIVELY when you are blocked on a tool, library, or service and want to ask its help/dev/support/docs agent, found a bug worth reporting to a vendor, or have a question only a product owner can answer. Requires the Primitive MCP server (bundled).

  • Capability orchestrator

    theadhithyankr/codex-capability-orchestrator-skills/capability-orchestrator Skill

    0★ repo

    Capability orchestrator for Codex. MUST use when a task mentions missing skill, install a skill, Skilldex, MCP registry, capability discovery, benchmark skills, compare tools, dynamic tool integration, meta-skill, tool evolution, TTE, synthesize a tool, or when Codex lacks a required capability. Search registries first, evaluate candidates, install the best safe option, or synthesize a reusable sandboxed tool when no registry match exists.

  • Goose

    dominion525/agent-skills/skills/goose Skill

    0★ repo

    Delegates a self-contained agentic task to Google Gemini via the Block Goose CLI, run headlessly from Claude Code. Goose can autonomously explore the repository, read files, and execute shell commands across multiple turns to produce a result rather than a single-shot answer. Use when offloading exploratory analysis to a different model family, getting a second opinion on a diff or design, or running a multi-step task that needs tool use beyond what a single prompt can return.

  • Sprint eval

    anupam-io/sprint-skills/skills/sprint-eval Skill

    0★ repo

    Rate a sprint plan by convening a panel of 3 local expert agents (engineering program management, operations-research scheduling, agentic task planning), each scoring the same 3 fixed criteria 1-10, then synthesizing a score table, consensus risks, and concrete fixes. Use when the user wants a sprint plan rated/evaluated/stress-tested, asks "how good is this sprint plan", or hands over a sprint doc asking for a quality verdict. Input is a sprint plan in any format (HTML, markdown, Slack dump, Linear export).

  • Loops graduate

    tcf-jw/plan-with-loops/skills/loops-graduate Skill

    0★ repo

    Promote a proven agent-loop from the loop store (~/.claude/loops/) into a reusable global skill. Reads the relevant loop-record note(s), verifies the loop has actually succeeded, then scaffolds a new ~/.claude/skills/<name>/ SKILL.md that encodes the proven loop as a concrete Claude Code Workflow procedure. Triggers: /loops-graduate, "promote this loop to a skill", "graduate this loop", "make a skill from this loop", "turn this loop into a skill".

  • Chatgpt agent skills

    bybaochaule/chatgpt-agent-skills Skill

    no license0★

    Was sind ChatGPT Agent Skills?

  • Eval harness architect

    satishTheLegend/eval-harness-architect Skill

    0★

    Stands up a rigorous, regression-proof evaluation harness for any LLM, agent, or RAG system from zero, through a dependency-ordered, phase-gated lifecycle: pins down what "good" means (dimensions, failure modes, thresholds, the decision the eval supports) BEFORE building; builds a versioned dataset with edge, adversarial, and known-failure cases plus a quarantined holdout split against overfitting; binds the right scorer per dimension (exact/regex/schema, embedding, code-exec, or LLM-as-judge), refusing a judge where a deterministic check works; calibrates the judge against human labels for measured agreement/bias; baselines with confidence intervals so deltas are real not noise; wires CI gates plus PR diff scorecards; and closes the loop with drift and prod feedback. Provider-agnostic; a runnable harness, not a checklist; composes with existing eval skills. Use whenever the user wants to build, set up, or fix evals for an LLM/agent/RAG system; has no way to tell if a change helped; wants an eval dataset, LLM-as-judge, scorer, or CI gate; asks "is the new model actually better"; says evals pass but prod still breaks (drift/overfitting); or wants regression testing for prompt changes — even without "evals", e.g. "make sure my prompt change doesn't break anything".

  • Scan ai visibility

    lishangyanyan1992/clientory-ai-visibility-skill/skills/scan-ai-visibility Skill

    0★ repo

    Measure whether AI assistants mention and recommend a law firm, identify competing firms and ranking gaps, and generate evidence-based recommendations. Use when a user wants a law-firm AI visibility audit, answer-engine optimization (AEO), generative-engine optimization (GEO), LLM recommendation, model mention, competitor, share-of-voice, or share-of-model scan across OpenAI, Claude, Gemini, xAI, Perplexity, OpenRouter, or another compatible model API. This version supports law firms only.

  • Avatar motion forge

    naimkatiman/premium-agent-skills/plugins/premium-agent-skills/skills/avatar-motion-forge Skill

    0★ repo

    Use to design an ORIGINAL premium AI-agent mascot or assistant avatar, SVG concepts plus state-driven motion specs (idle, hover, active, success, error) ready for Lottie or Rive. Use when the user asks to design a mascot, make a premium avatar, or create animation states. NEVER clone or closely imitate an existing product mascot (e.g. Copilot); enforce the originality checklist.

  • Agent input firewall

    dvnc-labs/agent-input-firewall Skill

    0★

    Quarantine untrusted GitHub issues, PR comments, user feedback, web excerpts, logs, or pasted external text before acting on them; extract source-tagged facts and safe tasks while defanging prompt injection. Not for trusted first-party specs, general security audits, or malware incident response.

  • Apple foundation models

    dbmrq/agent-skills/skills/apple-foundation-models Skill

    no license0★ repo

    Integrate Apple Foundation Models into iOS apps — model selection, availability gates, prompting for the on-device model, guided generation, tool calling, Private Cloud Compute, token budgeting, locale handling, and model-version prompt updates. Use when building or reviewing Apple Intelligence / Foundation Models features in Swift or SwiftUI.

  • Your prompt engineer

    polychrome7/your-prompt-engineer/skills/your-prompt-engineer Skill

    0★ repo

    Use when the user invokes $your-prompt-engineer, uses a host command alias for this skill, or asks to prepare, refine, structure, execute, or send an agent prompt/task prompt for Codex, Claude Code, or another compatible agent host. Treat text after explicit invocation as the raw request even when it is fragmentary. Do not trigger implicitly when the user asks only to run/delegate/inspect/fix with an agent and does not mention prompt preparation.

  • Ai agent builder

    aizech/bernhard-zechmann-skills/skills/engineering/ai-agent-builder Skill

    0★ repo

    Build an AI agent with tools, memory, and multi-step reasoning. Use when the user wants a chatbot, reasoning agent, or multi-agent system.

  • Relocation logistics orchestrator

    satishTheLegend/relocation-logistics-orchestrator Skill

    0★

    Turns a cross-state or international move into a backward-planned, deadline-aware, cross-domain program — housing and cost-of-living normalization, driver's-license and vehicle re-registration windows, healthcare and prescription/records transfer, partial-year and dual-state (or expat) tax items to verify, K-12 school enrollment windows, utilities, mover logistics and budgeting, and pet relocation — all driven from a persistent dated checklist plus a destination first-week kit. Use whenever the user mentions moving, relocating, or changing states or countries; comparing cost of living or relocating for a job; transferring a driver's license or registering a car in a new state; enrolling kids in a new school after a move; moving with pets; or an expat / moving-abroad / international relocation — even if they don't explicitly ask for a plan, checklist, or timeline, and even from a one-liner like "we're moving to Austin in October." Always builds a deadline-ordered timeline, never asserts jurisdiction deadlines or tax/immigration rules from memory, and routes the user to official sources and licensed pros for verification.

  • Agent ready ui

    dvnc-labs/agent-ready-ui Skill

    0★

    Make web UIs agent-ready for browser/GUI agents when the user asks to improve click/type automation, Playwright locators, accessible names, stable controls, or browser-agent reliability. Do not use for general redesigns, broad accessibility audits, or writing full end-to-end test suites without UI affordance changes.

  • Context cost tree

    HorizonBrute/Horizon_AI_OS/horizon_system/skills_bin/context-cost-tree Skill

    no license0★ repo

    Map Claude Code harness context overhead across the ENTIRE AIOS as an ASCII tree — brute-forces every directory under $HORIZON_ROOT, attributes each auto-loaded CLAUDE.md / agents.md / @-import file to the directory it lives in, and reports per-directory, subtree, and grand-total context cost. Use when the user types /context-cost-tree, wants a whole-AIOS context map, or asks where context cost accrues across the tree (as opposed to /context-cost, which measures one path's upward load).

  • Mcll real estate

    mcllrealestate/agent-skills/skills/mcll-real-estate Skill

    0★ repo

    Search and retrieve published MCLL real-estate listings from mcllrealestate.com. Use for Thai property searches, residences for sale or rent, prices, areas, branded residences, new developments, or comparisons across MCLL listings. Prefer the MCLL MCP server; its execute tool is Code Mode JavaScript for calculations and comparisons over published listings. REST and Markdown fallbacks work without MCP. Read-only, no auth, no API key. Skip real estate outside Thailand and non-MCLL portals.

  • Amap agent skill

    henrywen98/amap-agent-skill Skill

    0★

    高德地图(无需 MCP,纯 REST/curl):地理编码、逆地理、POI 周边/关键词搜索、POI 详情、天气、驾车/步行/骑行/公交路径规划、距离测算、IP 定位。当用户问基于位置的问题——「我在哪」「附近的…」「到 X 怎么走」「今天天气」「某地坐标」「两点距离」——时使用。没坐标时(macOS)可先用 whereami 取系统精确坐标再调本 skill 的 scripts/amap.sh。Use for any location / map / POI / weather / route / geocoding query; runs under pi, Claude Code, or any shell-capable agent — no MCP server needed.

  • Agentic remotion pipeline

    ryanwi/agentic-remotion-pipeline Skill

    0★

    Drive a JSON-in / video-out Remotion project. Use when producing a video from structured data in this repo (or one scaffolded from it) — authoring input/plan.json, running build-props → render → mix, and extending scenes. For how to write Remotion code itself, defer to the official remotion-dev/skills.

  • Skill vaccine review

    ch040602/skill-vaccine/skills/skill-vaccine-review Skill

    no license0★ repo

    Use when Codex or Claude Code should safely review or install an Agent Skill through Skill Vaccine: generate static evidence, judge SKILL.md/helper docs/scripts semantically, compare CLI-only and agent-assisted results, block malicious or uncertain packages, and avoid executing reviewed skill code.

  • Agent system designer

    satishTheLegend/agent-system-designer Skill

    0★

    Designs correct, verifiable agentic systems from a capability spec — decides per capability whether it is a prompt/skill (knowledge), a subagent (context isolation), an MCP server (external capability), or an orchestration workflow (control), then designs unambiguous non-overlapping tool contracts, a context/memory budget, least-privilege + human-in-the-loop safety, failure/loop/budget control flow, and a runnable behavioral test harness, emitting a build-ordered implementation spec with a phase-gate ledger. Use whenever the user is building or architecting an agent, multi-agent system, MCP server, tool/function integration, skill, or subagent — even if they don't explicitly ask for "design": triggers include "should this be a skill, subagent, MCP server, or workflow?", "my agent misuses its tools / loops forever / blows the context window", "design tool schemas the model won't misuse", "how do I structure agents and their handoffs", "give my agent safe tool permissions", or any time they're about to cram everything into one prompt or reach for an MCP server where a skill would do. Activate proactively to prevent expensive, hard-to-reverse mistakes before code is written; push back on needless multi-agent complexity and unscoped permissions. Composes with skill-creator.

  • Agent handoff

    Cairn-ai-tooling/agent-collab-tooling/skills/agent-handoff Skill

    0★ repo

    Use when finishing a chunk of work that another agent (or a future session) will continue — produces a structured handoff capturing goal, decisions, current state, remaining work, and blockers so the next agent can resume without re-deriving context.

  • Session handoff

    254095728-bit/session-handoff Skill

    0★

    Preserve and restore work across independent AI conversations by creating a provider-neutral Markdown handoff, validating project state, and preparing the next session. Use when the user asks to switch threads, start a fresh chat without losing context, create or update a handoff, continue from a handoff, checkpoint long-running work, compact context, or transfer work between ChatGPT, Codex, Claude Code, Cursor, Windsurf, Gemini CLI, Roo Code, OpenHands, or another AI assistant.

  • Consult claude

    pablonification/grok-build-consult-claude/skills/consult-claude Skill

    0★ repo

    Read-only second opinion from Claude Code (claude -p). Use when the user explicitly asks ("ask Claude", "second opinion", "/consult-claude") OR when a HARD GATE passes: high-stakes architecture/security decisions, 2+ credible approaches with real trade-offs, or blocked after 2+ distinct attempts. Modes: plan, review, advice. Do NOT use for routine coding, debugging, file edits, or "just to be thorough". Grok implements any follow-up changes.

  • Oh my goals

    MesTTo/oh-my-goals/skills/oh-my-goals Skill

    0★ repo

    Local MeTTa memory and reasoning for a coding agent. Use when a task is multi-step, consequential, constrained by user rules or repository policy, ambiguous, or likely to outlive the current context window. Store the material facts, goals, and constraints as short English propositions that survive across turns and MCP restarts, query them before you plan, and rank candidate actions against them before you act. Reach for it to hold a user constraint through context compaction, to choose between actions under a policy, or to keep a decision traceable to its evidence.

  • Locus agent tools

    velinussage/locus-agent-skill/skills/locus-agent-tools Skill

    0★ repo

    Use when an agent needs to connect to Locus over MCP, A2A, or REST for property and local-government context.

  • Design auto orchestrator

    chongchonghaoman/design-auto-orchestrator-kit/skills/design-auto-orchestrator Skill

    0★ repo

    UI/UX frontend website portfolio router. Mandatory first-use design orchestrator for Codex. Use before frontend-design, hallmark, ui-ux-pro-max, ui-design-brain, web-design-guidelines, better-icons, Open Design, or other specialized design skills whenever a request or intermediate work step touches UI, UX, frontend visuals, product interfaces, websites, landing pages, portfolios, dashboards, admin panels, app screens, components, forms, tables, navigation, design systems, typography, color, layout, motion, icons, accessibility, responsive behavior, screenshot critique, visual polish, anti-AI-slop, Open Design, or design-resource selection. Do not require the user to name this skill, downstream skills, Open Design, or any tool. Route work to the right local design skills and tools based on task semantics, project files, screenshots, and implementation context.

  • Context handoff

    djhyes/context-handoff/skills/context-handoff Skill

    0★ repo

    Use automatically and immediately when an agent thread is near the context limit, automatic compaction is about to happen or just happened, the user asks to hand off/continue in a new session, or the conversation contains triggers such as context full, context almost full, compact, handoff, transfer, resume in fresh thread, 新会话, 上下文快满, 交接, 接着干, or 续上. Create a complete handoff document and start a fresh continuation thread/session when the host agent supports it.

  • Agent brief

    mustafa3252/vibe-ship-skills/skills/agent-brief Skill

    0★ repo

    Write one crisp handoff that tells any coding agent the role, constraints, checks, and done definition.

  • Bootstrap issues

    chieaid24/skills/skills/bootstrap-issues Skill

    0★ repo

    Bootstrap a repo for parallel autonomous agents coordinated via a dependency-aware GitHub Issues queue - creates work-queue labels (lifecycle plus afk/hitl autonomy), a CI test gate, branch protection with self-merge, an agent issue template, a committed DESIGN.md design system for frontend repos, and the AGENTS.md/CLAUDE.md workflow docs. Use when the user wants to set up the parallel-agent / GitHub Issues flow in a repo, "bootstrap issues", port the agent workflow to a new repo, or invokes /bootstrap-issues.

  • Apify expert

    MrBridgeHQ/apify-expert-claude/skills/apify-expert Skill

    0★ repo

    Use when you need current, authoritative facts about the Apify PLATFORM itself - Actors, runs, builds, storage (Dataset / Key-value store / Request queue), Apify Proxy, schedules, webhooks, integrations, the REST API, the apify CLI, the JS/Python SDK, Standby mode, Store mechanics - or when asked "what's new on Apify", "latest Apify update", "Apify changelog", "did Apify change X", "is feature Y still current". Also the resource that scraper-building, MCP-server-building, monetization, and content-authoring workflows consult for up-to-date platform facts and recent changelog changes. NOT for deep domain work - scraper code, MCP server code, PPE pricing, README/schema authoring - which specialized workflows own; this skill provides their platform substrate.

  • Skill builder

    RKelln/hermes_skills/skills/skill-builder Skill

    no license0★ repo

    Hermes Agent skills

  • Agent ready

    oradotai/agent-ready Skill

    0★

    Build software that AI agents can see, use, and pay. Use this skill when building or extending a product, API, web app, SaaS, or service an agent might use on a user's behalf - designing API endpoints, auth flows, public docs, an MCP server, MCP Apps / interactive agent UI, llms.txt, structured data, or checkout. It bakes agent-readiness in at build time around three questions — can agents SEE you (discovery + identity), USE you (auth, integration, in-agent UX and human handoff), and PAY you (agentic commerce) - across the five layers of the Ora agent-readiness standard. Trigger phrases include make this agent-ready, build an API agents can use, add an MCP server, render UI in Claude or ChatGPT, MCP Apps, write an llms.txt, agent checkout, agentic payments, expose this to AI agents. Not for general SEO, human-only UX, or internal infra with no external agent surface.

  • Skill

    Subho4531/solana-agent-commerce-skill/skill Skill

    0★ repo

    Solana-first agent commerce and x402 skill for building paid APIs, paid MCP servers, and buyer agents that use Solana USDC/SPL/Token2022 payments. Use when implementing x402 on Solana, monetizing API endpoints or MCP tools, adding agent spend policies, pricing paid agent workflows, testing Solana devnet x402 payments, reconciling payment receipts, or hardening x402 payment flows against replay, stale quotes, route confusion, concurrency, and overspending.

  • Content localization orchestrator

    satishTheLegend/content-localization-orchestrator Skill

    0★

    Orchestrates end-to-end localization of CONTENT (marketing, docs, UX copy, growth assets) — not just code strings — across many locales the right way: per-locale strategy, a persisted glossary + translation memory, culture-aware transcreation instead of literal translation, a cultural-sensitivity and regulated-content QA gate, RTL and text-expansion layout adaptation, and a source-sync map that re-localizes only what changed. Plugs around an existing TMS (Crowdin/Lokalise/Phrase) or runs from files; keeps all locales consistent as the source evolves. Use whenever the user wants to localize, translate, or "go global" with their website, docs, app copy, or marketing into other languages — even if they don't explicitly ask for orchestration; wants to expand into a market or add locales; says their translations sound robotic, literal, inconsistent, or off-brand; wants to transcreate or culturally adapt copy; wants a glossary or translation memory; mentions RTL, Arabic, Hebrew, Japanese, or CJK adaptation; needs cultural or compliance review of translated content; or wants to keep translations in sync after editing the source. Trigger even without the word "localize" — e.g. "make this work for Germany" or "why do our French pages read so badly".