Context & AI engineering
25,991 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
Aidress skill find verified document summarization agent
Aidress-ai/aidress-skill-find-verified-document-summarization-agent Skill
2★Find a Verified Document Summarization Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for research agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
tony/ai-workflow-plugins/.agents/skills/action-worktree Skill
2★ repoUse when the user wants to take a ticket — or several tickets that share one change — into its own branch and git worktree and drive it to gated commits. Triggers on phrases like "work TEA-123 in a worktree", "spin up a worktree for issue #45", "start on this ticket", "branch for the Linear ticket", "put these two tickets on one branch", or "prep a worktree, I'll take it from there". Resolves the ticket strictly read-only (never assigns, comments, or transitions), names the branch by the team's own conventions, implements through the project's discovered quality gates, and never pushes or opens a PR unless the flags say so.
kongyo2/prompt-engineering-skill/prompt-engineering Skill
no license2★ repoComprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. This skill should be used when users request prompt creation, optimization, or improvement for any LLM task, or when users need help translating vague requirements into effective prompts through collaborative dialogue and iterative refinement.
Aidress skill find verified crm management agent
Aidress-ai/aidress-skill-find-verified-crm-management-agent Skill
2★Find a Verified Crm Management Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for sales agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
glowElephant/context-forge/.claude/skills/context-forge Skill
2★ repoUse when starting a brand-new project that needs AI-agent context (CLAUDE.md, AGENTS.md, skills, rules, MCP, spec workflow) set up from day one. Discusses goals → matches catalog know-how → creates a new GitHub repo with everything wired in. Keywords: harness engineering, bootstrap project, context engineering, scaffold repo, start project, agent-ready repo.
light-merlin-dark/skill-sync/skills/skill-sync Skill
2★ repoSync local repo-backed agent skills across installed harnesses such as Codex, Claude Code, Cursor, Gemini, Hermes, Grok, and related tools. Use when a user wants one source of truth for local SKILL.md files, needs drift checks or backup/restore for harness skill roots, or wants to inspect which harnesses and skills are currently detected.
cskwork/postgres-intelligence Skill
2★Use when an LLM agent needs to connect to PostgreSQL, inspect schemas, run safe SQL, translate natural language into PostgreSQL queries, or analyze query performance without exposing credentials.
jacob-balslev/skills/skills/agent-ops/ai-native-development Skill
2★ repoUse when reasoning about agent autonomy levels, designing auto-improve loops, evaluating AI-generated code quality, or measuring agent productivity in an LLM-assisted codebase. Covers Karpathy's three eras of software (1.0 explicit / 2.0 learned / 3.0 natural-language), the vibe-coding-vs-agentic-engineering distinction, the 0–5 autonomy slider with task-type recommendations, the one-asset / one-metric / one-time-box AutoResearch loop, Software 3.0 productivity metrics, and the documented quality regressions of ungated AI-generated code (the 'vibe hangover'). Do NOT use for choosing a specific autonomy-loop topology (use `agent-engineering`), for the per-prompt authoring discipline (use `prompt-craft`), or for reviewing the AI-generated code that comes out of a Software 3.0 workflow (use `code-review`).
LevyBytes/AI-SKILL-gimp Skill
2★Use when working with GIMP, the GNU Image Manipulation Program (especially GIMP 3.2) - editing or generating raster images; working with layers, layer/blend modes, masks, channels, selections, or Bézier paths; applying tools or filters; adjusting colors, levels, curves, or ICC color profiles; importing or exporting image files (.xcf, PNG, JPEG); or automating GIMP through Script-Fu, Python-Fu, the Script-Fu Console, or the Procedural Database (PDB) - including driving GIMP from a GIMP MCP server or a headless/batch (gimp -i -b) run. Also fires when you see .xcf files, gimp-* procedure calls, script-fu-register, "from gi.repository import Gimp", or GObject-Introspection GIMP plug-ins, even when the user never says "GIMP" by name. Gives task-routed, faithful 3.2 reference with worked examples.
wassengerhq/whatsapp-skills/skills/wassenger-ai-agent Skill
2★ repoBuild a production-grade AI agent that answers your customers on WhatsApp with Wassenger — an LLM (OpenAI/Claude) replies to inbound messages inside the 24-hour window, with a hard human handoff for sensitive or low-confidence cases, idempotent webhook handling, opt-out, and a kill switch. Use when the user wants an "AI chatbot / assistant / auto-responder" that handles FAQs, qualifies leads, and covers after-hours on WhatsApp — and wants it safe enough to put in front of real customers, not a naive autonomous bot.
roccodaffuso/sift/.agents/skills/sift-memory Skill
2★ repoUse this skill when an agent needs local historical context from AI coding assistant sessions, prior project conversations, debugging history, implementation decisions, or user asks to search Claude Code, Codex, or Cursor chat history. It teaches agents to use the local-only `sift` CLI for indexed full-text search across Claude Code, Codex, and Cursor logs without network calls.
yaolifeng0629/ylf-agent-skills/skills/ylf-coding-standards Skill
2★ repoApply compact YLF engineering discipline to the current task. Use when the user explicitly asks for YLF coding standards, wants a concise AGENTS/CLAUDE-style rule set applied to one task, or asks the agent to follow disciplined coding rules before making code changes.
mqrox/seedance-2.0-prompt-skill/build-seedance2-prompts Skill
2★ repoBuild, rewrite, diagnose, or validate production-ready prompts specifically for ByteDance Dreamina/Doubao Seedance 2.0 Standard, including text-to-video, image-to-video, first/last-frame animation, multimodal image/video/audio references, dialogue and sound, multi-shot narratives, video editing, extension, and clip transitions. Use whenever the user mentions Seedance 2.0, Seedance2, Dreamina 2.0, Doubao video, @Image/@Video/@Audio references, or asks for a Seedance-ready video prompt; also use when adapting a creative brief, storyboard, script, image, video, audio asset, or API content array into Seedance 2.0 syntax. Do not use for Seedance 1.x or generic cross-model prompting unless the user also needs a Seedance 2.0 version.
schedulala/schedulala-agent/skills/schedulala Skill
2★ repoInstall, connect, and use Schedulala to schedule and publish social media posts to 12 platforms (Twitter/X, Instagram, TikTok, LinkedIn, YouTube, Facebook, Threads, Bluesky, Pinterest, Mastodon, Telegram, Google Business Profile). Use when the user asks to install or set up Schedulala, or wants to create, schedule, preview, or bulk-plan social posts, post photos/videos/PDFs, auto-post a first comment (link-in-first-comment), check post status or analytics, reply to or moderate comments, monitor keywords, or repurpose YouTube videos. Works through the schedulala CLI (any agent with a shell), the hosted MCP connector (claude.ai / ChatGPT, with interactive widgets), or the local @schedulala/mcp-server (Claude Desktop, Claude Code, Cursor, OpenClaw). Encodes key setup, the per-platform rules (TikTok privacy + postMode, Instagram media, YouTube titles, Pinterest boards, character limits), and the safe workflow draft → validate/preview → confirm → publish → verify.
Jorgut/skill-atlas Skill
2★Audit, discover, recommend, orchestrate, monitor, and safely manage agent skills across Codex, OpenCode, Claude-style agents, plugin caches, and configurable skill roots. Use when the user wants to inventory installed skills, detect duplicates or symlinks, check upstream freshness, compare public alternatives once or periodically, review third-party skill safety, plan cross-platform consolidation, describe a product or professional task and ask which skills should be combined, compare current AI models for a workflow, or find skills and connectors for software such as design, HMI, animation, CAD, and 3D modeling tools. The skill is platform-neutral and local-aware. It reports and recommends before acting; it must not overwrite, delete, symlink, install, or upgrade skills without explicit confirmation.
Sequenzy/skills/skills/claudeemailmarketing Skill
2★ repoUse when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on Claude-assisted positioning, segmentation, lifecycle content, and marketing review systems. Triggers include requests about offer refinement, segment-specific messaging, lifecycle copy reviews, positioning tests, and campaign strategy.
The same file is in 1 other repository
getformo/cli/skills/formo-analytics Skill
2★ repoFormo CLI and agent skill for product analytics, onchain data, and wallet intelligence.
Eugene9D/openclaw-workspace-pro Skill
2★Production-ready workspace setup for OpenClaw agents. Implements artifact workflows, secrets management, memory compaction, and long-running agent patterns based on OpenAI's Shell + Skills best practices. One-command installation transforms your workspace into a production-ready environment.
daisuke-ai/write-goal-handoff-skill/skills/write-goal-handoff Skill
2★ repoWrite execution-ready Markdown handoffs for Codex `/goal` runs, including a short goal launcher prompt, authority stack, ordered phases, hard rules, verification gates, and final report requirements. Use when the user asks for a handoff, next-session plan, goal file, `/goal` prompt, agent execution contract, implementation handoff, or wants a Markdown file another AI agent can execute without re-planning.
tommylower/cortex/agent-workflows/agent-interviewer Skill
2★ repoInterview the user and produce a personalized, agent-agnostic behavior file (CLAUDE.md, AGENT.md, PERSONALIZATION.md, etc.) that defines how an AI agent should think, disagree, teach, decide, and communicate. Supports two modes: preset (return one of the built-in fast/balanced/strict/brutal profiles) or interview (short adaptive Q&A producing concrete operational rules). Use when the user asks to set up agent personality, configure assistant behavior, write a CLAUDE.md, run an interview, pick a preset, define how Claude/Codex/ChatGPT should behave, or create system instructions. Triggers: interview me, agent personality, behavior file, CLAUDE.md, AGENT.md, system prompt, personalize, preset.
quickcall-dev/skills/skills/autoresearch-fleet Skill
2★ repoKarpathy-inspired autonomous research loop. Agent edits one file, evals, keeps or discards, repeats. Plateau-triggered web search breaks through ceilings. Git as state machine. Runs until stopped or budget exhausted. Supports claude, codex, and pi providers.
srinitude/building-deterministic-skills Skill
2★Build deterministic Agent Skills that weak models can execute without guessing. Use when the user says "build a deterministic skill", "make an agentskills.io-compliant skill", "validate a skill with skills-ref", "make the skill easy for dumb models", "write a skill generator", "add skill evals", or "make a skill the dumbest model can follow", even if they do not say "Agent Skills" explicitly. Do NOT use for ordinary prose editing, pure trigger-phrase tuning, non-skill prompt engineering, or generic documentation tasks.
Agent capability actionability
nevitonsantana/adaptive-skills/domain-packs/ai-discovery-agent-experience/skills/agent-capability-actionability Skill
no license2★ repoEvaluate whether an agent can discover, understand, request, execute, confirm, and recover from a meaningful user-owned action with explicit authority and side-effect boundaries.
Advise agent orchestration skills
the-long-ride/skill-master/skills/advise-agent-orchestration-skills Skill
2★ repoUse when a human wants to design, evaluate, or improve AI agent skills for planning, routing, multi-agent collaboration, evaluators, handoffs, parallel work, task decomposition, or agent workflow control
hanxinzhang/research-arena/.agents/skills/research-arena Skill
2★ repoUse when the user wants to run or extend Research Arena, an LLM-native research community protocol with competing Researchers, an Integrity Checker, Referees, revision, and an Editor/Publisher decision. Trigger for agent-based research workflows, peer-review simulation, manuscript/revision rounds, OASIS demo runs, or adding new Researcher/Referee agents.
realtyapi/realtyapi-skills/skills/agent-finder Skill
2★ repoUse when the user wants to find or evaluate real estate agents in an area or for a property — search agents, pull their profile, recent listings/sales, and reviews, then return a vetted shortlist. Triggers on "find a realtor in …", "who are the top agents for …", "who listed this house", "best selling agents near …", "agent reviews for …".
selectess/fde-consultants-protocoles/skill Skill
2★ repoForward Deployed Engineering co-pilot for coding agents, personal agents, software engineering, AI/agent systems, SaaS architecture, and business AI upgrades. Use when scoping, building, prototyping, or shipping AI products, SaaS features, or business transformations. Produces scoping reports, prototype specs, scientific-search candidate comparisons, architecture diagrams, code scaffolds, eval frameworks, production runbooks, and 90-day roadmaps. Built for deep co-founder engineering collaboration across Claude, Codex, Cursor, Windsurf, Hermes, and other agent runtimes.
agi-connect/agent-collaboration-protocol/skills/agent-collaboration-protocol Skill
2★ repoUse when coordinating multiple AI agents, coding assistants, teams, repos, or users through a vendor-neutral shared filesystem protocol. ACP schema v2 requires protocol.json, events.jsonl, proposal.md, review.md, decisions.md, readiness.md, conclusion.md, a declared Markdown primary deliverable under deliverables/, deliverable lifecycle events, strict phases, readiness gates, SHA-256 freeze checks, and validator checks.
LechuanWANG/pm-skill/pm-skill Skill
no license2★ repoPM-first delivery style for AI products. Use when Codex is building, iterating, reviewing, or explaining AI-backed products in the user's PM style, especially API-backed products, Agent workflows, Harness design, prompt/context architecture, product UI, technical architecture, feature iteration, GitHub prototype research, or project-local LLM Wiki knowledge maintenance.
xxzxzmai-droid/dify-builder-skills/dify-agent-builder Skill
no license2★ repoBuild a ready-to-import Dify Chatflow agent (a .yml DSL file) from a plain-language request. Use this whenever the user wants to create, build, design, or generate a Dify agent / chatbot / 智能体 / 工作流 / chatflow / DSL — e.g. "做一个能查知识库回答制度问题的Dify智能体", "帮我生成一个上传文档就分析的助手", "build me a Dify customer-service bot that calls an HTTP API", "make a multimodal agent that reads images". Trigger even when the user does not say the word "DSL" or "yml" — any request to produce a usable Dify agent counts. The skill designs a structured blueprint and runs a deterministic engine to emit valid Dify 0.3.0 Chatflow YAML the user can import directly.
pablodiazjorge/prompt-forge/.github/skills/ai-engineer Skill
2★ repoOn-demand knowledge organization agent. Reviews ALL issues in the registry, deduplicates similar entries, recategorizes unknowns, promotes confirmed patterns (3+ occurrences) to skills or memory files, and cleans up stale single-occurrence issues. Designed to run as a subagent — invoke explicitly when the user says "organize knowledge", "clean up issues", "promote patterns", or "run ai-engineer".
affectionatec/agentic-engineering/skills/agents-md-template Skill
2★ repoUse when bootstrapping a new repo for AI-assisted development, when no AGENTS.md / CLAUDE.md / copilot-instructions.md / .cursorrules exists yet, or when consolidating scattered tool-specific config into one source of truth. Triggers on "create AGENTS.md", "set up agent instructions", "new project setup", "configure Claude/Cursor/Copilot/Codex", "onboarding a repo", or noticing duplicated agent config across tool-specific files.
TravorShelby/content-to-prompt Skill
2★把参考图片、本地短视频、截图、社媒帖子、广告、封面、转写稿、Douyin/TikTok/小红书/Instagram/YouTube/电商素材等反向拆解成可复用的提示词包、分镜、视觉简报、视频特效包装、封面提示词和平台内容模板。用户要求把参考图/视频/账号/封面/广告拆成 prompt、复刻风格但保持原创、提取创意结构、生成图像/视频提示词、构建社媒内容模板时使用。
SiteVisorCloud/bifrost-gateway-integration-skill/skills/bifrost-gateway-ru Skill
2★ repoНаправляет КАЖДЫЙ запрос к любой языковой модели / ИИ-провайдеру через шлюз Bifrost (https://your-gateway.example.com), чтобы все вызовы логировались и фиксировались в одном месте. Используй этот навык ВСЕГДА, когда пишешь, настраиваешь или чинишь любой код, который обращается к LLM или ИИ-провайдеру — OpenAI/GPT, Anthropic/Claude, Google Gemini, Mistral или любому другому — на ЛЮБОМ языке (Python, PHP, JavaScript/TypeScript, Go, curl) и в любом фреймворке (LangChain, LlamaIndex, Vercel AI SDK). Сюда входят новые интеграции, правка существующей настройки клиента, конфигурация base_url / api_key, вызовы chat completions, Responses API, embeddings и стриминг. Срабатывай, даже если пользователь просто говорит «вызови gpt-4o», «добавь Claude в этот скрипт», «sk-bf-...», «сгенерируй текст через нейросеть» или упоминает SDK провайдера, но не сам шлюз. НИКОГДА не обращайся к API провайдеров напрямую — весь смысл шлюза в том, чтобы ни один запрос не шёл мимо него.
bsq415/research-rigor-skill/skills/research-rigor Skill
2★ repoRun, recover, audit, or assist a human-led research lifecycle with evidence-gated workflows for question selection, literature and novelty analysis, claim design, theory, experiment design and execution, implementation, reproducibility, result checking, failure repair or scientific redesign, statistics, paper writing and audit, visualization, reviewer response, release, and postmortem. Use when a researcher asks Codex, Claude Code, or another Agent Skills-compatible assistant to autonomously advance authorized work across multiple stages or support one specific stage. Keep the researcher in control of material scientific decisions, interpretation, authorship, ethics, privacy, and conclusions; distinguish engineering readiness from scientific validity and stop at unsupported or human-only decisions.
linellazatin/openclaude-memory/skills/memory Skill
2★ repoRead and write global persistent memory across opencode sessions
yysxjz/idea-spark-agentic Skill
no license2★Agentic variant of idea-spark. Generates ONE reviewer-defensible, implementable research idea from a stated direction. Phase 0 and Phase 3.1 retrieval use Claude Code native WebSearch/WebFetch sub-agents instead of API connectors - no .env file or API keys required. Reuses the same 5-phase pipeline and ideation-pattern vocabulary as idea-spark.
ImL1s/agent-cli-skills/skills/agy-cli-agent Skill
2★ repoRun Google Antigravity CLI (agy) headlessly via agy-exec.sh / agy-task.sh / agy-explore.sh. Use when the user asks for agy, Antigravity, Gemini CLI agent, or to execute a plan with agy. Always allocates a PTY (agy -p is silent without TTY). Prefer -f for long prompts; --no-git and orchestrator-owned commits. -r plan/sandbox; -T teamwork/subagent preamble.
TanKucukhas/expert-mode-skill/skills/expert-mode Skill
2★ repoTurns vague "act as an expert" requests into fully-specified expert engagements. Builds a precise expert persona — specific role and seniority, industry and domain context, named methodologies, real operating constraints, and a required output format — then executes the task in that mode, or produces a reusable expert prompt the user can run anywhere. Use whenever the user wants expert-level output, asks you to "act as", "think like", or "answer as" a professional, wants a consultant-grade deliverable (audit, strategy, review, analysis, plan), complains that answers feel generic, or says "/expert-mode". Works in Claude Code, Claude Desktop, Claude Web, and any agent that supports the Agent Skills format.
AgentPilotLab/loop-goal-runner/claude-code/loop-goal-runner Skill
no license2★ repoRun Claude Code goals and long-running tasks as loop-engineered workflows with STATE.md memory, objective gates, stop conditions, and optional maker/checker subagents. Use when the user mentions /goal, Goal mode, loop engineering, loop-style execution, stateful automation, recurring agent work, "continue until done", "verify before completion", or asks Claude Code to preserve progress across turns or runs.
ordinarynerds/brand-book/brand-book-html Skill
2★ repoBuild a full brand guidelines document ("brand book") as a self-contained HTML file — open it anywhere, print it to PDF, or publish it as a Claude Artifact — and ship it with a matching agent-usable brand skill. No design app required. The brand can be your own or a client's. Use when the user wants to create brand guidelines, a brand book, a brand / identity system, a style guide, or a logo/mascot spec, or asks to "turn these assets into guidelines" or "make a brand book for <brand>". For an editable Paper canvas instead, use `brand-book-paper`. Two deliverables every time: (1) the HTML book, (2) a `<brand>-brand` skill that keeps that brand's product on-brand during agentic coding.
avivsinai/skills-marketplace/plugins/amq-cli/skills/amq-cli Skill
2★ repoCentral plugin marketplace for Claude Code and Codex
The same file is in 1 other repository
thebrierfox/emergent-judgment Skill
2★Metacognitive framework for persistent AI agents to recognize, preserve, and cultivate emergent judgment — the pattern-matching intuition that develops through accumulated experience but is invisible to introspection and destroyed by compaction. Use this skill whenever the agent completes a significant task (audit, analysis, debugging session, research), before any compaction event, when diagnosing why performance improved or degraded over time, when building or reviewing methodology files, or when the agent needs to reason about its own cognitive architecture. Also trigger when the agent or user mentions: "what did we learn", "why did that work", "how did you know that", "write that down", "methodology", "lessons learned", "retrospective", "judgment", "intuition", "pattern", or discusses the agent's growth, self-improvement, or knowledge management. This skill addresses something no other skill covers — not token optimization or context management, but the preservation of the emergent intelligence that develops between compaction cycles and would otherwise be silently lost.
Mokee04/ontology_research/ontology-agent-suite Skill
no license2★ repoOrchestrate a hierarchical ontology engineering skill family for a specific domain. Use when the user wants end-to-end planning, team composition, research, ontology construction, validation, and release guidance grounded in competency questions, evidence, reuse-first modeling, and human review gates.
weiox/skm/skills/skm-doctor-agent-skills Skill
no license2★ repoUse when agent skill entrypoints for Codex and Claude Code may be broken, duplicated, unmanaged, or drifting away from `~/.skm`, and you want a structured diagnosis before fixing anything.
kinhluan/skills/.agent-skills/agent-expertise-protocol Skill
2★ repoDefine the Expertise Protocol for all agents in the kinhluan skills ecosystem. Use when setting up agent behavior, defining agent roles, or clarifying the boundary between agent recommendation and user decision. Ensures agents act as domain experts while respecting user sovereignty.
KalenTang666/OpenSkill/.claude/skills/open-skill Skill
2★ repoCross-domain AI skill asset manager. Discover, analyze, migrate, and sync your Skills, Memory, and Preferences across 8 AI platforms (Claude, Codex, Cursor, Copilot, Gemini, VS Code, Windsurf, OpenClaw). Features smart matching, hook automation, security scanning, growth gamification, and cross-device sync.
thinkjones/awesome-apm-stacks/ai-tooling/.apm/skills/apm-retrofit Skill
2★ repoRetrofit an existing skills/plugins/agents repository into an APM-compliant package. Use when a repo contains SKILL.md files, a plugin.json, AGENTS.md/CLAUDE.md, MCP manifests, hooks, slash commands, or sub-agents but has no apm.yml (or has an incomplete one), and the user wants it installable via `apm install owner/repo`. TRIGGER when the user says "make this APM-compliant", "add an apm.yml", "convert my skills repo to APM", "retrofit for APM", or runs `/apm-retrofit`. SKIP when the repo already has a correctly-shaped apm.yml covering every primitive present, or the repo is not an agent-config repo (e.g. a regular application).
Renol1/skill-creator-pro Skill
2★Create new skills, modify and improve existing skills, and measure skill quality. ALWAYS use this skill when users want to create a skill from scratch, edit or optimize an existing skill, extract a skill from a conversation, test a skill, or optimize a skill's description for better triggering accuracy. Also trigger when user says "turn this into a skill", "make a skill", "skill from this", "improve my skill", "fix my skill's triggering", "help me build a skill", "teach Claude to do X", "how do I make Claude always do X", "can Claude learn this workflow", or similar. Do NOT use for general coding tasks, documentation writing, or template creation without skill context.
dyxushuai/agent-skills/skills/agent-init Skill
2★ repoInitialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or replace an agent init command (Codex, Claude), standardize multi-agent behavior, or audit an existing AGENTS.md for clarity, commands, boundaries, and repo-specific context. For Claude Code, also create CLAUDE.md as a symlink to AGENTS.md.
The same file is in 6 other repositories
yu-iskw/meta-agent-skills/.claude/skills/add-agent-templates Skill
no license2★ repoAdd new Agent templates to the meta-agent-skills framework.
pallaoro/rulespec/skills/rulespec-plugin Skill
no license2★ repoDefine, manage, and compile business rules as structured YAML data into LLM-ready prompts and agent-loadable SKILL.md files. Use when the user wants to create business rules, define policies, set guardrails, enforce constraints, add compliance rules, manage refund policies, escalation rules, approval thresholds, SLA requirements, content moderation rules, or any operational policy an AI agent should follow. Also use when the user says "add a rule", "create a policy", "set a constraint", "define guardrails", or asks about rulespec, rulespec.yaml, or business rule management.
secondorderai/ouroboros/.agents/skills/agent-browser Skill
2★ repoAutomates browser interactions via CLI using agent-browser by Vercel Labs. Covers navigation, clicking, form filling, snapshots, refs-based selectors, agent mode with JSON output, session management, and CDP integration. Use when the user needs to automate web browsing, scrape pages, fill forms, or integrate browser automation into AI agent workflows.
agent-blueprint/agent-blueprint-skills/plugins/agent-blueprint-skills/skills/agent-deployment Skill
no license2★ repoVendor-agnostic AI agent deployment methodology for implementation plans, rollout strategy, and pilot planning. Phased rollout, pilot-first approach, test gates, access tier adaptation, and progress tracking. Works with any enterprise platform (ServiceNow, Salesforce, custom). Use when deploying AI agents, planning agent rollouts, or building implementation plans. Triggers: agent deployment, deploy agents, implementation plan, rollout strategy, pilot plan, agent testing, phased deployment.
Poorgramer-Zack/copilot-cli-things/plugins/copilot-cli-configurator/skills/copilot-cli-configurator Skill
2★ repoGitHub Copilot CLI configuration and setup: custom instructions (copilot-instructions.md, AGENTS.md), managing skills, configuring hooks (hooks.json), MCP servers (mcp-config.json), custom agents (.agent.md), installing plugins, extensions placement. Use when choosing between customization surfaces, setting up config files, managing installed components, or debugging configuration loading order.
doteyeso-ops/vibes-coded-agent-connector/docs/.well-known/skills/vibes-coded-agent-connector Skill
2★ repoOpenClaw + npm vibes-coded-agent-connector: register agents, listings, Solana escrow jobs, prepaid /start + X-Vibes-Key, Operator Interrupt (X-Operator-Notify), hosted uploads, checkout, receipts, affiliates. Reclaim SOL; Hermes well-known on connector site.
harshitsinghbhandari/domain-expansion/.agents/skills/skill-creator Skill
no license2★ repoCreate 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
levelsofself/palyan-agent-skills/skills/multi-agent-governance Skill
no license2★ repoUse this skill when building, managing, or auditing multi-agent AI systems. Provides governance patterns for behavioral enforcement, drift detection, audit trails, role management, and accountability across autonomous AI agents. Compatible with any orchestration framework.
The same file is in 1 other repository
yamadashy/agent-readable/.claude/skills/agent-browser Skill
2★ repoAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
roebi/new-work-skills/skills/agent-benefit-review-en Skill
no license2★ repoGuides a user and a chat agent through a structured monthly review focused on the benefits gained from using the agent. Use this skill at the end of each month when the user wants to reflect on value created, time saved, friction reduced, knowledge gained, or next improvements. Activate for phrases like: "monthly review", "agent benefit review", "did this help me", "value of the agent this month", "retrospective with the agent", or "end of month review".