Context & AI engineering
25,745 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
AI-Business-Tools/claude-code/skills/knowledge-base-update Skill
4★ repoKnowledge base sync and health check for the knowledge-base skill. Scans all topic folders for unindexed documents, removes index entries for missing files, refreshes topic descriptions, cleans up stale split directories, and reports health issues (missing summaries, naming inconsistencies, orphaned files, duplicate content).
AI-Business-Tools/claude-code/skills/knowledge-base Skill
4★ repoPersonal knowledge base manager. Processes inbox files (PDF, MD, DOCX, RTF, TXT, HTML, PNG, URL), extracts metadata, renames with citation conventions, generates summaries, maintains a searchable index, answers questions grounded in indexed sources, performs full-text keyword search, moves pipeline output into topic folders, and builds slide decks from indexed or external content via a slides skill.
oyusypenko/creo/skills/creo-ai-generation Skill
4★ repoLLM generation pipeline expertise covering prompt engineering, structured output validation, queue-based async processing, SSE real-time progress, and multi-mode generation strategies. Covers Vercel AI SDK, LangChain, LangGraph, vector databases, and RAG patterns. Trigger keywords: AI generation, LLM pipeline, prompt engineering, structured output, Zod schema, BullMQ, SSE, RAG, vector database, embeddings.
oyusypenko/creo/skills/creo-image-prompt Skill
4★ repoGenerate optimized image prompts for AI image generation models including DALL-E 3, Midjourney, Stable Diffusion XL, Flux, and others. Creates contextually appropriate, visually compelling prompts based on page content and brand style. Trigger keywords: image prompt, AI image, hero image, marketing image, generate prompt, image generation.
YousefNabil-SOC/claude-apex/skills/gs-benchmark Skill
4★ repoPerformance regression detection - baseline page load, Core Web Vitals, resource sizes. CARL TRIGGERS: benchmark, performance check, page speed, core web vitals, perf baseline. SOURCE: garrytan/gstack/benchmark, integrated as gs-benchmark on 2026-05-29.
ralvarezdev/ralvaskills/skills/meta/skill-builder Skill
4★ repoScaffold a new ralvaskills skill per SPECS.md — SKILL.md skeleton, optional STACK/RECIPES, folder placement, SPECS updates. Interview-first; never guesses. Use when authoring a new skill or invoking /skill-builder.
ralvarezdev/ralvaskills/skills/protocols/mcp-architect Skill
4★ repoMCP (Model Context Protocol) 2025-11-25 server standards — tool/resource/prompt primitives, capability negotiation, Streamable HTTP transport with Mcp-Session-Id, OAuth 2.1 + RFC 8707 resource indicators, tool annotations (readOnly/destructive/idempotent), structured output, JSON-RPC error mapping, prompt-injection and SSRF defenses, MCP Inspector testing. Python (FastMCP) and Go (official SDK) recipes. Use when designing, reviewing, or scaffolding an MCP server.
mshadmanrahman/pm-operating-system/_context/skills/handoff-doc Skill
4★ repoCreates a portable handoff document when switching between chats, tasks, or sessions. Captures context, decisions, and next steps so nothing is lost.
mshadmanrahman/pm-operating-system/_context/skills/orchestrator Skill
4★ repoWave-based parallel agent execution with manifest communication. Decomposes complex work into 3+ parallel sub-agent streams, coordinates handoffs, and triggers strategic compaction between phases. Use when a task needs multiple agents working simultaneously.
soden46/syarif-laravel-ai-skills/skills/data-chunking-large-datasets Skill
4★ repoLaravel guidance to process large datasets efficiently using chunk(), chunkById(), lazy(), and cursor() to reduce memory consumption and improve performance
soden46/syarif-laravel-ai-skills/skills/laravel-prompting-patterns Skill
4★ repoUse Laravel-specific vocabulary-Eloquent patterns, Form Requests, API resources, jobs/queues-to get idiomatic framework code
mrhinkle/aienterprise-skills/plugins/aie-skill-creator/skills/aie-skill-creator Skill
4★ repoBuild a new, high-quality Claude Agent Skill from scratch — the right frontmatter, a tight SKILL.md, progressive-disclosure reference files, a self-test, and packaging as a .skill zip or a plugin/marketplace entry. Also improves or audits an existing skill against a quality rubric, and fixes descriptions that don't trigger reliably. Trigger on "create a skill," "make a skill," "build a skill for X," "turn this workflow into a skill," "write a SKILL.md," "improve this skill," "audit my skill," "why doesn't my skill trigger," or "package this skill."
NatiDvir/video-skills/director/seedance-prompt-builder Skill
no license4★ repoWrite production-ready Seedance 2.0 prompts (image, video, and motion/edit) for Higgsfield. Use this skill whenever the user wants a single Seedance prompt rather than a full shotlist — e.g. "make a Seedance prompt for X", "write me a video prompt", "restyle this clip", "turn my photo into a character sheet", "transformer video of my car", "bullet-time freeze", "sticker peel", "swap the character in my video". Covers the recurring prompt recipes (text-to-video, POV action, character/storyboard image sheets, timed-beat edits, JSON prompts, transformer template, freeze-frame, sticker peel, environment/object restyle) and the exact media-placeholder syntax Seedance expects. If the user instead wants a whole script broken into many numbered 15-second shots, use the seedance-shotlist-director skill instead. This skill produces one copy-ready prompt block (plus any required reference-image prompt) directly in chat.
NatiDvir/video-skills/director/storyboard-cheatcode Skill
no license4★ repoTurn a one-line concept into a multi-panel previs storyboard image, then optionally a cheap-preview video and a hero video render. Uses the Higgsfield MCP server (image and video tools). Asks the user before every render and never assumes budget tolerance. Use when the user asks to build a storyboard, plan AI video shots, generate a previs sheet, or wants an AI video from a concept.
NatiDvir/video-skills/higgsfield/11-social-hook Skill
no license4★ repoGenerate viral social media hook video prompts for TikTok, Instagram Reels, and YouTube Shorts using Seedance 2.0 on Higgsfield. Use whenever the user wants to create scroll-stopping hooks, viral short-form video, attention-grabbing openers, TikTok content, Reels content, Shorts content, or any social-media-optimized video. Triggers on: social media video, TikTok, Instagram Reels, YouTube Shorts, viral video, hook, scroll-stopper, short-form, trending, engagement, views, or any request for social media video content. Use even for "make something that gets views" or "viral content."
nahiddotai/operator-powers/plugins/operator-powers/skills/llm-council Skill
4★ repoPressure-test a real decision with independent perspectives, anonymous peer review, and a final verdict when the user wants to compare options or choose a direction.
dongzhigang13305312738-art/paper-skills/zotero-gpt-guide Skill
no license4★ repoGuide to Zotero GPT for AI-powered research assistance within Zotero
The same file is in 1 other repository
dongzhigang13305312738-art/paper-skills/zotero-mcp-guide Skill
no license4★ repoGuide to Zotero MCP for connecting Zotero library with AI assistants
The same file is in 1 other repository
Ldxs001/workbuddy-skills/skills/local-rag-builder Skill
4★ repo本地 RAG 系统搭建技能,支持环境检测修复、嵌入模型多源下载、5种切分策略 + GuardStack + 后处理 + 插件注册、多知识库管理 + 自动分类规则、可调 Prompt、Web 可视化配置 + 极客模式 + 模板管理
Ldxs001/workbuddy-skills/skills/memory-pet Skill
4★ repo宠物记忆压缩技能 - 通过文本块宠物交互触发记忆保存。纯ASCII文字图,Python全量管理,亲密度衰减与逃跑机制,跨平台智能体记忆系统。
escoffier-labs/skillet/skillet/skills/memory-handoff Skill
4★ repoA skillet full of agent skills that actually ship work. Production-tested SKILL.md workflows for audits, security, releases, and handoffs.
escoffier-labs/skillet/skillet/skills/worktree Skill
4★ repoA skillet full of agent skills that actually ship work. Production-tested SKILL.md workflows for audits, security, releases, and handoffs.
stealth-engine/skills/skills/dual-agent-review Skill
4★ repoReview a change set with two or more independent AI reviewers in parallel — a Sonnet subagent and the CodeRabbit CLI — then merge + dedupe their findings, triage valid vs invalid, fix (directly or via parallel fix-subagents), and hand back a report of what was fixed/how and what was ignored/why. Use when asked to 'review my changes with two/multiple agents', 'dual-agent / multi-reviewer review', 'get a second opinion from Sonnet and CodeRabbit', 'review the diff and fix the valid issues', 'run parallel reviewers and fix in parallel', or to cross-check one reviewer against another before committing. Diff-scoped by default (branch-vs-base or the PR diff), like CodeRabbit — NOT a whole-repo audit.
Git trunk branch and pr automation
stealth-engine/skills/skills/git-trunk-branch-and-pr-automation Skill
4★ repoTrunk-based Git workflow with enforced branch naming and squash-merge PR titles. Use when setting up or standardising a branch/PR workflow, naming branches (feature/ fix/ hotfix/ and AI-agent prefixes claude/ cursor/ codex/ copilot/ codegen-bot/ dependabot/), configuring squash-only merges where the PR title becomes the commit and the body is the concatenated commits, making the PR title a valid Conventional Commit, adding GitHub Actions that validate branch names or auto-normalise PR titles, fixing a PR-title bot that loops, or deciding trunk vs release branches. Covers the GitHub repo settings, the validation/normalisation workflows, and how it feeds semantic-release.
stealth-engine/skills/skills/multi-agent-codebase-audit Skill
4★ repoAudit an ENTIRE codebase with multiple agents in parallel — map the repo, partition it into review slices, fan out one (or more, multi-lens) reviewer subagent per slice, reduce with a cross-cutting/architecture critic + a completeness check, then triage, fix, and report with an honest coverage ledger. Use when asked to 'audit the whole codebase', 'full security/quality review of the repo', 'review the entire project', 'do a deep/comprehensive code audit', 'scan everything for bugs or vulnerabilities', when onboarding/inheriting an unfamiliar repo, or for a periodic deep sweep. Whole-repo scoped and scales agent count to repo size — NOT a diff review (for changed lines use dual-agent-review).
emaballarin/ccplugins/plugins/mindfunnel/skills/prime Skill
4★ repoPrime the current project for the mindfunnel workflow — stamp a project-scoped `AGENTS.md` from the bundled stub (if absent), create a project-local `CLAUDE.md` symlink to `./AGENTS.md`, touch an empty `PROJECT.md` if absent, clean up legacy `SOUL.md` / `CLAUDE.md` / `AGENTS.md` symlinks left behind by pre-0.3.0 primings, and strip legacy `CLAUDE.md`/`AGENTS.md` entries from `.gitignore` so the new committed files track cleanly. Run from the project root. Idempotent with a safety guard — leaves pre-existing hand-authored files alone. Requires `/mf:setup` to have been run first.
emaballarin/ccplugins/plugins/mindfunnel/skills/setup Skill
4★ repoOne-time bootstrap — seed ~/.mindfunnel/ with AGENTS.md, SOUL.md, USER.md, and PROJECT.md.example from the plugin's bundled templates. Use the first time you run the mindfunnel plugin on a new machine, or when ~/.mindfunnel/ is missing. Idempotent — detects existing files and never overwrites. Also creates a CLAUDE.md symlink pointing at AGENTS.md inside ~/.mindfunnel/, and ~/.claude/{SOUL,USER}.md + ~/.codex/{SOUL,USER}.md symlinks so both agents can reach the same personal files.
MarieLynneBlock/arcanum-artifex/skills/agentic/agent-supply-chain Skill
no license4★ repoReview, generate, and verify supply-chain integrity controls for AI agent tools, plugins, MCP servers, skills, prompts, and custom agents, including SHA-256 manifests, dependency pinning, provenance evidence, promotion gates, and CI verification.
MarieLynneBlock/arcanum-artifex/skills/agentic/agentic-eval Skill
no license4★ repoUse when designing and implementing evaluation loops for AI agents, including reflection, evaluator-optimiser patterns, rubric scoring, LLM-as-judge review, test-driven refinement, convergence checks, and iteration logging.
MarieLynneBlock/arcanum-artifex/skills/agentic/copilot-cli-quickstart Skill
no license4★ repoBeginner-friendly interactive tutorial for GitHub Copilot CLI concepts, slash commands, permissions, file context, planning, and custom instructions.
MarieLynneBlock/arcanum-artifex/skills/agentic/evaluation/eval-driven-dev Skill
no license4★ repoBuild an automated evaluation pipeline that tests a Python LLM application end-to-end with pixie test — real code paths, real LLM calls, instrumented external data — and scores outputs with evaluators instead of assertions. Use when adding evals to a Python AI app.
MarieLynneBlock/arcanum-artifex/skills/agentic/github-copilot-starter Skill
no license4★ repoSet up a GitHub Copilot customisation starter pack for a new project based on its technology stack, including instructions, skills, agents, and optional setup workflow files.
MarieLynneBlock/arcanum-artifex/skills/agentic/mcp/foundry-agent-sync Skill
no license4★ repoCreate and synchronise prompt-based AI agents directly within Azure AI Foundry via REST API, from a local JSON manifest. Unlike scaffolding skills that only generate local code, this skill registers agents in the Foundry service itself — making them immediately available for invocation. Use when the user asks to create agents in Foundry, sync, deploy, register, or push agents to Foundry, update agent instructions, or scaffold the manifest and sync script for a new repository. Triggers: 'create agent in foundry', 'sync foundry agents', 'deploy agents to foundry', 'register agents in foundry', 'push agents', 'create foundry agent manifest', 'scaffold agent sync'.
MarieLynneBlock/arcanum-artifex/skills/agentic/mcp/mcp-cli Skill
no license4★ repoInterface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers, list available MCP servers/tools, or call MCP tools from command line.
Mcp copilot studio server generator
MarieLynneBlock/arcanum-artifex/skills/agentic/mcp/mcp-copilot-studio-server-generator Skill
no license4★ repoGenerate a complete MCP server implementation optimised for Copilot Studio integration with proper schema constraints and streamable HTTP support
MarieLynneBlock/arcanum-artifex/skills/agentic/prompt-builder Skill
no license4★ repoGuide users through creating high-quality GitHub Copilot prompt files with clear structure, appropriate tools, validation criteria, and maintainable instructions.
MarieLynneBlock/arcanum-artifex/skills/agentic/tldr-prompt Skill
no license4★ repoCreate tldr-style summaries for GitHub Copilot customisation files, MCP server documentation, or Copilot documentation from files, URLs, or focused queries.
MarieLynneBlock/arcanum-artifex/skills/development/java/java-mcp-server-generator Skill
no license4★ repoGenerate a complete Model Context Protocol server project in Java using the official MCP Java SDK with reactive streams and optional Spring Boot integration.
MarieLynneBlock/arcanum-artifex/skills/development/python/python-mcp-server-generator Skill
no license4★ repoGenerate a complete MCP server project in Python with tools, resources, and proper configuration
MarieLynneBlock/arcanum-artifex/skills/scientific/bgpt-paper-search Skill
no license4★ repoSearch scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.
Geono/claude-launchpad/plugins/claude-launchpad/skills/launchpad Skill
4★ repoEnd-to-end development pipeline orchestrator. Guides through spec writing, task breakdown, parallelization planning, and multi-agent execution. Chains launchpad-spec, launchpad-plan, and launchpad-run in sequence. Triggers on /launchpad, build this feature, I want to build.
n-n-code/n-n-code-skills/.agents/skills/context-engineering Skill
4★ repoWorkflow for context packets, context audits, compaction, handoffs, session memory, and deciding what AI-agent context to load, retrieve, trim, summarize, refresh, or omit. Use for context rot, context flooding, stale or missing context, task switching, and long-running agent sessions. Do not use when prompt wording, repo file discovery for a story card, or AGENTS.md authoring is the main artifact.
n-n-code/n-n-code-skills/.agents/skills/prompt-engineering Skill
4★ repoPrompt engineering workflow for designing, rewriting, debugging, evaluating, and optimizing LLM prompts, system prompts, developer prompts, few-shot examples, structured-output instructions, tool-use prompts, and prompt eval cases. Use when prompt behavior, reliability, safety, cost, latency, or model fit is the main task. Do not use for generic prose editing, model selection alone, or ordinary documentation work with no prompt artifact.
Story implementation orchestrator
n-n-code/n-n-code-skills/.agents/skills/story-implementation-orchestrator Skill
4★ repoCoordinate the full story-to-plan preparation workflow across user-story-clarifier, story-repo-scout, and story-implementation-planner. Use when a rough ticket needs clarification, repo scouting, implementation planning, packet validation, partial-packet resumption, or downstream skill routing before coding; avoid direct implementation.
roodlicht/accans-sec-skills/skills/sast-orchestrator Skill
no license4★ repoSAST orchestration for Semgrep, CodeQL and SonarQube. Covers tool selection, ruleset curation, PR-comment integration, noise reduction with baselines, and language-specific linters (bandit, gosec, brakeman, eslint-security) when they add coverage.
celticht32/Couchbase-Skills-for-Claude.ai/skills/couchbase-analytics/cb-analytics-mcp-setup Skill
4★ repoUse this skill when the user is setting up cb-analytics-mcp from scratch or troubleshooting an existing install — generating secrets, configuring .env, running --check, picking single- vs multi-cluster mode, tuning rate limits, configuring audit rotation, or using the CLI. Trigger when the user mentions "install", "configure", "first run", "MCP_API_KEY", "GUI_PASSWORD", "clusters.json", "cb-analytics-mcp --check", "MAX_QUERY_ROWS", "RATE_LIMIT_", "AUDIT_ROTATE", "tools call", or "tools list".
celticht32/Couchbase-Skills-for-Claude.ai/skills/couchbase/couchbase-ai-applications Skill
4★ repoDesign and build AI-powered applications on Couchbase, including RAG pipelines, vector search architecture, embedding strategies, and AI agent data patterns. Use whenever the user asks about RAG, retrieval-augmented generation, vector search for AI, Hyperscale Vector Index (HVI), Composite Vector Index (CVI), Search Vector Index (SVI), embedding pipelines, semantic search, AI agent memory, grounding LLMs with Couchbase, agentic data patterns, billion-scale vector search, multi-vector search, AI application architecture, or 'how do I build an AI app with Couchbase.' Distinct from couchbase-fts (which covers FTS index mechanics and query syntax) — this skill is about end-to-end AI application design: the data model, embedding pipeline, index type selection, retrieval strategy, and integration with LLM frameworks. Use proactively when the user is building AI features or has a use case involving language models, embeddings, or semantic retrieval.
celticht32/Couchbase-Skills-for-Claude.ai/skills/couchbase/couchbase-app-integration Skill
4★ repoBuild application code that integrates with Couchbase. Use whenever the user asks about Couchbase SDKs (Python, Java, Node.js, .NET, Go, C, Ruby, PHP, Scala, Kotlin), connection strings, connection pooling, async vs sync clients, retry strategies, timeout patterns, circuit breakers, durability levels, scan consistency, bulk / batch operations, application-side transactions, the transactions library, idempotency, write conflict handling, active-active XDCR application patterns, error categorization (transient vs durable), TLS / mTLS client setup, certificate handling in clients, or any 'how do I do X in the Couchbase SDK' question. Triggers on application-developer language distinct from couchbase-mcp (server operation), couchbase-data-modeling (database design), and couchbase-sizing (capacity). Use proactively for: integrating a new app, debugging client-side errors, choosing durability for a write, picking the right SDK pattern, handling XDCR conflicts at the application layer.
celticht32/Couchbase-Skills-for-Claude.ai/skills/couchbase/couchbase-magma Skill
4★ repoUnderstand and tune the Magma storage engine in Couchbase. Use whenever the user asks about Magma, Magma storage engine, Couchbase storage backend, couchstore vs Magma, 128 vBuckets vs 1024 vBuckets, Magma compaction, Magma memory requirements, Magma disk layout, storage engine selection, when to use Magma vs couchstore, storageBackend bucket setting, numVBuckets bucket setting, or 'which storage engine should I use.' Distinct from couchbase-sizing (which has a brief Magma section in disk.md) — this skill covers Magma behavior, tradeoffs, and tuning in depth. Use proactively when the user is creating new buckets on 8.0 or is investigating storage-related performance issues.
celticht32/Couchbase-Skills-for-Claude.ai/skills/couchbase/couchbase-mcp Skill
4★ repoOperate Couchbase clusters and Capella v4 through an MCP server. Primary target is celticht32/MCP-Couchbase (167 tools) for full data-plane AND cluster admin; also covers the official Couchbase-Ecosystem/mcp-server-couchbase (narrower, data-plane-only, community-maintained, enterprise-supported via AI Data Plane license) and when to pick which. Use whenever the user mentions Couchbase, buckets, scopes, collections, SQL++ / N1QL, KV ops, subdocument ops, FTS, vector indexes, XDCR, eventing, backup, encryption / KMIP / DARE, user lock/unlock, query performance, Index Advisor, synonyms (8.x), or Capella organizations / projects / clusters / database users / allowed CIDRs / app services. Use proactively for cluster admin (rebalance, failover, recovery, autofailover, autocompaction, logs, alerts, audit, password policy), RBAC design, troubleshooting Couchbase errors, operational runbooks (rolling upgrade, node add/remove, post-failover recovery, backup/restore, credential rotation), and observability.
sefaertunc/Worclaude/.claude/skills/claude-md-maintenance Skill
4★ repoHow Claude writes rules for itself, when to update CLAUDE.md, keeping it lean and effective
sefaertunc/Worclaude/.claude/skills/context-management Skill
4★ repoContext budget awareness, when to compact, when to clear, subagent offloading
sefaertunc/Worclaude/.claude/skills/coordinator-mode Skill
4★ repoMulti-agent orchestration patterns: when to use coordinator mode, worker prompts, parallel execution
sefaertunc/Worclaude/.claude/skills/memory-architecture Skill
4★ repoFive-layer memory architecture: where each fact lives, how layers interact, when to promote learnings
sefaertunc/Worclaude/.claude/skills/prompt-engineering Skill
4★ repoEffective prompting patterns for working with Claude, demanding quality, writing specs
sefaertunc/Worclaude/.claude/skills/review-and-handoff Skill
4★ repoSession ending protocol, HANDOFF document format, seamless continuation between sessions
sefaertunc/Worclaude/.claude/skills/subagent-usage Skill
4★ repoWhen to use subagents, how many, context hygiene, worktree isolation patterns
sp-daewoon/chronicle/skills/claude-md Skill
4★ repoKeep the CLAUDE.md your agents rely on accurate and lean instead of stale. Use when maintaining (not first creating) a CLAUDE.md — syncing it with architecture, conventions and commands as the project evolves, and pruning bloat so it stays scannable. Complements the built-in /init by owning the ongoing upkeep.
medalsoftchina/workcopilot/embedded-skills/doa-harness Skill
4★ repo自动为项目搭建 Harness Engineering 工程轨道。一键生成 copilot-instructions.md、AGENTS.md、 tasks.json、CODEOWNERS、rules/*.md 五大配置文件,让 GitHub Copilot 从"碰运气"变成"稳定交付"。 USE FOR: 初始化 harness、搭建 copilot 工程轨道、配置 agent 约束、创建 instructions、 创建验证链、配置审批钩子、setup harness、init harness、harness engineering。 DO NOT USE FOR: 生成 PPT(使用 doa-ppt)、写代码逻辑、调试 bug。
warpirate/linkedin-maxxing/plugins/linkedin-maxxing/skills/write-hook Skill
no license4★ repoUse when user has a LinkedIn post body but a weak opening, wants to A/B several hook angles before drafting the full post, or their existing post is not earning "see more" expand clicks. Trigger phrases include "write a hook," "fix my hook," "give me 5 hook variants," "the first line of my post is weak," "rewrite the opening." Hook must fit the 210-character LinkedIn fold.