Context & AI engineering
25,772 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
Z-M-Huang/vcp/plugins/mcp-doc/skills/mcp-doc-scan Skill
14★ repoScan project and report documentation coverage. Finds undocumented directories, stale manifest entries, and prioritized recommendations.
Z-M-Huang/vcp/plugins/mcp-doc/skills/mcp-doc-sync Skill
14★ repoSync the git-doc-mcp manifest with current project state. Adds new docs not yet indexed, removes stale entries, refreshes descriptions and search index, and regenerates tool actions.
aborroy/aiup-alfresco/.cursor/skills/alfresco-architect-agent Skill
14★ repoGiven a business requirement, proposes full Alfresco extension architecture including content types, behaviours, REST endpoints, events, and deployment model. Produces an Architecture Decision Record.
aborroy/aiup-alfresco/.cursor/skills/alfresco-debugger-agent Skill
14★ repoGiven an Alfresco stack trace or log snippet, searches documentation and known issues to diagnose the root cause and suggest a fix. Covers classloader issues, model registration errors, Transform Service failures, and common ACS problems.
aborroy/aiup-alfresco/.cursor/skills/alfresco-migrator-agent Skill
14★ repoAnalyses an existing Alfresco AMP or JAR extension, identifies deprecated APIs and outdated patterns, and produces a migration plan with concrete code diffs.
SZoloth/skill-pack/skills/design-swarm Skill
14★ repoOrchestrate a team of 10 design agents for holistic UI audit, ideation, and implementation. Use when: "design swarm", "holistic audit", "design review with all lenses", "full design analysis". Modes: audit, ideate, implement (any combination). Targets: screenshots, URLs, file paths, or text briefs.
SZoloth/skill-pack/skills/mcp-builder Skill
14★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
The same file is in 18 other repositories
SZoloth/skill-pack/skills/orchestrating-swarms Skill
14★ repoMaster multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.
The same file is in 3 other repositories
SZoloth/skill-pack/skills/prompt-engineer Skill
14★ repoExpert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts, review or improve existing prompts, optimize AI instructions, or create any form of written communication intended for AI consumption (Claude, GPT, or other LLMs).
The same file is in 2 other repositories
SZoloth/skill-pack/skills/skill-creator Skill
14★ repoGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
The same file is in 16 other repositories
markoblogo/abvx-agent-skills/skills/agent-operations-contract Skill
14★ repoDefine and review concrete agent capability cards, asynchronous operation receipts, decision receipts with revalidation, isolated and trust-graded memory scopes, and evidence-backed provider or tool registry entries. Use when a project introduces named agents, scheduled or long-running work, durable decisions or memory, provider routing, MCP tools, or external-action approval boundaries.
markoblogo/abvx-agent-skills/skills/agent-tool-contract-review Skill
14★ repoReview tools, MCP functions, CLI commands, SET inputs, and AGENTS.md generator outputs as agent-facing contracts. Use when a tool description, schema, workflow input, or generated instruction may be ambiguous, unsafe, noisy, or hard for agents to call correctly.
markoblogo/abvx-agent-skills/skills/agents-best-practices Skill
14★ repoDesign, audit, or improve agentic systems and agent harnesses. Use for agent MVP blueprints, tool design, permission models, planning and goal loops, context compaction, memory, skills, connectors, observability, evals, safety, and provider-neutral agent architecture.
markoblogo/abvx-agent-skills/skills/bounded-evaluation Skill
14★ repoDesign small evaluation gates for agent outputs, skill changes, prompts, and tool contracts. Use when a change needs rubric checks, pairwise comparison, position-bias mitigation, regression fixtures, or LLM-as-judge discipline without building a heavy eval platform.
Bounded orchestration contract
markoblogo/abvx-agent-skills/skills/bounded-orchestration-contract Skill
14★ repoCoordinate an opt-in Planner, Reviewer, and bounded Executor workflow with stable findings, at most five review rounds, disjoint write ownership, explicit route evidence, and root-owned verification. Use when the user asks for plan review, multi-agent orchestration, routed executors, parallel implementation, or the SET bounded-orchestration capability.
markoblogo/abvx-agent-skills/skills/compaction-survival Skill
14★ repoPreserve working state across long sessions and context compaction by checkpointing decisions, edited files, blockers, open hypotheses, and unresolved errors into compact resumable artifacts. Use on long coding tasks, audits, research, or any session at risk of losing state after compaction.
markoblogo/abvx-agent-skills/skills/dynamic-workflow-packets Skill
14★ repoPlan and run large Codex tasks with compact dynamic workflow packets, risk gates, integration, and verification. Use when the user explicitly asks for dynamic workflows, packets, subagents, swarm, orchestration, long-running audits, multi-track coding/research work, job or client search agent design, migrations, repo-wide reviews, or tasks where independent discovery, implementation, review, and verification tracks would reduce drift.
markoblogo/abvx-agent-skills/skills/goal-loop-designer Skill
14★ repoCompile a raw agent goal into a bounded loop harness before execution. Use before launching long Codex, Claude Code, MiMo Code, or local-LLM coding loops when the goal needs clearer stop rules, verification rubric, judge prompt, budget policy, retry limits, memory policy, and portable YAML/JSON/Mermaid artifacts.
markoblogo/abvx-agent-skills/skills/handoff Skill
14★ repoCreate compact handoff documents for another agent, session, or human to continue work. Use when a task is long-running, context is about to compact, work must pause, an audit needs resumable state, or the user asks for a handoff, continuation note, checkpoint, or next-session brief.
markoblogo/abvx-agent-skills/skills/knowledge-base-enrichment Skill
14★ repoEnrich a Markdown knowledge base with durable tags, source provenance, existing-note links, and reviewed wiki synthesis while keeping raw notes read-only by default. Use when organizing Obsidian-style notes, refreshing generated wikis, or preparing source-grounded context for agents.
markoblogo/abvx-agent-skills/skills/lean-context-layout Skill
14★ repoRestructure agent-facing docs so the always-loaded context stays small and the rest is loaded on demand. Use when a repo has bloated AGENTS.md or CLAUDE-style docs, too many always-loaded notes, stale session history, oversized runbooks, or high startup token waste for coding agents.
markoblogo/abvx-agent-skills/skills/loop-readiness-review Skill
14★ repoReview whether a recurring or semi-autonomous agent loop is ready to run. Use before scheduling Codex, Claude Code, Grok, Opencode, CI, issue triage, PR babysitting, dependency sweeping, changelog drafting, or other repeated agent workflows.
markoblogo/abvx-agent-skills/skills/reversible-agent-task Skill
14★ repoRun risky or multi-file agent work as a reviewable proposal before mutating the target workspace. Use when a task should produce retained output, inspectable diffs, and an explicit select/apply/discard decision instead of direct edits.
markoblogo/abvx-agent-skills/skills/shell-output-compaction Skill
14★ repoReduce shell and tool-output token waste by preferring targeted commands, diff-only views, error-first logs, narrow slices, counts, and concise summaries instead of large raw stdout dumps. Use on coding, debugging, audits, CI triage, or repo exploration when command output is likely to dominate token usage.
param087/agent-ml-skills/skills/llm-finetuning Skill
14★ repoUse when fine-tuning a large language model. Covers choosing full vs LoRA/QLoRA, dataset formatting, the transformers/PEFT/TRL stack, key hyperparameters, and evaluating fine-tunes without overfitting.
The same file is in 1 other repository
param087/agent-ml-skills/skills/rag-pipeline Skill
14★ repoUse when building retrieval-augmented generation. Covers chunking strategy, embedding choice, vector stores, hybrid + reranking retrieval, prompt assembly, and evaluating retrieval and answer quality.
The same file is in 1 other repository
pinecone-io/skills/skills/pinecone-docs Skill
14★ repoCurated documentation reference for developers building with Pinecone. Contains links to official docs organized by topic and data format references. Use when writing Pinecone code, looking up API parameters, or needing the correct format for vectors or records.
The same file is in 1 other repository
pinecone-io/skills/skills/pinecone-full-text-search Skill
14★ repoPinecone's official Agent Skills library, for use with agentic IDEs such as Cursor, Github Copilot, Antigravity, Gemini CLI and more.
The same file is in 2 other repositories
pinecone-io/skills/skills/pinecone-help Skill
14★ repoPinecone's official Agent Skills library, for use with agentic IDEs such as Cursor, Github Copilot, Antigravity, Gemini CLI and more.
pinecone-io/skills/skills/pinecone-mcp Skill
14★ repoReference for the Pinecone MCP server tools. Documents all available tools - list-indexes, describe-index, describe-index-stats, create-index-for-model, upsert-records, search-records, cascading-search, and rerank-documents. Use when an agent needs to understand what Pinecone MCP tools are available, how to use them, or what parameters they accept.
The same file is in 3 other repositories
pinecone-io/skills/skills/pinecone-n8n Skill
14★ repoPinecone's official Agent Skills library, for use with agentic IDEs such as Cursor, Github Copilot, Antigravity, Gemini CLI and more.
The same file is in 1 other repository
pinecone-io/skills/skills/pinecone-query Skill
14★ repoPinecone's official Agent Skills library, for use with agentic IDEs such as Cursor, Github Copilot, Antigravity, Gemini CLI and more.
The same file is in 1 other repository
pinecone-io/skills/skills/pinecone-quickstart Skill
14★ repoPinecone's official Agent Skills library, for use with agentic IDEs such as Cursor, Github Copilot, Antigravity, Gemini CLI and more.
The same file is in 1 other repository
isak102/neowright/.agents/skills/setup-matt-pocock-skills Skill
14★ repoSets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
The same file is in 15 other repositories
geoly-ai/geo-skills/geo-hallucination-checker Skill
no license14★ repoDetect and annotate hallucinations, unsupported claims, fabricated studies, and incorrect conclusions in text so that AI only cites verifiable, trustworthy content. Use this skill whenever the user asks you to fact-check, validate sources, check for hallucinations, or ensure that generated content is grounded in real evidence, even if they do not explicitly use the word "hallucination".
geoly-ai/geo-skills/geo-prompt-researcher Skill
no license14★ repoDiscover high-value AI search prompts your target audience uses on ChatGPT, Perplexity, Gemini, and Claude. Research and generate comprehensive prompt lists for GEO (Generative Engine Optimization) strategy, including discovery, comparison, how-to, definition, and recommendation prompts. Use whenever the user mentions researching AI search queries, finding GEO prompts, building prompt monitoring lists, understanding what people ask AI about their brand/category, or wants to identify AI search opportunities for their product/service.
1c2d3e4f 5a6b 7c8d 9e0f 1a2b3c4d5e6f
onurkanbakirci/awesome-skills/public/skills/1c2d3e4f-5a6b-7c8d-9e0f-1a2b3c4d5e6f Skill
no license14★ repoGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
The same file is in 16 other repositories
49c975dc b8af 4332 903f f72d064ee861
onurkanbakirci/awesome-skills/public/skills/49c975dc-b8af-4332-903f-f72d064ee861 Skill
no license14★ repoGuide 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
68507ece 1eec 4a30 8cc0 ad60d1881390
onurkanbakirci/awesome-skills/public/skills/68507ece-1eec-4a30-8cc0-ad60d1881390 Skill
no license14★ repoGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
The same file is in 19 other repositories
A7b8c9d0 e1f2 4a5b 9c8d 7e8f9a0b1c2d
onurkanbakirci/awesome-skills/public/skills/a7b8c9d0-e1f2-4a5b-9c8d-7e8f9a0b1c2d Skill
no license14★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 7 other repositories
B2c3d4e5 f6a7 4b5c 9d8e 2f3a4b5c6d7e
onurkanbakirci/awesome-skills/public/skills/b2c3d4e5-f6a7-4b5c-9d8e-2f3a4b5c6d7e Skill
no license14★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
The same file is in 15 other repositories
onfire7777/universal-ai-skills-library/skill-router-cli/cmd/skills/testdata/route-fixture/skills/universal-ai-config Skill
14★ repoConfigure and audit the local universal AI skills setup across Codex, ChatGPT, Claude, Claude Code, Claude Cowork, Cursor, Gemini, OpenCode, OpenSkills, Hermes Agent, Paperclip agents, OpenClaw, Cline, Continue, GitHub Copilot, Kiro, OpenHands, hosted provider compatibility surfaces, plugin manifests, optional MCP bridges, and global instruction files. Use when the user asks to organize, consolidate, optimize, rename, or repair the cross-AI skill router configuration.
onfire7777/universal-ai-skills-library/skills/agent-introspection-debugging Skill
14★ repoStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
The same file is in 1 other repository
onfire7777/universal-ai-skills-library/skills/agent-mail-automation Skill
14★ repoAutomate Agent Mail tasks via Rube MCP (Composio). Always search tools first for current schemas.
The same file is in 6 other repositories
onfire7777/universal-ai-skills-library/skills/agent-sort Skill
14★ repoBuild an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
The same file is in 1 other repository
onfire7777/universal-ai-skills-library/skills/agentic-actions-auditor Skill
14★ repoAudits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.
onfire7777/universal-ai-skills-library/skills/ai-expertise-engine Skill
14★ repoComprehensive AI/ML expertise covering prompt engineering, LLM architecture, AI agent design, RAG systems, fine-tuning, AI safety, and cutting-edge AI research for building and leveraging AI systems.
onfire7777/universal-ai-skills-library/skills/benchmark-email-automation Skill
14★ repoAutomate Benchmark Email tasks via Rube MCP (Composio). Always search tools first for current schemas.
The same file is in 6 other repositories
onfire7777/universal-ai-skills-library/skills/breach Skill
14★ repoRed team engineering agent. Responsible for attack scenario design, threat modeling, MITRE ATT&CK/OWASP application, Purple Team exercises, and AI/LLM red teaming. Used when security verification is required.
onfire7777/universal-ai-skills-library/skills/browser-automation Skill
14★ repoBrowser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202
onfire7777/universal-ai-skills-library/skills/cavecrew Skill
14★ repoDecision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
The same file is in 7 other repositories
onfire7777/universal-ai-skills-library/skills/caveman-compress Skill
14★ repoCompress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress FILEPATH or "compress memory file"
The same file is in 1 other repository
onfire7777/universal-ai-skills-library/skills/claude-api Skill
14★ repoBuild apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
onfire7777/universal-ai-skills-library/skills/claude-native-algorithmic-art Skill
14★ repoCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Claude native brand guidelines
onfire7777/universal-ai-skills-library/skills/claude-native-brand-guidelines Skill
14★ repoApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
onfire7777/universal-ai-skills-library/skills/claude-native-canvas-design Skill
14★ repoCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
onfire7777/universal-ai-skills-library/skills/claude-native-claude-api Skill
14★ repoBuild, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.
onfire7777/universal-ai-skills-library/skills/claude-native-code-review Skill
14★ repoAdversarial code review — find what will break in production, not what looks wrong in theory. Covers correctness, security, failure modes, performance, and maintainability. Use when reviewing PRs, auditing code quality, or before merging. Triggers on: 'review this code', 'code review', 'check this PR', 'is this code good', 'review before merge', 'look over this code'.
onfire7777/universal-ai-skills-library/skills/claude-native-docx Skill
14★ repoUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
onfire7777/universal-ai-skills-library/skills/claude-native-mcp-builder Skill
14★ repoGuide 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).