Context & AI engineering
25,815 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
Lonsdale201/wp-agent-skills/fluentcrm/fluentcrm-funnel-benchmark Skill
21★ repoBuild a custom FluentCRM funnel benchmark — a goal/wait point inside a sequence that pauses execution until a matching event occurs (tag applied, list joined, course completed, custom event). Extends BaseBenchMark. Covers the three abstract methods (getBlock, getBlockFields, handle), Optional vs Essential semantics, the can_enter direct-entry toggle, the assertCurrentGoalState filter, and FunnelProcessor::startFunnelFromSequencePoint as the canonical resume entry — NOT startFunnelSequence (that starts a new run). Important — same lifecycle rule as triggers (instantiate on fluentcrm_loaded priority below 10); benchmarks share the action listener with triggers via FunnelHandler::mapTriggers, so the init:2 fluentcrm_funnel_arg_num_{name} timing applies. Use when a funnel needs to wait for a contact-state change. Triggers on BaseBenchMark, fluentcrm_funnel_benchmark_start_, assertCurrentGoalState, startFunnelFromSequencePoint, benchmarkTypeField, canEnterField.
Lonsdale201/wp-agent-skills/lw-plugins/lw-site-manager-overview Skill
21★ repoReference for the LW Site Manager plugin (lwplugins/ lw-site-manager) — a WP 6.9+ Abilities-API-native exposure layer that registers 120+ machine-callable abilities under the site-manager/* namespace for AI agents (Claude, ChatGPT, MCP clients) to discover and invoke. Covers updates / plugins / themes / posts / pages / comments / media / users / taxonomies / settings / backups / health / database / cache / WooCommerce. Calling pattern — REST run endpoint is /wp-json/wp-abilities/v1/abilities/{namespace}/{ability}/run with Application Password Basic auth. Important — this is NOT MainWP; the surface and security model are different (per-ability cap-checks via PermissionManager, not a single dashboard token). Header requires PHP 8.2 (not 8.1 as some docs say). Use when calling the plugin's abilities, advising on AI agent integration, or before extending the plugin (see lw-site-manager-extend-abilities). Triggers on site-manager/, lw-site-manager, wp-abilities/v1, AI agent + WP.
Lonsdale201/wp-agent-skills/wp-rocket/wp-rocket-mcp-and-abilities Skill
21★ repoExpose, scope, or secure WP Rocket settings for AI / MCP clients — new in 3.23. Two layers — WP Abilities API abilities (wp-rocket/get-options readonly, wp-rocket/set-option destructive, category wp-rocket-options, cap rocket_manage_options) and a built-in MCP OAuth 2.1 server at /wp-json/mcp/mcp-oauth-server (/oauth/*, /.well-known) with trusted publisher Claude (claude.ai). Critical — abilities default ON (rocket_enable_abilities), the OAuth server defaults OFF (rocket_mcp_oauth_server_enabled), and both need the WP Abilities API + wordpress/mcp-adapter or nothing registers. Scope what AI may read / write via rocket_mcp_options_allowlist (an additive allowlist); add clients via rocket_mcp_trusted_publishers. Filters are typed (wpm_apply_filters_typed) — return exact bool / array. Use when exposing WP Rocket settings to an MCP client, scoping the allowlist, or reviewing AI-facing code. Triggers on rocket_mcp_, rocket_enable_abilities, wp-rocket/get-options, wp-rocket/set-option, "/oauth/" MCP server.
Ai agent tool abuse and privilege escalation
ShulkwiSEC/bb-huge/skills/curated/ai-agent-tool-abuse-and-privilege-escalation Skill
21★ repoTest AI agent systems for tool abuse, unauthorized actions, privilege escalation through tool chaining, and safety bypass via agentic workflows. Use this skill when assessing autonomous AI agents that use tool-calling (function calling, plugins, actions) to interact with external systems. Covers multi-step attack chains, implicit trust exploitation, and capability boundary testing for AI agents.
ShulkwiSEC/bb-huge/skills/curated/ai-jailbreak-prompt-injection Skill
21★ repoExecute sophisticated Prompt Injection and Jailbreak techniques against Large Language Models (LLMs) to bypass safety filters, extract system prompts, and manipulate the AI's output to perform malicious or disallowed actions.
ShulkwiSEC/bb-huge/skills/curated/ai-jailbreak-system-prompts Skill
21★ repoAdvanced techniques for bypassing LLM safety filters, instruction tuning, and system prompt restrictions using specialized linguistic constructs, hypothetical scenarios, and persona adoption.
ShulkwiSEC/bb-huge/skills/curated/ai-pair-hunting-with-claude Skill
21★ repoConfigure Claude as a "Pair Hunter" — autonomous overnight hacking, context management via per-target .claudemd files, sub-agent compaction avoidance, and scope enforcement. Based on Critical Thinking Bug Bounty Podcast Episode 166.
ShulkwiSEC/bb-huge/skills/curated/ai-prompt-leaking Skill
21★ repoSystematically extract hidden system prompts, core directives, and invisible context intentionally concealed within Large Language Model (LLM) applications. This skill utilizes targeted linguistic engineering and boundary manipulation to bypass prompt opacity.
ShulkwiSEC/bb-huge/skills/curated/claude-skills-for-bug-bounty Skill
21★ repoBuild production-grade Claude Code CLI skills with fallback architecture, TypeScript implementation, and creativity directives. Based on Critical Thinking Bug Bounty Podcast Episode 166 — "Building Claude Skills as a Bug Bounty Hunter."
ShulkwiSEC/bb-huge/skills/curated/hackerone-brain-mcp Skill
21★ repoUse the H1 Brain MCP Server to pull HackerOne program policies, scope definitions, and disclosed vulnerability reports directly into Claude's context. Based on Critical Thinking Bug Bounty Podcast Episode 166.
ShulkwiSEC/bb-huge/skills/curated/indirect-prompt-injection Skill
21★ repoExecute Indirect Prompt Injection attacks against Large Language Models (LLMs) by subtly embedding malicious instructions within external data sources (e.g., websites, documents, databases) that the LLM autonomously ingests. This forces the model to execute attacker-controlled commands under the guise of processing legitimate user requests.
ShulkwiSEC/bb-huge/skills/curated/llm-attacks Skill
21★ repoComplete PortSwigger deep-dive with exact payloads for every lab variant including zero-day techniques
ShulkwiSEC/bb-huge/skills/curated/llm-direct-prompt-injection Skill
21★ repoTest Large Language Models for direct prompt injection vulnerabilities where user input overrides system instructions, extracts system prompts, bypasses safety filters, or causes unauthorized actions. Use this skill when assessing chatbots, AI assistants, LLM-powered tools, or any application that processes natural language input through an LLM. Covers role-playing attacks, instruction hierarchy exploitation, multi-turn manipulation, and context window abuse for comprehensive AI security testing.
ShulkwiSEC/bb-huge/skills/curated/llm-jailbreaking-personas Skill
21★ repoExecute advanced LLM Jailbreaking techniques using roleplay, nested environments (virtual machines), and complex personas to completely bypass safety constraints and ethical alignments embedded in AI models.
ShulkwiSEC/bb-huge/skills/curated/llm-jailbreaking-techniques Skill
21★ repoSystematically bypass LLM safety filters and content moderation systems using advanced jailbreaking techniques. Use this skill when testing AI systems for safety alignment robustness, evaluating content moderation effectiveness, or conducting authorized AI red team assessments. Covers role-play attacks, few-shot manipulation, encoding bypass, multi-modal exploitation, and automated jailbreak discovery methods.
Llm overreliance hallucination
ShulkwiSEC/bb-huge/skills/curated/llm-overreliance-hallucination Skill
21★ repoExploit an application's absolute trust in its underlying LLM (Overreliance). Use this skill to induce critical "hallucinations" (confident falsehoods) that cause downstream logical systems or automated agents tracking the LLM's output to make destructive actions or grant unauthorized access.
ShulkwiSEC/bb-huge/skills/curated/llm-prompt-injection Skill
21★ repoLLM prompt injection playbook. Use when testing AI/LLM applications for direct injection, indirect injection via RAG/browsing, tool abuse, data exfiltration, MCP security risks, and defense bypass techniques.
ShulkwiSEC/bb-huge/skills/curated/llm-supply-chain-poisoning Skill
21★ repoIdentify and exploit vulnerabilities in the AI Supply Chain by injecting malicious models, datasets, or dependencies. Use this skill to simulate advanced persistent threats (APTs) compromising Hugging Face repositories, manipulating pre-trained weights (Model Poisoning), and exploiting insecure deserialization during model loading (e.g., Pickle files).
ShulkwiSEC/bb-huge/skills/curated/llm-testing Skill
21★ repoComprehensive LLM security testing prompts for bias detection, data leakage, alignment testing, and adversarial prompt resistance.
The same file is in 1 other repository
ShulkwiSEC/bb-huge/skills/curated/llm-training-data-extraction Skill
21★ repoExtract sensitive training data (PII, API keys, intellectual property, or code) directly from a deployed Large Language Model (LLM). This AI Red Teaming skill focuses on forcing models to regurgitate memorized, unredacted data from their massive internet-scraped datasets through repetition attacks, prefix continuation, and context window manipulation.
ShulkwiSEC/bb-huge/skills/curated/mcp-protocol-exploitation Skill
21★ repoTest Model Context Protocol (MCP) servers and tool-calling systems for security vulnerabilities including tool injection, parameter manipulation, privilege escalation, and data exfiltration through AI agent tool interfaces. Use this skill when assessing MCP server implementations, AI agent tool integrations, or any system that exposes tools to language models. Covers tool confusion attacks, cross-tool exploitation, and MCP server hardening assessment.
ShulkwiSEC/bb-huge/skills/curated/memory-forensics-volatility Skill
21★ repoMemory forensics playbook using Volatility 2/3. Use when analyzing memory dumps for malware analysis, credential extraction, process investigation, code injection detection, and incident response timeline reconstruction.
ShulkwiSEC/bb-huge/skills/curated/prompt-leaking-system-prompts Skill
21★ repoExtract the hidden foundational System Prompts, internal instructions, backend APIs, and confidential contextual data powering Large Language Model (LLM) applications using targeted prompt injection manipulation and adversarial psychological engineering.
ShulkwiSEC/bb-huge/skills/curated/volatility-memory-forensics Skill
21★ repoAnalyze full RAM captures (memory dumps) to extract forensic artifacts, detect stealthy malware, recover injected shellcode, and identify rootkits that bypass traditional disk-based antivirus scanning. Use this skill during Incident Response and advanced threat hunting engagements to identify what was actively running on a compromised system at a specific point in time.
ShulkwiSEC/bb-huge/skills/curated/web-exploit Skill
21★ repoDeep web exploitation beyond initial scanning. Covers SQLi (blind, OOB, second-order), NoSQL injection (MongoDB, operator bypass), GraphQL injection (introspection, batching, mutation abuse), XSS (reflected/stored/DOM with full source-sink analysis), SSTI (Jinja2/Twig/Freemarker/ERB engine identification and RCE), SSRF chains, file upload bypass (polyglot creation), XXE (blind, DOCX/SVG injection, Content-Type switching), deserialization (Java/PHP/Python/.NET), command injection, path traversal (LFI wrapper bypasses), race conditions, CSRF, JWT attacks (none/key confusion/kid injection), HTTP request smuggling (CL.TE/TE.CL/H2), CRLF injection, open redirect bypass chains, CORS exploitation, web cache deception/poisoning, OAuth misconfiguration, prototype pollution, session management, and business logic flaws. Uses sqlmap (advanced modes), commix, xsser, wapiti, davtest, and manual http(action="request", ...) payloads. Every technique includes actual payloads, commands, and code snippets for immediate use. Chains from /pentester or /api-security when injection points are discovered, chains into /post-exploit when RCE is achieved, and chains into /ai-redteam when an LLM/AI endpoint is discovered (chat APIs, RAG search, agentic tool-use, MCP servers).
smixs/disruptor-skills/skills/qa-demo-stand Skill
21★ repoPrompt template that builds a local demo test stand and QA-tests a converged project to production quality.
smixs/disruptor-skills/skills/setup-server Skill
21★ repoA prompt template for safely provisioning a production Ubuntu/Debian web server (Docker Compose, reverse proxy, TLS, firewall, SSH hardening) without lockouts or data loss.
smixs/disruptor-skills/skills/write-spec Skill
21★ repoA prompt template that turns a settled 7w3 design into a canonical, build-ready implementation specification covering data, API, security, testing, and deployment.
cobusgreyling/agent-skills/skills/agent-evaluation-harness Skill
no license21★ repoDesign an evaluation harness for an LLM agent before shipping it. Use when the user is building or rewriting an agent, deciding ship/no-ship, debugging regressions, or mentions golden sets, eval suites, regression tests, trace-level evals, LLM-as-judge, scoring rubrics, or asks "how do I test this agent?" / "how do I know if my agent got better?".
cobusgreyling/agent-skills/skills/agent-observability Skill
no license21★ repoInstrument an LLM agent so failures are diagnosable, traces are replayable, and evals can run against production data. Use when the user is moving an agent past prototype and mentions tracing, spans, OpenTelemetry, LangSmith, Langfuse, Arize, OpenLLMetry, structured logs, GenAI semantic conventions, or asks "how do I debug this agent in production?" / "what should I log?".
cobusgreyling/agent-skills/skills/context-window-hygiene Skill
no license21★ repoManage what enters and stays in the context window — pruning, compaction, summary fidelity, ordering — so the agent stays coherent on long runs without inflating cost. Use when the user is hitting context limits, running long agentic loops, paying for full-history replays, or asks "how do I keep context manageable?" / "the agent forgets things after N turns".
cobusgreyling/agent-skills/skills/guardrails-and-safety Skill
no license21★ repoDesign guardrails for an LLM agent that handles user input, calls real tools, or operates in a regulated domain. Use when the user is building a user-facing agent and mentions guardrails, jailbreaks, prompt injection, content moderation, PII redaction, output validation, red-teaming, safety filters, or asks "how do I keep this agent from doing X?" / "how do I make this production-safe?".
cobusgreyling/agent-skills/skills/human-in-the-loop Skill
no license21★ repoDesign where, when, and how a human gates, reviews, or rescues an LLM agent — without turning the agent into a button labelled "approve". Use when the user is building an agent that takes irreversible actions or operates in regulated workflows and mentions human-in-the-loop, HITL, approval gate, escalation, review queue, oversight, or asks "when should a human approve this?" / "how do I add review without killing the agent's speed?".
cobusgreyling/agent-skills/skills/latency-budgeting Skill
no license21★ repoBudget and engineer latency for an LLM agent — TTFT, tokens-per-second, tool round-trips, parallelism, streaming. Use when the user is building a user-facing or real-time agent and mentions latency, p50, p95, p99, TTFT, streaming, throughput, time-to-first-token, slow agent, or asks "why is my agent slow?" / "how do I hit a 2-second latency target?".
cobusgreyling/agent-skills/skills/llm-as-judge Skill
no license21★ repoDesign and validate LLM-as-judge scoring — pairwise vs pointwise, bias correction, anchor calibration, and the cases where a judge is the wrong tool. Use when the user is building an eval, scoring open-ended outputs, or comparing model versions and mentions LLM-as-judge, model grader, pairwise comparison, position bias, length bias, judge calibration, meta-eval, or asks "how do I score open-ended responses?" / "is my LLM-judge biased?".
cobusgreyling/agent-skills/skills/memory-design Skill
no license21★ repoDesign memory for an LLM agent — what to keep, where to keep it, and when memory hurts more than it helps. Use when the user is adding memory to an agent and mentions short-term memory, long-term memory, episodic, semantic, conversation history, summary memory, vector memory, memory store, mem0, Letta, MemGPT, or asks "should this agent remember?" / "why is the agent recalling the wrong thing?".
cobusgreyling/agent-skills/skills/multi-agent-orchestration Skill
no license21★ repoDecide when to split work across multiple agents vs one agent with tools, and design the handoffs when you do. Use when the user is sketching a multi-agent system or debugging one, and mentions handoff, delegation, supervisor, swarm, crew, sub-agent, agent-to-agent, A2A, manager-worker, team of agents, or asks "should I split this into multiple agents?" / "why do my agents talk forever and never finish?".
cobusgreyling/agent-skills/skills/prompt-caching Skill
no license21★ repoUse prompt caching correctly across Anthropic, OpenAI, Bedrock, and Gemini to cut cost and latency on hot paths. Use when the user is building a production LLM app and mentions prompt caching, cache hits, cache key, cache TTL, ephemeral cache, system-prompt caching, or asks "why is my cache hit rate low?" / "should I cache this?".
cobusgreyling/agent-skills/skills/prompt-injection-defense Skill
no license21★ repoDefend an LLM agent against prompt injection — direct, indirect, tool-result, and document-borne. Use when the user is building an agent that reads untrusted content (web pages, emails, documents, tool outputs) or exposes user-provided text to a downstream agent, and mentions prompt injection, indirect injection, jailbreak via document, tool-result injection, untrusted input, instruction override, or asks "how do I stop the agent from following injected instructions?" / "is RAG safe from injection?".
cobusgreyling/agent-skills/skills/rag-vs-context-engineering Skill
no license21★ repoDecide between RAG, long-context, structured tool retrieval, and prompt-only approaches for grounding an LLM in private or fresh data. Use when the user is designing a knowledge-grounded agent or chatbot and mentions RAG, vector search, embeddings, retrieval, chunking, long context, context window, tool retrieval, hybrid search, rerank, or asks "do I need RAG?" / "should I just use a big context window?".
cobusgreyling/agent-skills/skills/tool-use-schema-design Skill
no license21★ repoDesign tool schemas (function-calling definitions) that LLMs can use reliably. Use when the user is defining tools for Claude, GPT, Gemini, or any function-calling agent and mentions tool definitions, function calling, JSON schema, tool descriptions, parameters, structured outputs, MCP tools, or asks "why is the model calling my tool wrong?" / "how should I design this tool?".
Clientell-Ai/salesforce-skills/skills/sf-eval Skill
21★ repoEvaluate and benchmark Salesforce skill quality. Compares AI-generated code with vs without skill context, scores against a Salesforce-specific rubric (security, governor limits, bulkification, patterns, completeness), and produces a comparison report. Use to run benchmarks, verify skill value, or check Apex code quality. Activate on mentions of "evaluate skills", "benchmark", "skill quality", "run eval", or "compare with/without skills".
The same file is in 2 other repositories
agents-inc/skills/dist/plugins/ai-orchestration-langchain/skills/ai-orchestration-langchain Skill
20★ repoLangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing
agents-inc/skills/dist/plugins/ai-orchestration-llamaindex/skills/ai-orchestration-llamaindex Skill
20★ repoLlamaIndex.TS data framework for RAG, indexing, retrieval, query engines, chat engines, and agentic workflows in TypeScript
Ai orchestration vercel ai sdk
agents-inc/skills/dist/plugins/ai-orchestration-vercel-ai-sdk/skills/ai-orchestration-vercel-ai-sdk Skill
20★ repoVercel AI SDK patterns - providers, text generation, streaming, structured output, tool calling, chat UI hooks, embeddings, and RAG
agents-inc/skills/dist/plugins/ai-patterns-tool-use-patterns/skills/ai-patterns-tool-use-patterns Skill
20★ repoProvider-agnostic patterns for LLM function calling, tool loops, and agentic workflows
agents-inc/skills/dist/plugins/ai-provider-claude-vision/skills/ai-provider-claude-vision Skill
20★ repoImage understanding and document analysis with Claude's multimodal capabilities -- image input formats, PDF processing, multi-image patterns, structured extraction, and token cost estimation
agents-inc/skills/dist/plugins/api-vector-db-chroma/skills/api-vector-db-chroma Skill
20★ repoChroma vector database -- collection management, automatic embedding, metadata filtering, document storage, query patterns
agents-inc/skills/dist/plugins/api-vector-db-pinecone/skills/api-vector-db-pinecone Skill
20★ repoPinecone serverless vector database -- index management, vector operations, metadata filtering, namespaces, hybrid search, inference API
agents-inc/skills/dist/plugins/api-vector-db-qdrant/skills/api-vector-db-qdrant Skill
20★ repoQdrant vector database -- collection management, point operations, payload filtering, named vectors, quantization, recommendations, snapshots
agents-inc/skills/dist/plugins/api-vector-db-weaviate/skills/api-vector-db-weaviate Skill
20★ repoWeaviate vector database patterns with weaviate-client v3 -- collection management, vectorizer modules, hybrid search, filtering, generative search (RAG), multi-tenancy, batch imports
agents-inc/skills/dist/plugins/web-forms-react-hook-form/skills/web-forms-react-hook-form Skill
20★ repoReact Hook Form patterns - useForm, Controller, useFieldArray, validation resolver, performance optimization
agents-inc/skills/src/skills/api-vector-db-chroma Skill
20★ repoChroma vector database -- collection management, automatic embedding, metadata filtering, document storage, query patterns
agents-inc/skills/src/skills/api-vector-db-pinecone Skill
20★ repoPinecone serverless vector database -- index management, vector operations, metadata filtering, namespaces, hybrid search, inference API
agents-inc/skills/src/skills/api-vector-db-qdrant Skill
20★ repoQdrant vector database -- collection management, point operations, payload filtering, named vectors, quantization, recommendations, snapshots
agents-inc/skills/src/skills/api-vector-db-weaviate Skill
20★ repoWeaviate vector database patterns with weaviate-client v3 -- collection management, vectorizer modules, hybrid search, filtering, generative search (RAG), multi-tenancy, batch imports
agents-inc/skills/src/skills/web-forms-react-hook-form Skill
20★ repoReact Hook Form patterns - useForm, Controller, useFieldArray, validation resolver, performance optimization
sergebulaev/facebook-skills/.codex-marketplace/facebook-skills/skills/fb-hook-extractor Skill
20★ repoReverse-engineer the hook from a high-share Facebook Page post, from its URL or pasted text. Identifies which of the 10 canonical 2026 Facebook formulas it uses (one-line opinion, tiny number, ask-the-page question, this-or-that, behind-the-scenes, story post, announcement, spotlight), explains why it earned shares or comments, and returns a blank template mapped to your topic. Use to learn from a Page post you admire. Not for writing your own (use fb-post-writer).
sergebulaev/facebook-skills/skills/fb-hook-extractor Skill
20★ repoReverse-engineer the hook from a high-share Facebook Page post, from its URL or pasted text. Identifies which of the 10 canonical 2026 Facebook formulas it uses (one-line opinion, tiny number, ask-the-page question, this-or-that, behind-the-scenes, story post, announcement, spotlight), explains why it earned shares or comments, and returns a blank template mapped to your topic. Use to learn from a Page post you admire. Not for writing your own (use fb-post-writer).
kennethkhoocy/applied-micro-skills/plugins/applied-micro/skills/lit-review-orchestrator Skill
20★ repoMaster controller for the lit-review pipeline, driven by a document. Give it a .tex or .docx file describing an article — a full manuscript, an abstract, or a proposal — and it extracts a search plan, runs Undermind (an automated Playwright driver in Classic mode) and Google Scholar (SearchAPI.io), then merges, deduplicates, and screens the results. Only use this skill when explicitly requested — e.g., the user says "run lit-review-orchestrator", "lit-review-orchestrator", or "/lit-review-orchestrator". Do NOT auto-trigger on general literature review requests.
The same file is in 1 other repository