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
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/ai-taking-actions Skill
no license12★ repoBuild AI that takes actions, calls APIs, and does things autonomously. Use when you need AI to call APIs, use tools, perform calculations, search the web and act on results, interact with databases, or do multi-step tasks. Also AI that does things not just talks, tool-using AI agent, AI calls external APIs, function calling with DSPy, build AI that books appointments, AI workflow automation, agent that searches and acts on results, AI that updates databases, autonomous AI agent, AI performs multi-step tasks, give LLM access to tools, agentic AI workflow, AI agent for DevOps, build AI assistant that takes actions, MCP tool integration with AI, AI that can browse and click, LLM with tool access.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-adapters Skill
no license12★ repoUse when you need to customize how DSPy formats prompts for a specific provider — switching from chat to completion format, forcing JSON output, or debugging prompt rendering issues. Common scenarios - debugging why your prompt looks wrong when sent to the model, switching from OpenAI to Anthropic and the formatting breaks, forcing the model to return valid JSON instead of markdown, working with completion-style models that do not support chat format, customizing system messages, or handling models that choke on structured output instructions. Related - ai-switching-models, ai-following-rules, ai-parsing-data. Also used for prompt template rendering, how DSPy builds the prompt, custom system message in DSPy, JSON mode not working, model ignores format instructions, switch from chat to completion API, dspy.ChatAdapter, dspy.JSONAdapter, prompt formatting issues, debug what DSPy sends to the model, dspy.XMLAdapter, XML output format.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-better-together Skill
no license12★ repoJointly optimize prompts and model weights using dspy.BetterTogether for maximum accuracy. Use when you have already tried prompt-only optimization and want the next level — jointly tuning prompts and model weights for maximum quality. Common scenarios - you have maxed out prompt optimization and need the next level, combining instruction tuning with weight tuning for maximum quality, making a small model match a large model through joint optimization, or squeezing the last few percent of accuracy. Related - ai-fine-tuning, ai-improving-accuracy, ai-cutting-costs. Also used for dspy.BetterTogether, joint prompt and weight optimization, beyond prompt engineering, combine fine-tuning with prompt optimization, maximum possible quality from DSPy, hybrid optimization strategy, prompt optimization hit a ceiling, fine-tune and optimize prompts at the same time, advanced DSPy optimization, best possible accuracy, what to try after MIPROv2, next level AI quality.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-bootstrap-few-shot Skill
no license12★ repoAutomatically generate and select few-shot demonstrations for a DSPy program from labeled data using dspy.BootstrapFewShot - the simplest and fastest optimizer. Use when you have 50+ labeled examples and want a quick accuracy boost as your first optimization step. Common scenarios - your first optimization attempt on a new DSPy program, adding few-shot examples automatically from labeled data, quick accuracy boost before trying heavier optimizers, bootstrapping demonstrations from a teacher model, or getting started with DSPy optimization. Related - ai-improving-accuracy, dspy-labeled-few-shot. Also used for dspy.BootstrapFewShot, simplest DSPy optimizer, first optimizer to try, automatic few-shot example selection, bootstrap demonstrations from labels, quick optimization baseline, add examples to prompt automatically, teacher bootstrapping, labeled data to few-shot demos, starting point for DSPy optimization, easy accuracy improvement, how to optimize DSPy program for the first time.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-chain-of-thought Skill
no license12★ repoUse when the task benefits from intermediate reasoning before producing an answer — multi-step logic, analysis, math, or complex classification where direct prediction fails. Common scenarios - classification tasks where the model needs to reason about edge cases, math word problems, multi-step analysis, complex question answering, legal or medical reasoning, any task where thinking before answering improves quality. Related - ai-reasoning, dspy-predict, dspy-multi-chain-comparison. Also used for dspy.ChainOfThought, CoT prompting in DSPy, think step by step, show your reasoning, intermediate reasoning steps, LLM gives wrong answer without thinking, reasoning before output, make AI explain its logic, step-by-step problem solving, when to use ChainOfThought vs Predict, add reasoning to any DSPy module, let the model think, chain of thought for classification.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-chatadapter Skill
no license12★ repoDeep dive into dspy.ChatAdapter -- the default adapter that formats DSPy signatures into multi-turn chat messages with field delimiters, parses LM responses back into typed Python objects, and falls back to JSONAdapter on failure. Use when you need to understand how DSPy builds prompts, debug why a model ignores output format, customize prompt rendering, enable native function calling, use callbacks, generate fine-tuning data, or control the JSON fallback. Also used for how DSPy formats prompts, field delimiters, prompt template rendering, parse error debugging, ChatAdapter vs JSONAdapter vs TwoStepAdapter, format_finetune_data, dspy prompt inspection, why model output is wrong format, adapter callbacks, native function calling in DSPy.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-codeact Skill
no license12★ repoBuild agents that write and execute Python code using dspy.CodeAct. Use when the task requires computation, data transformation, or multi-step logic better expressed as code than tool calls or natural language - data analysis, precise calculations, file processing. Common scenarios - data analysis tasks where the agent writes pandas code, computation-heavy tasks where natural language reasoning fails, file processing automation, tasks requiring precise calculations, or building agents that manipulate data programmatically. Related - ai-taking-actions, dspy-react, dspy-program-of-thought. Also used for dspy.CodeAct, agent writes and runs Python code, code execution agent, data analysis agent, AI agent that writes code, computation with LLM agent, pandas automation with AI, agent that processes files, code-generating agent, execute Python in sandbox, when ReAct is not precise enough use code, programmatic problem solving agent.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-copro Skill
no license12★ repoUse when you want to optimize instructions by generating many candidates and picking the best — useful when few-shot demos alone are not enough and you want to tune the task description itself. Common scenarios - your current task instructions produce mediocre results, you want to automatically generate and test many instruction variants, the task is hard to describe in one sentence, or few-shot examples alone are not improving quality enough. Related - ai-improving-accuracy, dspy-gepa, dspy-miprov2. Also used for dspy.COPRO, instruction optimization, optimize task description, generate better prompts automatically, prompt engineering automation, find the best instruction for my task, automatic prompt generation, instruction tuning without fine-tuning, COPRO vs MIPROv2, when to optimize instructions vs demos, instruction search, prompt optimization by generating candidates, systematic prompt improvement.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-gepa Skill
no license12★ repoOptimize instructions in DSPy programs via reflective evolution using dspy.GEPA without adding few-shot examples. Use when you want to optimize instructions without few-shot examples — a lightweight alternative when you do not have or do not want to use demonstrations. Common scenarios - optimizing instructions when you do not have or do not want to use few-shot demonstrations, lightweight instruction search as a first step, tasks where examples in the prompt confuse the model, or when you want fast instruction optimization. Related - ai-improving-accuracy, dspy-copro, dspy-miprov2. Also used for dspy.GEPA, instruction optimization without demos, lightweight prompt optimization, optimize instructions only, no few-shot examples needed, GEPA vs COPRO, GEPA vs MIPROv2, quick instruction search, when demonstrations hurt performance, zero-shot optimization, instruction-only optimizer, simplest instruction tuner, fast prompt optimization, skip few-shot and just tune instructions, optimize Pydantic field descriptions, GEPA structured output, GEPA does not optimize field desc.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-knn-few-shot Skill
no license12★ repoSelect the most relevant few-shot demonstrations for each input at runtime using dspy.KNNFewShot and dspy.KNN — embedding-based retrieval that adapts demos per query. Use when you want few-shot demos dynamically selected per input based on similarity, inputs vary widely and fixed examples do not cover enough cases, dynamically selecting the most relevant demos per input, building a retrieval-augmented prompt with similar examples, or when static few-shot examples work for some inputs but fail on others. Related - ai-improving-accuracy, dspy-labeled-few-shot, dspy-bootstrap-few-shot, dspy-retrieval. Also used for dynamic few-shot selection, similar examples per input, retrieval-augmented few-shot, adaptive demonstrations, nearest neighbor example selection, dynamic prompt construction, different examples for different inputs, embedding-based demo retrieval, when fixed examples do not generalize, per-input demo selection, contextual few-shot examples, smart example selection.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-labeled-few-shot Skill
no license12★ repoAttach hand-curated labeled examples as few-shot demonstrations using dspy.LabeledFewShot — no bootstrapping, no metric, no LM calls at compile time. Use when you have hand-picked high-quality examples and want to inject them directly as prompt demos without bootstrapping. Common scenarios - expert-curated examples you trust more than bootstrapped ones, hand-picked demonstrations for high-stakes tasks, using existing labeled data directly without bootstrapping, or full control over which examples appear in the prompt. Related - dspy-bootstrap-few-shot, dspy-knn-few-shot, ai-generating-data. Also used for dspy.LabeledFewShot, hand-picked examples in prompt, curated demonstrations, use my own examples directly, manual few-shot setup, expert-labeled demonstrations, no bootstrapping just my examples, static few-shot with labeled data, gold standard examples, controlled few-shot demos, fixed example set in prompt.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-mcp Skill
no license12★ repoUse when you need to connect DSPy agents to external MCP tool servers — databases, file systems, APIs, or any MCP-compatible service. Common scenarios - wiring MCP tools into a ReAct or CodeAct agent, discovering tools from an MCP server at runtime, converting MCP tools to DSPy tools, or building agents that use tools hosted on remote servers. Related - dspy-tools, dspy-react, dspy-codeact, ai-taking-actions. Also used for dspy.Tool.from_mcp_tool, MCP with DSPy, connect DSPy to MCP server, use MCP tools in DSPy agent, model context protocol DSPy, DSPy agent with external tools via MCP, MCP tool integration, StdioServerParameters, ClientSession, stdio_client, mcp tool discovery, async MCP connection, acall with MCP tools.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-miprov2 Skill
no license12★ repodspy.MIPROv2 jointly optimizes instructions and few-shot demos using Bayesian search - DSPy most powerful prompt optimizer. Use when you want the best possible accuracy from prompt optimization, jointly tuning instructions and few-shot demonstrations, using auto=light/medium/heavy presets for different compute budgets, or when COPRO or BootstrapFewShot alone are not reaching your accuracy target. Also used for best DSPy optimizer, highest quality optimization, auto=light medium heavy, joint instruction and demo optimization, most powerful prompt optimizer, MIPROv2 vs COPRO vs BootstrapFewShot, which optimizer should I use, state of the art prompt optimization, when to use MIPROv2, optimize both instructions and examples, heavy optimization for production, best optimizer for accuracy, ai-improving-accuracy.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-qdrant Skill
no license12★ repoUse Qdrant as a vector database with DSPy, or connect any vector DB (Pinecone, ChromaDB, Weaviate) with custom retrievers. Use when you want to set up Qdrant, QdrantRM, dspy-qdrant, vector database for DSPy, vector search, hybrid search, or build custom retrievers for Pinecone, ChromaDB, or Weaviate. Also used for qdrant, dspy-qdrant, QdrantRM, vector database, vector search, pinecone DSPy, chromadb DSPy, weaviate DSPy, vector DB for DSPy, pip install dspy-qdrant, qdrant docker, qdrant cloud, hybrid search DSPy, sparse dense vectors, custom dspy.Retrieve, which vector DB for DSPy, DSPy 3.0 retriever removed.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-react Skill
no license12★ repoBuild tool-using agents with dspy.ReAct - the Reasoning-Action-Observation loop for interleaved thinking and action. Use when the task requires calling external tools or APIs to gather information - multi-step tool use with reasoning, like searching databases, calling APIs, or combining multiple data sources. Common scenarios - building agents that search the web and synthesize results, multi-step information gathering from APIs, chatbots that look up data before answering, question answering that requires external knowledge, or any task needing interleaved reasoning and action. Related - ai-taking-actions, ai-searching-docs, dspy-codeact, dspy-tools, dspy-mcp. Also used for dspy.ReAct, ReAct agent pattern, reasoning and acting loop, tool-using agent in DSPy, search then answer pattern, agent with tools, multi-step tool use, interleave thinking and acting, API-calling agent, agent that reasons about tool outputs, when to use ReAct vs CodeAct, build intelligent agent with DSPy.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-retrieval Skill
no license12★ repoDSPy retrieval modules (dspy.Retrieve, dspy.ColBERTv2, dspy.Embedder, dspy.retrievers.Embeddings) for searching documents, computing embeddings, and building RAG pipelines. Use when you need to search over documents, build a RAG pipeline, connect DSPy to a vector database, compute embeddings for semantic search, set up ChromaDB or Pinecone with DSPy, or build knowledge-grounded question answering. Also used for RAG pipeline in DSPy, vector database integration, semantic search, embedding retrieval, retrieval augmented generation setup, connect knowledge base to DSPy, search documents then answer, grounded generation with retrieval.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-rlm Skill
no license12★ repoRecursive Language Model (dspy.RLM) that explores large contexts via a sandboxed Python REPL -- the LM writes code, queries sub-LMs, and iterates until it produces a final answer. Use when your input is too large for the context window, the model needs to explore data iteratively, you need recursive self-refinement with code execution, or you have research-style tasks requiring programmatic investigation. Also used for recursive language model, iterative exploration with LLM, model explores data in REPL, agent that keeps digging until it finds the answer, REPL-based reasoning, explore then answer pattern, deep research agent, when one pass is not enough.
lebsral/DSPy-Programming-not-prompting-LMs-skills/skills/dspy-tools Skill
no license12★ repoWraps Python functions as dspy.Tool objects and configures dspy.PythonInterpreter for sandboxed code execution in DSPy agents. Use when you need to give DSPy agents tool-calling abilities — wrapping Python functions as tools, building tool-using pipelines, or setting up code execution environments. Common scenarios - wrapping a Python function as a tool for DSPy agents, building tool-using pipelines, setting up a calculator or search tool, giving agents access to databases or APIs, or configuring code execution environments for agents. Related - ai-taking-actions, dspy-react, dspy-codeact. Also used for dspy.Tool, dspy.PythonInterpreter, wrap function as DSPy tool, give agent tools, tool calling in DSPy, function calling for agents, build custom tools for DSPy agent, calculator tool for LLM, search tool for agent, database tool for AI, Python function to agent tool, MCP tools with DSPy, tool registry, how to define tools in DSPy, agent tool configuration, executable tools for AI agents.
iuliandita/skills/skills/command-prompt Skill
12★ repo· Write/debug shell commands, scripts, dotfiles, completions for zsh, bash, POSIX sh, fish. Triggers: 'shell', 'script', '.zshrc', '.bashrc', 'alias', 'completion', 'trap'. Not for CI blocks (use ci-cd).
iuliandita/skills/skills/handoff Skill
12★ repo· Compress the current session into a handoff doc another agent continues from. Triggers: 'handoff', 'hand off', 'context handoff', 'fresh session', 'AFK run'. Not for idea capture (use roadmap) or full dev workflow (use dev-cycle).
iuliandita/skills/skills/mcp Skill
12★ repo· Build/review MCP servers, tools, resources, prompts, transports, OAuth, elicitation. Triggers: 'mcp', 'model context protocol', 'mcp server', 'tool handler', 'fastmcp', '@modelcontextprotocol/sdk'. Not for HTTP APIs (use backend-api).
iuliandita/skills/skills/prompt-generator Skill
12★ repo· Turn notes into structured LLM prompts or improve existing prompts. Triggers: 'write a prompt', 'system prompt', 'prompt template', 'evaluator prompt', 'delegation prompt', 'rewrite this prompt'. Not for skills or routines.
iuliandita/skills/skills/skill-creator Skill
12★ repo· Create/review skills: frontmatter, triggers, overlaps, collection consistency, retrospective updates. Triggers: 'skill creator', 'new skill', 'skill audit', 'skill review', 'update skill library'.
JustMichael-80/MasterVault/skills/anthropic/skills/skill-creator Skill
12★ 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
JustMichael-80/MasterVault/skills/context7/skills/context7-mcp Skill
12★ repoThis skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
JustMichael-80/MasterVault/skills/superpowers/skills/dispatching-parallel-agents Skill
12★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
The same file is in 5 other repositories
JustMichael-80/MasterVault/skills/superpowers/skills/subagent-driven-development Skill
12★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 6 other repositories
dolphindb/DolphinX_Skill/dolphindb-factor/dolphindb-rag Skill
no license12★ repoMUST use before answering any DolphinDB question — enforces source-grounded answers (no fabrication from memory) when no retrieval tool is available. Code execution happens on the DolphinDB.
alonbaron/claude-skills/skills/prompt-generator Skill
12★ repoTurns a vague ask into a rigorous, grounded, token-efficient prompt: role + objective, testable done criteria, anti-hallucination (verify or say "I don't know"), anti-tokenmaxing (lead with the answer, output budget), strict agent discipline. Use proactively when the user hands over a prompt or task spec destined for another agent or LLM. Also on "write a prompt", "improve this prompt", "prompt for an agent". Not for human-facing prose or work you'll execute yourself this session.
alonbaron/claude-skills/skills/review-swarm Skill
12★ repoLocal, free, multi-specialist review of a diff: parallel Claude subagents (correctness, security/trust boundaries, data/perf, architecture-altitude, ponytail-simplicity, tests/failure paths), adversarial verification, dedup, ranked file:line report. Use proactively when asked to review, check, or assess a diff, branch, or PR — and after any non-trivial implementation, before the PR. Also on "review-swarm", "swarm review", "deep review". Not for trivial diffs, not when asked to fix rather than review, not when security alone is the whole ask (built-in "security-review"), and not when "/code-review" is named explicitly.
serejaris/kimi-skills/skills/backend-building-swarm Skill
12★ repoSwarm-aware backend building that grafts tRPC + Drizzle ORM + Hono onto an existing webapp-building-swarm frontend. Grafts in place on a worktree of the shared repo (created via swarm-workspace) and commits on a backend branch the main agent merges. Supports incremental features (db, auth) and fullstack-template provisioning (--template). Use when the user needs a backend, API, database, server, or authentication in a swarm setup. Requires webapp-building-swarm first.
serejaris/kimi-skills/skills/batch-download Skill
12★ repoMulti-agent batch download and data collection orchestration. Use this skill whenever the task requires discovering, validating, and downloading multiple files or datasets from the web — batch report downloads, multi-source data collection, structured web scraping, file archival, or any task demanding parallel discovery and retrieval with verification. This skill enforces plan-first decomposition, parallel sub-agent delegation, evidence-based URL discovery, strict output validation, and structured result integration. Do NOT use for: single file download, simple API calls, tasks that don't involve web discovery or file retrieval.
serejaris/kimi-skills/skills/deep-research-swarm Skill
12★ repoПолная коллекция скиллов Kimi (267 built-in + 7 plugin skills), выгруженная из сандбокса агента
serejaris/kimi-skills/skills/gitlab-cli-guide/glab-mcp Skill
12★ repo使用 MCP(Model Context Protocol,模型上下文协议)服务器进行 AI 助手集成。将 GitLab 功能作为工具暴露给 AI 助手(如 Claude Code),用于与项目、issue、合并请求和流水线交互。适用于将 AI 助手与 GitLab 集成或使用 MCP 服务器。触发词:MCP、模型上下文协议、AI 助手集成、glab mcp serve。
serejaris/kimi-skills/skills/gitlab-cli-skills/glab-mcp Skill
12★ repoWork with Model Context Protocol (MCP) server for AI assistant integration. Exposes GitLab features as tools for AI assistants (like Claude Code) to interact with projects, issues, merge requests, and pipelines. Use when integrating AI assistants with GitLab or working with MCP servers. Triggers on MCP, Model Context Protocol, AI assistant integration, glab mcp serve.
serejaris/kimi-skills/skills/longread Skill
12★ repoUse this skill when an agent (main agent or subagent) encounters a file too large to read in a single pass — e.g. cat, read_file, or Read tool hits size limits or truncates output. First assess whether the file is suitable for chunk-based parallel reading, then proceed accordingly. Supports PDF, DOCX, TXT, MD, PPTX files. NOT for structured data (CSV, DTA, XLSX, etc.).
serejaris/kimi-skills/skills/skill-creator-swarm Skill
12★ repoGuide for creating effective skills. Use when users want to create a new skill or update an existing skill that extends an agent's capabilities with specialized knowledge, workflows, tool usage, or reusable resources. Also use when users want to refine a skill through swarm-style evaluation using subagents, baseline comparisons, grading, and analysis inside an agent swarm framework.
serejaris/kimi-skills/skills/skill-creator Skill
12★ 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 agent's capabilities with specialized knowledge, workflows, or tool integrations.
serejaris/kimi-skills/skills/swarm-workspace Skill
12★ repoFoundation for swarm coding workflows: the two-tier filesystem contract (a shared coordination git repo + fast per-subagent git worktrees) and the canonical setup-local.sh that spins up a worktree. Use its setup-local.sh whenever a swarm subagent needs an isolated, fast local checkout of the shared repo to edit and build in.
serejaris/kimi-skills/skills/vibecoding-general-swarm Skill
12★ repoGeneral-purpose coding orchestration. MANDATORY for ANY coding task not covered by vibecoding-webapp-swarm. Skip ONLY if the task matches vibecoding-webapp-swarm or is entirely non-coding.
serejaris/kimi-skills/skills/vibecoding-webapp-swarm Skill
12★ repoBuild any web-based project: websites, landing pages, web apps, dashboards, browser games, portfolios, and interactive experiences. Design-first React workflow. Skip if the user explicitly requests a non-React framework (Vue, Svelte, Angular, vanilla HTML) or the task is unrelated to web UI (CLI tools, scripts, data pipelines).
serejaris/kimi-skills/skills/webapp-building-swarm Skill
12★ repoTools for building modern React webapps with TypeScript, Tailwind CSS and shadcn/ui. Best suited for applications with complex UI components and state management. Supports optional templates for specialized requirement.
mirkobozzetto/arsenal/plugins/rfc/skills/rfc Skill
12★ repoMulti-step RFC (Request For Comments) workflow for Claude Code. Forces reasoning before action: problem → alternatives → tradeoffs → design → risks → recommendation → impl plan. Use when user says "RFC", "write an RFC", "design doc", "propose a", "before implementing", or when decision crosses a boundary (system/team/version). Integrates GitNexus codebase context, Exa research, adversarial review subagent.
pivyme/suiperpower/core/skills/build/build-with-claude Skill
12★ repoPair with a coding agent to build a Sui MVP step by step. Use when the user wants to build the MVP iteratively with an agent.
pivyme/suiperpower/core/skills/idea/overflow-copilot Skill
12★ repoResearch past Sui Overflow hackathon projects, winners, and gaps. Use when the user wants past Overflow research, winners, or hackathon archive.
troykelly/claude-skills/external/skills/hook-development Skill
no license12★ repoThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
troykelly/claude-skills/skills/autonomous-orchestration Skill
no license12★ repoUse when user requests autonomous operation across multiple issues. Orchestrates parallel workers using Task tool, monitors with TaskOutput, handles SLEEP/WAKE cycles, and works until scope is complete without user intervention.
The same file is in 2 other repositories
troykelly/claude-skills/skills/memory-integration Skill
no license12★ repoUse to maintain context across sessions - integrates episodic-memory for conversation recall and mcp__memory knowledge graph for persistent facts
The same file is in 2 other repositories
ahmedibrahim085/Claude-Multi-Agent-Research-System-Skill/.claude/skills/spec-workflow-orchestrator Skill
12★ repoOrchestrate comprehensive planning phase from ideation to development-ready specifications using 3 specialized agents (Full workflow documentation at docs/workflows/planning-workflow.md)
technicalpickles/pickled-claude-plugins/plugins/agent-meta/skills/harness-binary-spelunking Skill
12★ repoUse when investigating an agent-harness CLI's internals (Claude Code, codex, opencode, or similar): extracting the system prompt or tool descriptions, finding what code path produces a specific UI message, decoding minified function names or Rust symbols, understanding undocumented config keys, or otherwise spelunking a shipped binary (or its pinned source) to figure out how the tool actually behaves.
technicalpickles/pickled-claude-plugins/plugins/mcpproxy/skills/working-with-mcp Skill
12★ repoUse when user mentions MCPProxy/MCP tools (e.g., "check buildkite mcp", "use slack mcp") or when you need to discover or call tools through MCPProxy - immediately checks if mcp__MCPProxy__* tools are available, suggests /mcp reconnect if missing (MCPProxy MCP server not connected), explains when to use MCP tools vs HTTP API for debugging
The same file is in 3 other repositories
0x-Professor/Agent-Skills-Hub/skills/ml-model-eval-benchmark Skill
12★ repoCompare model candidates using weighted metrics and deterministic ranking outputs. Use for benchmark leaderboards and model promotion decisions.
0x-Professor/Agent-Skills-Hub/skills/skill-creator-pro Skill
12★ repoCreate and evolve production-ready skills with reusable scripts, references, and validation. Use for new skill creation, skill upgrades, and enforcing consistent metadata and structure.
Analyzing memory dumps with volatility
Mikaru0Mystic/sectinel/arsenal/Anthropic-Cybersecurity-Skills/skills/analyzing-memory-dumps-with-volatility Skill
12★ repo'Analyzes RAM memory dumps from compromised systems using the Volatility framework to identify malicious processes, injected code, network connections, loaded modules, and extracted credentials. Supports Windows, Linux, and macOS memory forensics. Activates for requests involving memory forensics, RAM analysis, volatile data examination, process injection detection, or memory-resident malware investigation.
The same file is in 1 other repository
Analyzing memory forensics with lime and volatility
Mikaru0Mystic/sectinel/arsenal/Anthropic-Cybersecurity-Skills/skills/analyzing-memory-forensics-with-lime-and-volatility Skill
12★ repo'Performs Linux memory acquisition using LiME (Linux Memory Extractor) kernel module and analysis with Volatility 3 framework. Extracts process lists, network connections, bash history, loaded kernel modules, and injected code from Linux memory images. Use when performing incident response on compromised Linux systems.
Conducting memory forensics with volatility
Mikaru0Mystic/sectinel/arsenal/Anthropic-Cybersecurity-Skills/skills/conducting-memory-forensics-with-volatility Skill
12★ repo'Performs memory forensics analysis using Volatility 3 to extract evidence of malware execution, process injection, network connections, and credential theft from RAM dumps captured during incident response. Covers memory acquisition, process analysis, DLL inspection, and malware detection. Activates for requests involving memory forensics, RAM analysis, Volatility framework, memory dump investigation, volatile evidence analysis, or live memory acquisition.
Deploying edr agent with crowdstrike
Mikaru0Mystic/sectinel/arsenal/Anthropic-Cybersecurity-Skills/skills/deploying-edr-agent-with-crowdstrike Skill
12★ repo'Deploys and configures CrowdStrike Falcon EDR agents across enterprise endpoints to enable real-time threat detection, behavioral analysis, and automated response. Use when onboarding endpoints to EDR coverage, configuring detection policies, or integrating Falcon telemetry with SIEM platforms. Activates for requests involving CrowdStrike deployment, Falcon sensor installation, EDR policy configuration, or endpoint detection and response.
Detecting ai model prompt injection attacks
Mikaru0Mystic/sectinel/arsenal/Anthropic-Cybersecurity-Skills/skills/detecting-ai-model-prompt-injection-attacks Skill
12★ repo'Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison''s prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.
Exploiting constrained delegation abuse
Mikaru0Mystic/sectinel/arsenal/Anthropic-Cybersecurity-Skills/skills/exploiting-constrained-delegation-abuse Skill
12★ repoExploit Kerberos Constrained Delegation misconfigurations in Active Directory to impersonate privileged users via S4U2self and S4U2proxy extensions for lateral movement and privilege escalation.
Extracting config from agent tesla rat
Mikaru0Mystic/sectinel/arsenal/Anthropic-Cybersecurity-Skills/skills/extracting-config-from-agent-tesla-rat Skill
12★ repoExtract embedded configuration from Agent Tesla RAT samples including SMTP/FTP/Telegram exfiltration credentials, keylogger settings, and C2 endpoints using .NET decompilation and memory analysis.