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
S3YED/appie-kit/skills/ecc/agent-eval Skill
12★ repoHead-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
The same file is in 5 other repositories
S3YED/appie-kit/skills/ecc/agent-payment-x402 Skill
12★ repoAdd x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol.
The same file is in 1 other repository
S3YED/appie-kit/skills/ecc/agent-sort Skill
12★ 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 3 other repositories
S3YED/appie-kit/skills/ecc/autonomous-agent-harness Skill
12★ repoTransform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks (Hermes, AutoGPT) by leveraging Claude Code's native crons, dispatch, MCP tools, and memory. Use when the user wants continuous autonomous operation, scheduled tasks, or a self-directing agent loop.
The same file is in 1 other repository
S3YED/appie-kit/skills/ecc/benchmark-optimization-loop Skill
12★ repoUse when the user asks to make something faster, try many variants, run recursive optimization, benchmark latency/throughput/cost, or choose the best implementation by repeated measured tests.
S3YED/appie-kit/skills/ecc/benchmark Skill
12★ repoUse this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.
The same file is in 2 other repositories
S3YED/appie-kit/skills/ecc/claude-devfleet Skill
12★ repoOrchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.
The same file is in 6 other repositories
S3YED/appie-kit/skills/ecc/continuous-agent-loop Skill
12★ repoPatterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
The same file is in 5 other repositories
S3YED/appie-kit/skills/ecc/cost-aware-llm-pipeline Skill
12★ repoCost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
The same file is in 9 other repositories
S3YED/appie-kit/skills/ecc/data-scraper-agent Skill
12★ repoBuild a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.
The same file is in 8 other repositories
S3YED/appie-kit/skills/ecc/dmux-workflows Skill
12★ repoMulti-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
The same file is in 5 other repositories
S3YED/appie-kit/skills/ecc/dynamic-workflow-mode Skill
12★ repoDesign task-local harnesses, eval gates, and reusable skill extraction for Claude dynamic workflow mode and other adaptive agent harnesses.
S3YED/appie-kit/skills/ecc/enterprise-agent-ops Skill
12★ repoOperate long-lived agent workloads with observability, security boundaries, and lifecycle management.
The same file is in 7 other repositories
S3YED/appie-kit/skills/ecc/eval-harness Skill
12★ repoFormal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
The same file is in 9 other repositories
S3YED/appie-kit/skills/ecc/healthcare-eval-harness Skill
12★ repoPatient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures.
The same file is in 2 other repositories
S3YED/appie-kit/skills/ecc/ito-data-atlas-agent Skill
12★ repoDesign background Data Atlas style agents for Itô basket research, market discovery, parameter drafting, and human-in-the-loop editing. Use for architecture and workflow planning, not live order execution.
S3YED/appie-kit/skills/ecc/knowledge-ops Skill
12★ repoKnowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.
The same file is in 1 other repository
S3YED/appie-kit/skills/ecc/llm-trading-agent-security Skill
12★ repoSecurity patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling.
The same file is in 2 other repositories
S3YED/appie-kit/skills/ecc/mcp-server-patterns Skill
12★ repoBuild MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
The same file is in 2 other repositories
S3YED/appie-kit/skills/ecc/prompt-optimizer Skill
12★ repoAnalyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.
The same file is in 2 other repositories
S3YED/appie-kit/skills/ecc/ralphinho-rfc-pipeline Skill
12★ repoRFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.
The same file is in 7 other repositories
S3YED/appie-kit/skills/ecc/recsys-pipeline-architect Skill
12★ repoDesign composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced For You algorithm. Use this skill whenever the user is building any system that picks "the top K items for a (user, context)" — social feeds, content CMSs, RAG rerankers, task prioritizers, notification triage, search reranking, ad ranking.
The same file is in 3 other repositories
S3YED/appie-kit/skills/ecc/regex-vs-llm-structured-text Skill
12★ repoDecision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
The same file is in 7 other repositories
S3YED/appie-kit/skills/ecc/security-scan Skill
12★ repoScan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
The same file is in 9 other repositories
S3YED/appie-kit/skills/ecc/skill-stocktake Skill
12★ repoUse when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.
The same file is in 3 other repositories
S3YED/appie-kit/skills/ecc/team-agent-orchestration Skill
12★ repoRun team-based orchestration for agent squads using work items, ownership, agent Kanban, merge gates, and control pane handoffs.
S3YED/appie-kit/skills/fleet/kanban-worker-auto Skill
12★ repoPitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
S3YED/appie-kit/skills/integrations/cognify Skill
12★ repoDurable client memory for KRATOS via Cognify (isolated local knowledge graph). Ingest documents and recall facts about Ibrahim Ramzy and his business with typed entities + relations. ALWAYS query this before answering recall questions about the client. Local backend only, tenant=ramzy, fully isolated (no shared/fleet endpoints).
S3YED/appie-kit/skills/integrations/drive-knowledge-ingestion Skill
12★ repoVijf-fase knowledge pipeline: Drive scanning → document text extraction → SQLite FTS5 knowledge base → entity extraction (heuristics) → knowledge graph → Neo4j export → Cognify memory integration → realtime dashboard. Disk-safe: media wordt alleen metadata, documenten download naar temp en verwijderen direct. Ontworpen voor 8GB+ constraints.
S3YED/appie-kit/skills/integrations/mcp/native-mcp Skill
12★ repoBuilt-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.
S3YED/appie-kit/skills/integrations/n8n-agents Skill
12★ repoDesign n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain.* AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output, output parser, RAG, vector store, a chat assistant/bot, or human-in-the-loop review. Covers Agent-vs-chain-vs-classifier choice, the model/memory/tools/outputParser slots, tool names/descriptions as prompt, structured output with autoFix, memory, RAG, human review, and chat topologies.
S3YED/appie-kit/skills/integrations/n8n-code-tool Skill
12★ repoWrite JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the `query` input, returning a string result, defining an input schema for structured arguments (specifyInputSchema, jsonSchemaExample, DynamicStructuredTool), or troubleshooting errors like "Wrong output type returned", "No execution data available", "The response property should be a string, but it is an object", "Cannot assign to read only property 'name'", or an AI agent that refuses to call the tool. Covers the critical differences between Code node and Code Tool: return format (string vs `[{json:{...}}]`), unavailability of `$fromAI`/`$input`/`$helpers` in the Code Tool sandbox, naming rules for AI invocation, and when to use `toolWorkflow`/HTTP Request Tool instead.
S3YED/appie-kit/skills/integrations/n8n-workflows/claude Skill
12★ repoClaude Code-specific n8n v2.0 workflow reference. Use when building n8n workflows — creating workflow JSON, implementing Wait node approval flows, troubleshooting Execute Sub-Workflow issues, setting up API credentials, building orchestrator patterns, using expressions, or any n8n workflow task.
S3YED/appie-kit/skills/integrations/n8n-workflows/n8n-agents Skill
12★ repoDesign n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain.* AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output, output parser, RAG, vector store, a chat assistant/bot, or human-in-the-loop review. Covers Agent-vs-chain-vs-classifier choice, the model/memory/tools/outputParser slots, tool names/descriptions as prompt, structured output with autoFix, memory, RAG, human review, and chat topologies.
The same file is in 1 other repository
S3YED/appie-kit/skills/integrations/n8n-workflows/n8n-code-tool Skill
12★ repoWrite JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the `query` input, returning a string result, defining an input schema for structured arguments (specifyInputSchema, jsonSchemaExample, DynamicStructuredTool), or troubleshooting errors like "Wrong output type returned", "No execution data available", "The response property should be a string, but it is an object", "Cannot assign to read only property 'name'", or an AI agent that refuses to call the tool. Covers the critical differences between Code node and Code Tool: return format (string vs `[{json:{...}}]`), unavailability of `$fromAI`/`$input`/`$helpers` in the Code Tool sandbox, naming rules for AI invocation, and when to use `toolWorkflow`/HTTP Request Tool instead.
The same file is in 1 other repository
S3YED/appie-kit/skills/integrations/n8n-workflows/n8n-mcp-tools-expert Skill
12★ repoExpert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, managing credentials, auditing instance security, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns. IMPORTANT — Always consult this skill before calling any n8n-mcp tool — it prevents common mistakes like wrong nodeType formats, incorrect parameter structures, and inefficient tool usage. If the user mentions n8n, workflows, nodes, or automation and you have n8n MCP tools available, use this skill first.
S3YED/appie-kit/skills/integrations/n8n-workflows/n8n-v2 Skill
12★ repoComprehensive n8n v2.0 reference for building workflow automation. Use this skill when working with n8n workflows, especially for (1) creating workflow JSON files for import, (2) implementing human-in-the-loop approval workflows with Wait nodes, (3) troubleshooting Execute Sub-Workflow node issues, (4) setting up API credentials (LinkedIn, Anthropic, NewsAPI), (5) building orchestrator patterns with sub-workflows, (6) using expressions in nodes, (7) understanding MCP server limitations, or (8) any n8n workflow development task.
S3YED/appie-kit/skills/integrations/native-mcp Skill
12★ repoBuilt-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.
S3YED/appie-kit/skills/knowledge/llm-wiki Skill
12★ repoKarpathy's LLM Wiki: build/query interlinked markdown KB.
S3YED/appie-kit/skills/knowledge/lm-evaluation-harness Skill
12★ repolm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
S3YED/appie-kit/skills/knowledge/turbovec Skill
12★ repoLocal vector search with turbovec (Google TurboQuant, Rust+Python). Use for embeddings indexing, semantic search, local RAG, or filtered vector retrieval without external services like Pinecone.
S3YED/appie-kit/skills/meta/hermes-agent-skill-authoring Skill
12★ repoAuthor in-repo SKILL.md: frontmatter, validator, structure.
S3YED/appie-kit/skills/meta/skill-creator Skill
12★ repoCreate, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
S3YED/appie-kit/skills/misc/agent-browser Skill
12★ repoBrowser automation CLI built for AI agents — compact ref-based text output (200-400 tokens vs 3000-5000 for full DOM), native Rust, 50+ commands. Default browser-automation tool for the fleet. Use for any web navigation, scraping, form-filling, screenshots, or testing from the shell.
S3YED/appie-kit/skills/misc/agentic-video-tools Skill
12★ repoCompare and integrate agentic short-form video editing SaaS tools and OSS alternatives for the Weblyfe Content Factory pipeline. Use when Appie-2 needs to automate: raw clip → Reel/Short/TikTok with captions/SFX/music/transitions → publish to IG/TikTok/YT with zero human editor in the loop. Covers automation depth ranking, API integration recipes, OSS alternatives, and anti-patterns.
S3YED/appie-kit/skills/misc/hermes-agent Skill
12★ repoConfigure, extend, or contribute to Hermes Agent.
S3YED/appie-kit/skills/misc/higgsfield-image Skill
12★ repoGenerate images using Higgsfield's Nano Banana Pro (nano_banana_2) via the mcporter MCP server. Use for product photos, character-consistent fashion photography, and creative assets. Primary image generation tool for TracyToronto e-commerce content.
S3YED/appie-kit/skills/misc/kanban-agent-workflows Skill
12★ repoOperate Hermes Kanban multi-agent boards as an orchestrator or worker: decompose work, route tasks, follow worker lifecycle, manage dependencies, heartbeat, block/unblock, recover stuck workers, and summarize results. Use for any Hermes Kanban collaboration workflow.
S3YED/appie-kit/skills/misc/memory-search Skill
12★ repoSearch and retrieve information from the Appie brain — daily logs, project notes, decisions, topics, and long-term memory files stored in ~/.hermes/memory/. Use this skill whenever you need to recall past conversations, decisions, project context, personal preferences, or anything discussed previously.
S3YED/appie-kit/skills/misc/n8n-agents Skill
12★ repoDesign n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain.* AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output, output parser, RAG, vector store, a chat assistant/bot, or human-in-the-loop review. Covers Agent-vs-chain-vs-classifier choice, the model/memory/tools/outputParser slots, tool names/descriptions as prompt, structured output with autoFix, memory, RAG, human review, and chat topologies.
S3YED/appie-kit/skills/misc/n8n-code-tool Skill
12★ repoWrite JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the `query` input, returning a string result, defining an input schema for structured arguments (specifyInputSchema, jsonSchemaExample, DynamicStructuredTool), or troubleshooting errors like "Wrong output type returned", "No execution data available", "The response property should be a string, but it is an object", "Cannot assign to read only property 'name'", or an AI agent that refuses to call the tool. Covers the critical differences between Code node and Code Tool: return format (string vs `[{json:{...}}]`), unavailability of `$fromAI`/`$input`/`$helpers` in the Code Tool sandbox, naming rules for AI invocation, and when to use `toolWorkflow`/HTTP Request Tool instead.
S3YED/appie-kit/skills/misc/native-mcp Skill
12★ repoMCP client: connect servers, register tools (stdio/HTTP).
S3YED/appie-kit/skills/misc/subagent-driven-development Skill
12★ repoExecute plans via delegate_task subagents (2-stage review).
S3YED/appie-kit/skills/misc/turbovec Skill
12★ repoLocal vector search with turbovec (Google TurboQuant, Rust+Python). Use for embeddings indexing, semantic search, local RAG, or filtered vector retrieval without external services like Pinecone.
Gws modelarmor sanitize prompt
S3YED/appie-kit/skills/openclaw-imports/gws-modelarmor-sanitize-prompt Skill
12★ repoGoogle Model Armor: Sanitize a user prompt through a Model Armor template.
The same file is in 1 other repository
S3YED/appie-kit/skills/openclaw-imports/kanban-orchestrator Skill
12★ repoDecomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
S3YED/appie-kit/skills/ops/agent-fleet-operations Skill
12★ repoOperate Hermes-style agent fleets across machines: provision remote hosts, validate transport/auth, refresh knowledge packs, and recover provider or gateway runtime failures.
S3YED/appie-kit/skills/ops/fleet-agent-provisioning Skill
12★ repoProvision a remote Hermes agent with the Appie Kit (skills, workspace, SOUL.md preservation, knowledge doc transfer, and verification). Use when setting up a new fleet member, reinstalling a corrupted agent, or bulk-updating skills across the fleet.
Hermes agent skill authoring sd
S3YED/appie-kit/skills/ops/hermes-agent-skill-authoring-sd Skill
12★ repoAuthor in-repo SKILL.md: frontmatter, validator, structure.
S3YED/appie-kit/skills/ops/hermes-agent-skill-authoring Skill
12★ repoAuthor in-repo SKILL.md: frontmatter, validator, structure.