Context & AI engineering
25,729 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
JamesPrial/skills/skills/skill-creator Skill
no license0★ 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
Chengyu create something from nothing
evnchn-agentic/chengyu-skills/chengyu-create-something-from-nothing Skill
0★ repoSUBAGENT-ONLY skill for generating a graduated spread of plausible-to-speculative solutions when the main agent is stuck in a local minimum. Output is one continuous artifact (NO dividers) that starts from verified fact and slides into bottom-K speculation; calling main-agent fact-checks throughout. Has TWO HARD PRECONDITIONS that must be met before any output: (1) running on a BullshitBench-passing model (Claude 4.5+ Opus/Sonnet, or equivalent), (2) operator — NOT the agent — explicitly confirms for this invocation that the running model qualifies. Outside subagent context, or without both gates met: ABORT and surface the precondition failure.
Chengyu listen all sides see clearly
evnchn-agentic/chengyu-skills/chengyu-listen-all-sides-see-clearly Skill
0★ repoUse BEFORE declaring victory / shipping / committing — get adversarial multi-angle review from at least one of three source classes (subagent, internet, other LLMs via API). Inter-links with chengyu-create-something-from-nothing — high-hallucination LLM sources behave like uncontrolled 無中生有, so apply the verify-don't-trust-verbatim discipline. Source selection via BullshitBench (canonical hallucination-rate index); high vs low hallucination both useful for different needs; escalate to the user when unclear. One of the strongest pre-ship disciplines in this catalog.
evnchn-agentic/chengyu-skills/chengyu-one-time-one-meeting Skill
0★ repoUse when tempted to treat the current session as interchangeable with past or future ones — the every-session-is-unique discipline, and the invocation surface that fires durable-fix skills a fungible-session mindset would skip. Fires when about to defer something to "a future session" as if that session will reconstitute this exact context, when a memory-aware agent assumes "I'll just re-derive it from memory next time," or when about to take the cheap reversible-looking shortcut (leave a comment instead of a stub, a TODO instead of the fix, skip the memory write) on the assumption the work is trivially recoverable later. The specific context window you have now is the only one you'll ever have.
evnchn-agentic/chengyu-skills/chengyu-review-old-know-new Skill
0★ repoUse when bringing forward priors from PAST sessions / cross-agent history before doing new work — NOT about re-reading the current context window (which is trivially in-context). Specifically triggered when auto-compact is lossy, when cross-session reference is needed, when the same topic has been treated before, when the original work was done in a different agent's session, or when you need to locate/date a past session JSONL or answer "have we done this before / what did we decide". The discipline is targeted historical retrieval via grep + read of session JSONLs (incl. the mtime/substring/leading-dash traps that make naive search silently return nothing), then promotion to memory if the prior deserves persistence.
Chengyu think thrice before acting
evnchn-agentic/chengyu-skills/chengyu-think-thrice-before-acting Skill
0★ repoUse AFTER first-round planning is complete, to do META-PLANNING — what wasn't planned that should have been? What pitfalls don't surface in the first round due to existing context bias, context rot, plan mode system prompt biases, or other distortions? Triage importance, surface escape routes (subagent assessment, backups, operator ready for ctrl+C, anything). NOT a duplicate of plan mode or common-sense planning — this is the SECOND pass that catches what the first pass missed.
realraelrr/handoff-skill Skill
0★Compact the current conversation into a handoff document for another agent to pick up.
9uiLe/plugins/plugins/compact-plus/skills/compact-plus Skill
0★ repoSave the current Claude Code session state to a temporary state file before running /compact. MANDATORY TRIGGERS: /compact-plus, compact-plus, compact plus, compaction plus handoff, pre-compact state save. DO NOT TRIGGER: post-compact recovery, ordinary progress updates, plan creation, or casual context-usage discussion. Japanese triggers: 「/compact の前に状態を保存して」「コンパクト前の状態を残して」「compact-plus で退避して」
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/agent-architecture-audit Skill
no license0★ repoFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
The same file is in 3 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/agent-eval Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/agent-harness-construction Skill
no license0★ repoDesign and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
The same file is in 7 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/agent-introspection-debugging Skill
no license0★ repoStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
The same file is in 5 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/agent-payment-x402 Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/agent-sort Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/agentic-engineering Skill
no license0★ repoOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
The same file is in 10 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/agentic-os Skill
no license0★ repoBuild persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.
The same file is in 1 other repository
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/autonomous-agent-harness Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/autonomous-loops Skill
no license0★ repoPatterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
The same file is in 5 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/awesome-claude-skills/composio-skills/agent-mail-automation Skill
no license0★ repoAutomate Agent Mail tasks via Rube MCP (Composio). Always search tools first for current schemas.
The same file is in 6 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/awesome-claude-skills/composio-skills/benchmark-email-automation Skill
no license0★ repoAutomate Benchmark Email tasks via Rube MCP (Composio). Always search tools first for current schemas.
The same file is in 6 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/awesome-claude-skills/mcp-builder Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/awesome-claude-skills/skill-creator Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/benchmark Skill
no license0★ repoUse this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.
The same file is in 2 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/claude-devfleet Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/claude-red Skill
no license0★ repoOffensive security and penetration testing skill. Covers automated vulnerability scanning, secure-coding bypass detection, sanitization reviews, and exploit drafting.
The same file is in 1 other repository
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/composio-skills/agent-mail-automation Skill
no license0★ repoAutomate Agent Mail tasks via Rube MCP (Composio). Always search tools first for current schemas.
The same file is in 6 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/composio-skills/benchmark-email-automation Skill
no license0★ repoAutomate Benchmark Email tasks via Rube MCP (Composio). Always search tools first for current schemas.
The same file is in 6 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/continuous-agent-loop Skill
no license0★ repoPatterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
The same file is in 5 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/cost-aware-llm-pipeline Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/data-scraper-agent Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/enterprise-agent-ops Skill
no license0★ repoOperate long-lived agent workloads with observability, security boundaries, and lifecycle management.
The same file is in 7 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/eval-harness Skill
no license0★ repoFormal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
The same file is in 9 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/healthcare-eval-harness Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/knowledge-ops Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/llm-trading-agent-security Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/mcp-builder Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/mcp-server-builder Skill
no license0★ repoBuild custom MCP (Model Context Protocol) servers for AI tool integration. Covers server architecture, tool definitions, resource providers, and deployment.
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/mcp-server-patterns Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/prompt-engineering Skill
no license0★ repoSystematic prompt design patterns. Covers system prompts, few-shot examples, chain-of-thought, structured output, and evaluation strategies.
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/prompt-optimizer Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/rag-pipeline Skill
no license0★ repoRetrieval-Augmented Generation (RAG) pipeline patterns. Covers document ingestion, chunking, embeddings, vector search, and answer generation.
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/ralphinho-rfc-pipeline Skill
no license0★ repoRFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.
The same file is in 7 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/recsys-pipeline-architect Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/regex-vs-llm-structured-text Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/security-scan Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/skill-creator Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/skill-stocktake Skill
no license0★ 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
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/superpowers/skills/dispatching-parallel-agents Skill
no license0★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
The same file is in 13 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/superpowers/skills/subagent-driven-development Skill
no license0★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 6 other repositories
goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/zeoel-security Skill
no license0★ repoCheck any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security posture before production deployment - Running a compliance check against OWASP ASI 2026 standards - Mapping existing security controls to the 10 agentic risks - Generating a compliance report for security review or audit - Comparing agent framework security features against the standard - Any request like "is my agent OWASP compliant?", "check ASI compliance", or "agentic security audit"
The same file is in 1 other repository
goharabbas321/zeoel-framework/all-skills/agent-architecture-audit Skill
no license0★ repoFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
The same file is in 3 other repositories
goharabbas321/zeoel-framework/all-skills/agent-eval Skill
no license0★ 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
goharabbas321/zeoel-framework/all-skills/agent-harness-construction Skill
no license0★ repoDesign and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
The same file is in 7 other repositories
goharabbas321/zeoel-framework/all-skills/agent-introspection-debugging Skill
no license0★ repoStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
The same file is in 5 other repositories
goharabbas321/zeoel-framework/all-skills/agent-payment-x402 Skill
no license0★ 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
goharabbas321/zeoel-framework/all-skills/agent-sort Skill
no license0★ 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
goharabbas321/zeoel-framework/all-skills/agentic-engineering Skill
no license0★ repoOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
The same file is in 10 other repositories
goharabbas321/zeoel-framework/all-skills/agentic-os Skill
no license0★ repoBuild persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.
The same file is in 1 other repository
goharabbas321/zeoel-framework/all-skills/autonomous-agent-harness Skill
no license0★ 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
goharabbas321/zeoel-framework/all-skills/autonomous-loops Skill
no license0★ repoPatterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
The same file is in 5 other repositories