Loading...
Loading...
Found 5,041 Skills
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines. Part of the context engineering skill suite — also activates when the user mentions "context engineering" or "context-engineering" in the context of measuring agent effectiveness.
This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents, sandboxed VMs, agent infrastructure, Modal sandboxes, self-spawning agents, or remote coding environments. Part of the context engineering skill suite — also activates when the user mentions "context engineering" or "context-engineering" in the context of agent deployment and execution infrastructure.
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits. A core context engineering skill — also activates when the user mentions "context engineering" or "context-engineering" in the context of managing token budgets and session longevity.
This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution. Part of the context engineering skill suite — also activates when the user mentions "context engineering" or "context-engineering" in the context of orchestrating context across multiple agents.
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. A core context engineering skill — also activates when the user mentions "context engineering" or "context-engineering" in the context of diagnosing and mitigating context failures.
Artifact status + multi-phase orchestration. Scan what exists, check freshness, compose and track complex workflows across sessions. Not for skill routing (the agent does that proactively).
Multi-agent discussion rooms — debate or poll a problem from multiple perspectives. Standalone or invoked by other skills as a sub-routine. Mode=debate: N agents argue in rounds, converge. Mode=poll: N agents independently analyze, aggregate by consensus. Not for implementation (use system-architecture). Not for verification (use review-chain). For clarifying requirements first, see discover. For decomposing work after a decision, see task-breakdown.
Index skill for the blockint-skills bundle—includes a “choosing a skill” routing map and routes to focused skills on blockchain intelligence fundamentals, address clustering, analytics, tokenomics, investigation ethics, Phalcon Compliance documentation pointer, Chainalysis public Sanctions API/oracle router, FATF official AML/CFT glossary, Arkham Intel research article on leading crypto analysis tools for traders, Christoph Michel cmichel.io guide on becoming an EVM smart contract auditor, risk exposure, behavioral risk, address and transaction screening workflow concepts, Range AI investigation playbook (MCP), crypto market mechanics, OSINT (Bellingcat toolkit), Solana external stacks (Helius, Range MCP, Tavily, PayAI, React Flow, Solana Policy Institute), DeFi/MEV/rug skills, privileged-access mitigation lessons (Chainalysis Drift case study), coral-xyz sealevel-attacks Solana security examples, Neodyme Solana Security Workshop (workshop.neodyme.io), Osec (osec.io) Solana auditor introduction blog post, canonical X post citation for @armaniferrante status 1411589629384355840, BlockchainSpider open-source data collection, MoTS (Know Your Transactions / transaction semantics research repo), Impersonator dApp devtools (EVM + Solana read-only address presentation), Katana web crawling, lcamtuf American Fuzzy Lop (AFL) classic documentation (lcamtuf.coredump.cx/afl), and the official Agent Skills open-format specification (agentskills/agentskills, agentskills.io/llms.txt doc index). Use when the task spans multiple topics or the user needs help picking which named skill to load.
Manages parent/child agent relationships with task delegation and result aggregation. Supports sequential chains, parallel fans, conditional routing, retry logic, timeout handling, and YAML-based visual workflow definition.
Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.
Generates customized client onboarding checklists with phased tasks, ownership assignments, dependencies, acceptance criteria, and email templates. Adapts to consulting, SaaS, or agency engagement models.
Full-stack hybrid memory system with vector + keyword search. Stores embeddings in SQLite with FTS5 for BM25 keyword search and cosine similarity. Enables semantic memory recall for agents.