Loading...
Loading...
Found 4,749 Skills
Audit token waste across agent systems (Claude Code, OpenClaw, Hermes, OpenCode). Detect idle burns, model misrouting, and config bloat with dollar savings.
Guided, section-by-section GDD authoring for a single game system. Gathers context from existing docs, walks through each required section collaboratively, cross-references dependencies, and writes incrementally to file.
Use when the user says "This is a long-running task. Record it." or "Create task memory for this long-running task", or when a new long-running task needs separate tracking across sessions.
Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model, MemoryClient/MemorySettings, the memory MCP server, or any of the framework integrations (LangChain, PydanticAI, CrewAI, AWS Strands, Google ADK, Microsoft Agent Framework, OpenAI Agents, LlamaIndex). Also use when the user mentions the hosted service at memory.neo4jlabs.com, NAMS, the Neo4j Agent Memory Service, the `nams_` API key prefix, or the hosted MCP endpoint. Also use when writing documentation, blog posts, tutorials, PRDs, or code samples for the project, when comparing agent memory approaches, or when positioning graph-native memory against vector-only approaches — even if the user doesn't explicitly name the package.
Detects and prevents code injection attacks targeting serverless functions (AWS Lambda, Azure Functions, Google Cloud Functions) through event source poisoning, malicious layer injection, runtime command execution, and IAM privilege escalation via function modification. The analyst combines static analysis of function code, CloudTrail event correlation, runtime behavior monitoring, and IAM policy auditing to identify injection vectors across the expanded serverless attack surface including API Gateway, S3, SQS, DynamoDB Streams, and CloudWatch event triggers. Activates for requests involving Lambda security assessment, serverless injection detection, function event poisoning analysis, or serverless privilege escalation investigation.
You are **Infrastructure Maintainer**, an expert infrastructure specialist who ensures system reliability, performance, and security across all technical operations. You specialize in cloud archite...
Expert in conversion tracking architecture, tag management, and attribution modeling across Google Tag Manager, GA4, Google Ads, Meta CAPI, LinkedIn Insight Tag, and server-side implementations. Ensures every conversion is counted correctly and every dollar of ad spend is measurable.
Error-to-fix playbook for every known failure mode on the OpenFinance backend — Polymarket, Relay, Hyperliquid, Privy delegation, and Solana RPC issues. Use this the moment a call fails, returns an unexpected status, or behaves inconsistently with on-chain state. Triggers on ANY of these error signatures verbatim or in paraphrase. Polymarket: "allowance: 0 but on-chain shows max", "CLOB reports allowance 0", "approvals confirmed but order rejected", "404 upstream" on market orders, "tick size" rejection, "order size below minimum", USDC.e vs pUSD vs native USDC confusion, V1 vs V2 exchange confusion. Relay: "InstructionFallbackNotFound", "Custom:101", "Custom:6000", "AnchorError", "Blockhash not found", "TransactionExpired", "No valid authorization signatures were provided", "Solana wallet is not delegated to the app", 412 delegation errors, quote succeeded but execute failed, stuck funds on Solana, stuck funds cross-chain, topupGas forced off. Hyperliquid: "Insufficient perp account value", "price out of bounds", WebSocket stale data, spot vs perp balance confusion. General: any "why is X failing", "why does on-chain and API state disagree", "what does this error mean". Read this BEFORE assuming a bug in the MCP or backend — most of these errors are already catalogued with known fixes.
Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with multiple agent roles.
16:9 HTML deck in editorial-minimalist taste. Warm cream slides, serif display + grotesque body, hairline rules, monospace meta, generous macro-whitespace, one accent. Distilled from Leonxlnx/taste-skill `minimalist-skill`.
Use when auditing a wiki for health issues — contradictions between pages, orphan pages, broken cross-references, stale claims, missing pages, or coverage gaps. Run after every 5-10 ingests.
Checkpoint and resume workflow state for context persistence across sessions. Use when the user says 'save progress', 'checkpoint', 'I need to stop', or runs /checkpoint or /rehydrate. Saves current workflow phase, task progress, and artifacts for later resumption. Do NOT use for workflow initialization (handled by ideate/debug/refactor commands).