4,052 tools found
Claude skill that runs AI-powered audits on Linux kernel patches, Terraform plans, and Kubernetes manifests to catch security and cost risks before merge.
Claude skill that scaffolds a new subagent plugin: interviews the user, generates a detailed persona, and writes the agent and routing-skill files.
Transforms raw agent evaluation runs into decision-ready reports with explicit outcome populations, denominators, latency data, and experiment conditions
Claude skill that fault-injects a deterministic schedule into an agent workflow to prove recovery, checkpoints, and budgets hold, not just claim it.
agentMemory gives AI agents persistent, searchable memory via an MCP server that auto-syncs to project markdown files.
Agent QA Authoring creates, validates, and executes Agent QA tests, suites, and hooks through MCP or CLI while preserving canonical IDs and schema contracts.
Claude skill that repairs a failed Agent QA run from recorded evidence, making the smallest justified fix and verifying it with the narrowest rerun.
Classify failed Agent QA runs by inspecting artifacts and logs, returning category, confidence, ownership, and next action.
Decide between cron, external schedulers, or Hermes built-in scheduling for recurring, heartbeat, and looped agent work.
Orchestrator skill that routes work through a squad of eight specialized agents and relays compressed summaries back to the user.
Converts requirements into ordered, dependency-mapped implementation checklists with clear definitions of done and risk flags.
Aria is an architect skill for AI agent squads: it designs data models, API contracts, file structure, and security architecture before coding starts.
