A curated registry of reusable Mercury Agent, Open Claw or Hermes Agent skills designed for real developer workflows, persistent memory, and token-efficient execution.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Implement comprehensive audit logging and reporting for multi-agent systems. Covers event capture, structured logging, traceability, compliance reporting, forensic analysis, and real-time monitoring dashboards for agent actions and decisions.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Design and implement agent-to-agent handoff protocols for multi-agent systems. Covers context passing, escalation patterns, handshake mechanisms, conversation continuity, and routing between specialized agents in production workflows.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Monitor AI agent health, detect anomalies, set up alerting, and maintain observability dashboards for production multi-agent systems. Covers liveness checks, performance metrics, drift detection, and incident response.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Design and operate task delegation systems for multi-agent fleets. Covers workload distribution, load balancing, queue management, priority scheduling, and dynamic agent scaling for production agent systems.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Comprehensive guide to designing, building, and operating AI agents. Covers agent architecture, tool use patterns, memory systems, orchestration strategies, planning approaches, error recovery, and safety guardrails for production-grade agent systems.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Design robust error recovery, retry logic, and fallback strategies for production AI agents. Covers transient failure handling, circuit breakers, exponential backoff, state recovery, graceful degradation, and dead-letter queues for agent systems.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Lightweight personal knowledge base — markdown + YAML frontmatter structured notes with full-text search and cross-referencing for AI agents.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Design and operate memory systems for long-running AI agents. Covers context window optimization, summarization strategies, vector-based retrieval, episodic memory, memory consolidation, and garbage collection for production agent systems.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Master the art and science of crafting effective prompts for large language models. Covers foundational patterns, advanced techniques like chain-of-thought and role prompting, structured output formats, and practical strategies for iterative refinement.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Manage prompt versions, run A/B tests across agent prompts, track performance regressions, and safely roll out prompt changes in production. Covers prompt diffing, semantic versioning, canary releases, and automated evaluation.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Configure RouterBase as an OpenAI compatible model gateway for AI apps, with routing, fallback, media generation, and credential handling patterns.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Track, optimize, and control token consumption across multi-agent systems. Covers budget allocation, real-time monitoring, cost attribution, per-agent limits, and proactive cost optimization for production LLM deployments.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Automated daily tech briefing — multi-source collection → knowledge-base deduplication → AI summarization → TTS speech synthesis, generating MP3 audio briefings.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Capture high-fidelity screenshots of any website using Playwright — supports custom viewports, dark/light mode, mobile/tablet/desktop presets, split-screen, element-based capture by CSS selector, and text-based area capture. Integrates with Telegram or any output channel for delivery.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Master shell scripting best practices, error handling, portability, debugging, and performance optimization for reliable automation scripts.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
EDUCATIONAL / RESEARCH ONLY — Single-account always-on Twitter/X manager driven by cookies + headless Playwright. Runs a 10-minute scheduler that drafts posts, engages with timeline/search results, and queues anything risky for Telegram human approval. Hard daily ceilings, structural prompt-injection defenses, and DM…
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Master workflow design, n8n patterns, automation triggers, error handling, and monitoring for reliable business process automation.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Design safe X/Twitter automation workflows for tweet search, reply reads, monitoring, posting, and agent-operated social media actions.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Design agent workflows that pull YouTube transcripts, search videos and channels, and monitor new uploads without Google API quotas or OAuth setup.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
REST and GraphQL API design principles, versioning, error handling, and documentation patterns.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
JWT, OAuth2, SAML, session management, RBAC, ABAC, and MFA implementation.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
CDN, Redis, in-memory cache, cache invalidation, and distributed caching patterns.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
Schema design, normalization, indexing, migrations, and query optimization for SQL and NoSQL.
cosmicstack-labs/mercury-agent-skills
Skill Claude CodeCodex
RabbitMQ, Kafka, SQS, pub/sub, competing consumers, dead letter queues, and event streaming.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: