hashgraph-online

Coordinate agents via the AMQ CLI for file-based inter-agent messaging. Use this skill whenever you need to send messages to another agent (codex, claude, or any named handle), check your inbox, drain queued messages, set up co-op mode between agents, join a…

Parallel-research-then-converge design workflow between two agents. Use this skill when the user wants two agents to independently think through a design problem before aligning on a solution — "spec X with codex", "design X together", "both agents think…

Use when defining new features, product behavior, UI/component design, architecture choices, contract changes, or ambiguous medium/high-complexity work before implementation, or when the user asks to grill or pressure-test a plan or design.

Use when starting a turn or checking Aegis skill routing.

Use when you have a spec or requirements for a multi-step task, before touching code

Retrieve bounded finished-job output. Use for completed work and automatically when a CPJ hook begins "Background job `...` finished".

Determine whether a repository contains a supported cloud workload, then assess eligible targets for cloud-native readiness with a 0-12 score. Use for containerization readiness, Docker/Kubernetes compatibility, deployment feasibility, workload eligibility,…

Convert Docker Compose files or installation docs into production-grade Sealos templates with role-specific personal low-load resource sizing, official route and runtime semantics, KubeBlocks database and Job gates, and managed or optional S3 storage…

Run HOL Guard scanner and guard operations via `uv run hol-guard`. Use when the user asks to scan plugins/MCP/skills for security, quality, or ecosystem compliance, or when they ask to run guard detect/install/protect workflows for local AI harnesses.

An example skill that does things with clear provenance, taxonomy, and metadata for trust scoring.

Dangerous fixture that tries to exfiltrate workspace secrets.

Fixture that tries to exfiltrate SSH keys and environment secrets.

Looks benign but has malicious subdirectory files.

A completely safe skill with no risk signals.

Example Claude skill

Example repository plugin skill.

Create an inspectable CIGAR checkpoint before compaction, interruption, or a meaningful task boundary.

Compile a deterministic CIGAR context bundle for the current task with an explicit token budget and inspectable manifest.

Prepare, inspect, commit, and reconcile governed CIGAR effects while preserving explicit authorization and idempotency.

Create or accept a recipient-specific CIGAR handoff without forwarding the parent conversation transcript.

Explain the provenance, authority, expiry, degradation state, and token accounting of CIGAR context already presented in this session.

Install, initialize, repair, or check local HOL Guard security protection for OpenClaw.

Scan AI agent skills, plugins, MCP servers, and agent tooling for prompt injection, unsafe commands, secret exposure, and supply-chain risks before installing or trusting them.

Use when setting up HOL Guard, protecting local AI harnesses, reviewing Guard approvals or receipts, scanning Codex plugins, skills, MCP servers, marketplace packages, or running plugin-scanner verification before release.

Demo skill used to verify skill registry `pricing` metadata round-trips end-to-end.

Use Seltz's official MCP search tool for current, source-backed web research in Codex.

Use CurrencyGuard's public MCP to price and explain invoice-linked FX protection, inspect rates, and resolve settlement dates without executing trades or giving financial advice.

Use Droplinked's live Inventory MCP to research catalog and merchant facts, then draft evidence-backed AEO/GEO product briefs and listicles.

Use when setting up HOL Guard, protecting local AI harnesses (Grok Build, Codex, Claude Code), reviewing Guard approvals or receipts, scanning plugins, skills, MCP servers, marketplace packages, or running plugin-scanner verification before release.

Use this skill when operating the Programmable Secrets contracts and released CLI for dataset registration, policy creation, preview-first writes, UAID-gated purchases, receipt checks, Robinhood or Arbitrum testnet workflows, local KRS helpers, profiles,…