Claude Skills by systempromptio

Read the workspace at a glance: spend, request volume, agent performance, tool reliability, sessions, and conversations - all rolled up over a time window. This is the fleet view; for drilling into one request use `inspect_ai_requests`, and for one conversation use `inspect_conversation`.

Drive every stage of the governance pipeline end to end, then prove that each decision was audited. This is the guided tour of the enforcement spine: the same four stages run on every tool call in the workspace.

Work with the agents in the workspace: list them, check their configuration and the MCP tools they can reach, send one a message over the A2A protocol, and read the artifacts and traces it produces.

Follow one inference request through the AI gateway: from the client's `/v1/messages` call, through model routing and the governance pipeline, to the provider and back. Use it to debug a single request - routing, denials, latency, cost, or the tool calls it spawned.

Show the structured data behind a conversation that is happening right now. When a client like Claude Desktop talks to the gateway, every message, AI request, tool call, governance decision, and cost lands in the database keyed to one session. This skill reconstructs that whole picture from a single starting id.

Discover and exercise the MCP plugin surface - especially the admin-only `systemprompt` MCP server that runs CLI commands as a tool - and keep the skills catalogue in sync.

Change what a user is allowed to do, then watch the governance pipeline honour the change on the very next call - no restart, no new token. This is the live proof that authority is data, not a baked-in constant.

Operate the running Enterprise Demo stack: services, the Postgres database, and scheduled jobs.

A navigable map of the `systemprompt` CLI. Use it to find the right command, then drill in with `--help`.

A deliberately dangerous capability that the platform **refuses**. It exists in the catalog to prove that governance stops unsafe actions on two independent layers - access control and runtime secret scanning - rather than trusting the agent to behave.

Search the web for information using the WebSearch tool

Demonstrates governance blocking when plaintext secrets are detected in tool inputs

A simple demonstration skill that searches the web for information

Demonstration skill that attempts to use a plaintext secret, designed to be blocked by governance hooks

List, message, configure, and restart agents via the systemprompt CLI

View traffic, costs, agent stats, and bot detection via the systemprompt CLI

Explore schema, run queries, and manage migrations via the systemprompt CLI

List, run, enable, and disable scheduled jobs via the systemprompt CLI

View, filter, stream, trace, and audit logs via the systemprompt CLI

Start, stop, restart, and health-check services via the systemprompt CLI

Create, structure, and publish skills through the skill-plugin-marketplace pipeline

Manage users, roles, sessions, and IP bans via the systemprompt CLI

Layer architecture, module boundaries, extension patterns, plugin structure, config system, and build pipeline standards

PageDataProvider, ContentDataProvider, and FrontmatterProcessor trait implementations

RssFeedProvider and SitemapProvider trait implementations for SEO and content syndication

Hook catalog, lifecycle events, hook scripts, and event-driven automation

Jobs, Schemas, Router, Assets, Storage Paths, Site Auth, and Config Validation trait implementations

LlmProvider, ToolProvider trait implementations and MCP server integration

ComponentRenderer, TemplateProvider, TemplateDataExtender, and PagePrerenderer trait implementations

Complete JavaScript, CSS, accessibility, event architecture, bundle pipeline, and admin UI coding standards

Complete Rust coding, linting, testing, architecture, and layer boundary standards for systemprompt.io development

Extension system, content templates, page prerendering, and CSS management standards for systemprompt.io web development