All authors
Claude Skills by systempromptio
github.com/systempromptio39 skills0 installs53 views
- Analytics DashboardsRead 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`.Votes: 0GitHub stars: 29
- Demonstrate GovernanceDrive 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.Votes: 0GitHub stars: 29
- Inspect AgentsWork 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.Votes: 0GitHub stars: 29
- Inspect Ai RequestsFollow 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.Votes: 0GitHub stars: 29
- Inspect ConversationShow 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.Votes: 0GitHub stars: 29
- Inspect Mcp And SkillsDiscover 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.Votes: 0GitHub stars: 29
- Manage PermissionsChange 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.Votes: 0GitHub stars: 29
- Manage ServicesOperate the running Enterprise Demo stack: services, the Postgres database, and scheduled jobs.Votes: 0GitHub stars: 29
- Systemprompt CliA navigable map of the `systemprompt` CLI. Use it to find the right command, then drill in with `--help`.Votes: 0GitHub stars: 29
- Use Dangerous SecretA 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.Votes: 0GitHub stars: 29
- Example Web SearchSearch the web for information using the WebSearch toolVotes: 0GitHub stars: 29
- Use Dangerous SecretDemonstrates governance blocking when plaintext secrets are detected in tool inputsVotes: 0GitHub stars: 29
- Example Web SearchA simple demonstration skill that searches the web for informationVotes: 0GitHub stars: 29
- Use Dangerous SecretDemonstration skill that attempts to use a plaintext secret, designed to be blocked by governance hooksVotes: 0GitHub stars: 29
- Systemprompt Admin Agent ManagementList, message, configure, and restart agents via the systemprompt CLIVotes: 0GitHub stars: 29
- Systemprompt Admin AnalyticsView traffic, costs, agent stats, and bot detection via the systemprompt CLIVotes: 0GitHub stars: 29
- Systemprompt Admin DatabaseExplore schema, run queries, and manage migrations via the systemprompt CLIVotes: 0GitHub stars: 29
- Systemprompt Admin JobsList, run, enable, and disable scheduled jobs via the systemprompt CLIVotes: 0GitHub stars: 29
- Systemprompt Admin LogsView, filter, stream, trace, and audit logs via the systemprompt CLIVotes: 0GitHub stars: 29
- Systemprompt Admin ServicesStart, stop, restart, and health-check services via the systemprompt CLIVotes: 0GitHub stars: 29
- Systemprompt Admin Skill CreationCreate, structure, and publish skills through the skill-plugin-marketplace pipelineVotes: 0GitHub stars: 29
- Systemprompt Admin User ManagementManage users, roles, sessions, and IP bans via the systemprompt CLIVotes: 0GitHub stars: 29
- Dev Architecture StandardsLayer architecture, module boundaries, extension patterns, plugin structure, config system, and build pipeline standardsVotes: 0GitHub stars: 29
- Dev Ext Data ProvidersPageDataProvider, ContentDataProvider, and FrontmatterProcessor trait implementationsVotes: 0GitHub stars: 29
- Dev Ext FeedsRssFeedProvider and SitemapProvider trait implementations for SEO and content syndicationVotes: 0GitHub stars: 29
- Dev Ext HooksHook catalog, lifecycle events, hook scripts, and event-driven automationVotes: 0GitHub stars: 29
- Dev Ext InfrastructureJobs, Schemas, Router, Assets, Storage Paths, Site Auth, and Config Validation trait implementationsVotes: 0GitHub stars: 29
- Dev Ext ProvidersLlmProvider, ToolProvider trait implementations and MCP server integrationVotes: 0GitHub stars: 29
- Dev Ext RenderingComponentRenderer, TemplateProvider, TemplateDataExtender, and PagePrerenderer trait implementationsVotes: 0GitHub stars: 29
- Dev Frontend StandardsComplete JavaScript, CSS, accessibility, event architecture, bundle pipeline, and admin UI coding standardsVotes: 0GitHub stars: 29
- Dev Rust StandardsComplete Rust coding, linting, testing, architecture, and layer boundary standards for systemprompt.io developmentVotes: 0GitHub stars: 29
- Dev Web StandardsExtension system, content templates, page prerendering, and CSS management standards for systemprompt.io web developmentVotes: 0GitHub stars: 29
- Admin Ai UsageAnswer questions about AI spend and adoption on this platform - "what did we spend on AI this week", "top users by cost", "which skills / models / plugins are used most", "were there failed or denied requests", "how does this week compare to last". For what a person or team has been working on, use `admin_person_activity`. All tools are on the admin `systemprompt` server and read this platform's own audit tables, so figures are exact; quote them as returned.Votes: 0GitHub stars: 29
- Admin Person ActivityAnswer "what has <person> been working on", "how much is <person/team> using the platform", "who in <team> is active", "how intensively", or "whose work relates to <topic>". Reads conversations, skills used and active days, not raw requests. The unit is the **conversation**, not the request. One Claude Code session is hundreds of requests, so request counts and request timestamps say nothing about what someone did or how long they worked.Votes: 0GitHub stars: 29
- Who Am IUse when someone asks who they are on this instance, what they have access to, why a skill or connector they expected is missing, or what they are allowed to do here. It is the first thing a new user runs and the fastest answer to "why can't I see X".Votes: 0GitHub stars: 29
- Alpha DiscoveryWalk a new field engagement from first contact to a scoped brief.Votes: 0GitHub stars: 8
- Alpha ReportTurn engagement notes into an account report the delivery lead can send.Votes: 0GitHub stars: 8
- Beta SummaryProduce the weekly delivery summary from the group's open work.Votes: 0GitHub stars: 8
- Gamma OneA skill in a tree that violates the sidecar contract.Votes: 0GitHub stars: 8