fmind

Write standalone single-file Python scripts using PEP 723 inline metadata and uv. Use when creating a quick CLI script that needs dependencies without a full project.

Canonical Python development stack — uv, Ruff, ty, pytest, scaffolding, Litestar web, Typer scripts, and AI agents via agents-cli. Use for any Python project, library, CLI, or agent.

Cut a versioned release for fmind/dotfiles using the Go dot CLI release command (alias r). Use when shipping a new tagged version of dotfiles.

Build a presentation as one self-contained, zero-dependency HTML file (16:9, keyboard + touch nav), authored directly by the agent. Use when creating slides, a deck, or a talk from notes or a document.

Configure MCP servers for Antigravity, OpenCode, and Claude — stdio or remote transport, workspace or user scope. Use when adding, connecting, or troubleshooting an MCP server.

Bootstrap workspace agent configuration — AGENTS.md, the .agents/ layout, subagents, and skills — for Antigravity, OpenCode, and Claude. Use when initializing or onboarding a repository for agents.

Install Agent Skills with the `skills` CLI — from a Git repo or local path, into workspace or global scope for Antigravity, OpenCode, and Claude. Use when adding or updating skills.

Build minimal, non-root OCI images — `ko` for Go or a distroless multi-stage Dockerfile — then scan, sign, and SBOM them. Use when containerizing or packaging an app for deployment.

Guide to refine MLOps projects with task automation, containerization, CI/CD pipelines, and robust experiment tracking.

Guide to prepare MLOps projects for sharing, collaboration, and community engagement.

Guide to transform prototypes into robust, distributable Python packages using the src layout, hybrid paradigm, and strict configuration management.

Guide to initialize a new MLOps project with standard tools (uv, git, VS Code) and best practices.

Guide to implement full stack observability including reproducibility, lineage, monitoring, alerting, and explainability.

Guide to create structured, reproducible Jupyter notebooks for MLOps prototyping, emphasizing configuration management and pipeline integrity.

Guide to implement rigorous validation layers including static analysis, automated testing, structured logging, and security scanning.

Bootstrap a repo for agent-levers. Creates .agents/levers/, wires CLAUDE.md/GEMINI.md to import AGENTS.md, writes an AGENTS.md skeleton when missing. Hands off via /lever-new.

Start a new lever — discuss the ask in chat, then capture intent (Goal, Success sketch, Context, Open questions) as §Brief. Hands off via /lever <id>.

Advance an existing lever. Reads lever.yaml.step and runs the chain (plan → do → check → act → done) autonomously until it pauses or finishes.

Inspect or cancel levers. List all (no arg), detail one (TL;DR + criteria + per-criterion events timeline), or cancel one with `<id> cancel [<reason>]`. Never advances the chain.

Seed `.agents/docs/` with a navigation map of the project's key topics (tools, services, frameworks, ...) — a structured link index to upstream pages, plus a brief summary and key concepts. Future agents read locally to find the right upstream URL in one hop. Triggers include "gather docs for X", "seed agent docs", "set up .agents/docs", "deepen agent docs".

Re-verify entries in `.agents/docs/` against upstream — repair dead links in the documentation map, update drifted captured snippets, and bump `last_verified` dates. Triggers include "refresh agent docs", "update .agents/docs", "re-verify the docs".

Before web-searching or fetching docs for a project topic, check `.agents/docs/INDEX.md` and the matching `DOC.md` for a navigation map of curated upstream URLs. No-op if `INDEX.md` is missing.

Apply phase of an agent evolution — diff the winner workspace against the live repo, get explicit user confirmation, copy files in, optionally re-run gates against the live tree. Writes `applied`. Requires `winner` set by `/run-agent-evolution`.

Capture phase of an agent evolution — discuss the objective, gates, rubric, scope, and budget; write `.agents/evolutions/<id>-<slug>/{evolution.yaml, EVOLUTION.md}` only on explicit user agreement. Pairs with `/run-agent-evolution` (next) and `/apply-agent-evolution` (later).

Run phase of an agent evolution — plan a batch of up to `budget.parallel` variants, dispatch sub-agents in parallel to materialize and evaluate them, learn from results, repeat until budget / wall-clock / plateau. Writes `winner` on a clean stop. Requires an evolution captured via `/new-agent-evolution`; `/apply-agent-evolution` lands the winner afterward.

Apply the AI Coding 5xP Template framework to the project.

Use when authoring or building supagents sources under .agents/supagents/ — markdown that compiles to subagent files for Claude Code, Gemini CLI, GitHub Copilot, Cursor, OpenCode, and Kilo Code.