AI-driven, CLI-first dotfiles for Linux & macOS — chezmoi + mise, Fish, Neovim, and a custom Go CLI
Skill Claude CodeCodex
Use the Hugging Face hf CLI to download, upload, cache, and run jobs for models, datasets, and spaces with token auth and bounded transfers. Use for any Hugging Face Hub task.
Skill Claude CodeCodex
Canonical Hugo static-site stack with the Hextra docs theme: Hugo Modules, mise tasks, dprint, lefthook, GitHub Pages deploy. Use for docs sites and static websites.
Skill Claude CodeCodex
Turn accepted requirements into ordered dependency-aware slices and a repository-grounded implementation plan. Use before editing when work spans systems, has migration or rollout risk, needs architecture choices, or should be split.
Skill Claude CodeCodex
Trim, restructure, and verify project documentation: docs sites, wikis, guides, changelogs, long AGENTS.md files. Use when docs are too long, outdated, or noisy.
Skill Claude CodeCodex
Coordinate a live outage, breach, or degradation affecting users. Establish incident command; triage, contain harm, bound blast radius, preserve evidence, communicate, roll back, verify restoration.
Skill Claude CodeCodex
Run an opt-in k3d or kind cluster on the workstation and deploy into it with kubectl, helm, helmfile, or skaffold. Use only when a project needs local Kubernetes.
Skill Claude CodeCodex
Use the kaggle CLI for competitions, datasets, kernels, and models with token auth, bounded downloads, and explicit submission authority. Use for any Kaggle CLI task.
Skill Claude CodeCodex
Canonical lefthook git-hooks setup: pre-commit (format, check, secret scan) and pre-push (test), each delegating to mise run tasks. Use for git hook configuration.
Skill Claude CodeCodex
Author an MCP server in Go, Python, or TypeScript with the official SDKs over stdio or Streamable HTTP and test it with the MCP Inspector. Use when building an MCP server.
Skill Claude CodeCodex
Create, theme, validate, and embed Mermaid diagrams, the default diagram format for GitHub, Hugo, Slidev, and docs. Use for any new diagram unless D2 or LikeC4 applies.
Skill Claude CodeCodex
Configure pinned mise tools and the canonical install, format, check, test, build, and watch tasks shared by hooks and CI. Use for any mise.toml or task work.
Skill Claude CodeCodex
Bootstrap a new repository by composing the stack, license, mise, lefthook, dprint, CI, agent files, GitHub settings, and first release skills. Use when creating a project.
Skill Claude CodeCodex
Instrument a service or agent with JSON logs, OpenTelemetry traces and metrics, traceid correlation, and GenAI spans on Google Cloud. Use when adding logs, traces, or metrics.
Skill Claude CodeCodex
Run semantic SAST with opengrep and a pinned opengrep-rules checkout as the opt-in check:sast task, with inline suppressions and JSON or SARIF reports. Use for any opengrep scan or rule pin.
Skill Claude CodeCodex
Execute an accepted implementation plan in bounded, verified slices. Use to coordinate agents and shared-file ownership, resume planned work, or finish scoped tasks without crossing commit or deploy boundaries.
Skill Claude CodeCodex
Red-team a product, architecture, implementation, migration, or launch plan before execution. Use for pre-mortems, scope challenge, and testing assumptions, dependencies, and failure modes, not code.
Skill Claude CodeCodex
Drive browsers with Playwright for end-to-end tests, screenshots, traces, and codegen, and install the official Playwright skills. Use for browser automation or e2e testing.
Skill Claude CodeCodex
Critique customer interface flows for interaction, visual, responsive, keyboard and screen-reader accessibility, and content with runtime evidence. Use for UX audits, design reviews, onboarding, empty states, or redesign.
Skill Claude CodeCodex
Run the product loop — discover, specify, launch, learn — with build-or-stop calls, MVP, demand tests, PRDs, journeys, acceptance, positioning, onboarding, rollout, pricing, pivots. Use when deciding, launching, or reviewing a product bet.
Skill Claude CodeCodex
Audit production operability and operational fitness: go/no-go, rollback, migrations, observability, recovery, support and halt thresholds; separate local, exact-head CI, runtime, deployed, and public release proof.
Skill Claude CodeCodex
Turn audit findings into deduplicated, prioritized issue drafts with dependencies and explicit authorization before any GitHub mutation. Use when review findings must become tracked issues.
Skill Claude CodeCodex
Refresh an existing repository so everything is current, consistent, simple, and working: upgrade tools, cut debt, sync docs, green gate. Use for a full project review.
Skill Claude CodeCodex
Write the right LICENSE and manifest field: MIT for public fmind, fmind-ai, and mlops-courses repos, CC-BY-4.0 for written courses, proprietary otherwise. Use when adding a license.
Skill Claude CodeCodex
Design a prompt stack for an LLM or agent app: instruction precedence, request-time and retrieved context, tool contracts and side effects, structured output, versioned candidates. Use when writing production prompts.
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: