Menu
Skills in this repository
SkillsMP has collected 73 skills from oysteinkrog/dotfiles. Open a skill to review its source and details.
oysteinkrog/dotfilesShowing 33 of 73 collected skills.
Patch Claude Code's native binary to suppress two nag warnings: (1) "Auth conflict: Both a token and an API key are set" — for intentional dual-auth/proxy setups. (2) "Claude Code has switched from npm to native installer" — when keeping the npm install on…
Mine atuin history and shell logs to find repetitive workflows, build Rust CLI or bash automations. Use when analyzing command patterns or finding automation opportunities.
Beads Rust issue tracker (br). Use when tracking tasks, managing dependencies, finding ready work, or syncing issues to git via JSONL.
Graph-aware task triage with bv and br. Use when prioritizing work, finding bottlenecks, tracking dependencies, or managing local issues across projects.
Convert markdown plans into beads with dependencies using br CLI. Use when creating task graphs, polishing beads before implementation, or bridging planning to agent swarm execution.
Brenner Bot CLI for research sessions. Use when in your brenner_bot repo, managing hypotheses, searching corpus, or running multi-agent sessions.
Gemini 3.1 Pro code review swarm via NTM. Use when "gemini review swarm", "code review with gemini", or multi-round code auditing with Gemini agents.
Domain-parameterized codebase auditing (security, UX, performance, API, copy, CLI). Use when auditing code, assessing quality, finding issues, or pre-launch review.
Build showcase-grade FrankenTUI screens. Use when working in ftui-demo-showcase, diagnosing TUI issues with doctor_frankentui, polishing TUI UX, or replacing placeholder interfaces.
Find stubs, mocks, placeholders, TODOs, and fake code in a project. Use when "find mocks", "find stubs", "find placeholders", "check for fake code", or auditing for incomplete code.
Audit and clean shell PATH pollution in .bashrc, .zshrc, .zshenv, .profile. Use when PATH has junk, wrong binary resolves, temp dirs in PATH, or duplicates.
Assess project status against README/plan vision. Use when "where are we", "reality check", "what's missing", "are we on track", "gap analysis", or "does this actually work".
Design and implement metamorphic testing for systems with the oracle problem. Use when: testing ML models, scientific computing, compilers, search engines, databases, graphics pipelines, or any system where correct output is unknown but input-output…
Manage WezTerm mux servers for AI agent swarms on high-RAM servers (512GB+). Use when wezterm mux unresponsive, agent sessions need rescue, tuning scrollback, or configuring persistent remote sessions.
Diagnose and fix system sluggishness caused by zombie processes, stuck commands, and accumulated cruft from running multiple coding agents. Finds stuck test runners, hung git operations, zombie search processes, and other resource-wasting processes while…
Fetch and display any X/Twitter tweet by URL or ID. Use when the user shares a tweet link (x.com or twitter.com), asks to read/fetch/see a tweet, or references a tweet ID. Handles text, images, videos, quoted tweets, and embedded links.
Review and polish all beads in the current project for correctness, completeness, and quality. Checks every bead carefully, finds issues, and fixes them using br/bv. Triggers on: polish beads, review beads, check beads, beads polish, qa beads.
Generate a comprehensive plan/PRD for AI agent execution. Creates agent-operable plans with architecture, security, testing, and user stories that convert to beads. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
Convert a PRD to br (beads_rust) issues. Creates an epic with child issues for each user story, sets up dependencies, and appends quality gates. Triggers on: convert prd, prd to beads, create beads from prd, prd to br, create issues from prd.
Interview me until you have 95% confidence about what I actually want, not what I think I should want.
What's the single smartest and most radically innovative and accretive and useful and compelling addition you could make to the project at this point?
Run ruff (Astral's Python linter & formatter) on Python code. Use when writing, editing, or reviewing Python code for lint issues and formatting. Triggers on: writing Python files, "lint", "format python", "run ruff", or after editing .py files.
Run ty (Astral's Python type checker) on Python code. Use when writing, editing, or reviewing Python code to catch type errors. Triggers on: writing Python files, "type check", "run ty", "check types", or after editing .py files.
Manage Python projects with uv (Astral's package/project manager). Use when creating Python projects, adding dependencies, running scripts, or managing Python versions. Triggers on: "create python project", "add dependency", "uv init", "uv add", "run python",…
Evaluate a repository against the Harness Engineering framework (OpenAI, Feb 2026) with multi-model consensus scoring. Triggers on "harness eval", "harness engineering", "agent readiness", "evaluate harness", "score repo".
Open markdown files in Markpad (Windows GUI viewer). Use when user says "view markdown", "read md", "show readme", "preview markdown", "open in markpad", "mdv", or wants to open a .md file for reading.
Publish static content to GitHub Pages (oysteinkrog/sites repo). Use when user says "publish site", "deploy to pages", "publish to gh-pages", or wants to put static HTML somewhere shareable.
Generate beautiful, well-designed web pages and visualizations. Creates self-contained HTML with professional design (typography, color, layout, spacing), OKLCH color palettes, dark/light themes, Mermaid diagrams, Chart.js charts, KPI dashboards, timelines,…
Monitor PR and fix any check failures until it is all green. Use when user says "monitor PR", "fix CI", "fix checks", "make PR green", or after creating a PR that has failing checks.
Open Windows Explorer in the current git worktree root. Use when user says "open explorer", "open folder", "show in explorer".
Copy text to the Windows clipboard from WSL. Handles Unicode correctly. Use when user says "copy to clipboard", "clip this", or "copy that".
Inspect .NET assemblies and NuGet packages. Use when you need to understand package contents, view public API surfaces, compare APIs between versions, or audit assemblies for SourceLink/determinism. Essential for .NET development tasks involving package…
Understand and work with the grove worktree manager. Use when the user references projects, worktrees, switching between projects, or managing their mono-repo workflow. Grove manages named git worktrees with tags, issue tracking, and terminal tab…