dotfiles

Use when drafting or editing prose or copy, including reports, research write-ups, guidance, documentation, READMEs, emails, announcements, summaries, blog posts, marketing copy, product copy, or any text meant to be read. Triggers whenever the user asks to draft, write, rewrite, edit, or polish copy. Applies GOV.UK and GDS house style, favoring plain English, active voice, front-loaded content, sentence case, and no bold or italics for emphasis. Balances that house style against ASD-STE100 Simplified Technical English, then runs Orwell's rules from 'Politics and the English Language' over the result. Simplified Technical English stays on for all prose unless the author explicitly asks for it to be switched off, and the agent announces that it is in use and offers to switch it off. Use it to compose new prose and to keep editing, not to audit finished text.

Use when drafting or editing prose or copy, including reports, research write-ups, guidance, documentation, READMEs, emails, announcements, summaries, blog posts, marketing copy, product copy, or any text meant to be read. Triggers whenever the user asks to draft, write, rewrite, edit, or polish copy. Applies GOV.UK and GDS house style, favoring plain English, active voice, front-loaded content, sentence case, and no bold or italics for emphasis. Balances that house style against ASD-STE100 Simplified Technical English, then runs Orwell's rules from 'Politics and the English Language' over the result. Simplified Technical English stays on for all prose unless the author explicitly asks for it to be switched off, and the agent announces that it is in use and offers to switch it off. Use it to compose new prose and to keep editing, not to audit finished text.

This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.

Respond to code review comments point by point, quoting each reviewer point verbatim and answering directly beneath it.

Use when moving local sessions between Claude Code and Codex, converting Claude Code JSONL into Codex rollout format, converting Codex rollout JSONL into Claude scrollback, or debugging cross-agent resume state.

Use when moving local sessions between Codex and Claude Code, converting Codex rollout JSONL into Claude scrollback, converting Claude Code JSONL into Codex rollout format, or debugging cross-agent resume state.

Operate remote hosts over SSH through the ssh-mcp server, driving a box like a person at a terminal instead of firing blind one-off commands.

Use when a task involves SSH or a remote host, including remote commands, interactive shells, sudo over SSH, tailing logs, deployments, scp or rsync file transfer, and port forwards or tunnels.

Import a claude.ai / Claude Desktop conversation as a resumable Claude Code session transcript.

Ideate and critique data visualizations using Edward Tufte's principles, blended with the user's personal plotting preferences.

Use when designing or critiquing charts, dashboards, reports, or other data visualizations; choosing between visualization approaches; reducing chartjunk; improving data-ink ratio; or planning small multiples and high-density displays.

Ask Claude to audit Codex's work. Use when the user wants a second opinion, Claude audit, independent review, or a check of Codex changes.

Search the web using Exa.

Search and fetch current web content using the configured Exa MCP server. Use when the user asks to search the web, look something up, verify current information, find sources, crawl a page, or use Exa specifically.

Write comprehensive, principled tests for code. Use when the user asks to write tests, add tests, create a test suite, test a file/function/module, or improve coverage.

Get Codex to audit Claude's mistakes.

Build a Claude Code plugin using best practices.

Snapshot the session into beads memories so the next agent (Claude Code, Codex, or any bd-aware tool) picks it up automatically via bd prime.

Snapshot the session into beads memories so the next Codex, Claude Code, or bd-aware agent picks it up automatically via bd prime. Use when the user asks to hand off, wrap up, persist session state, or summarize work for the next agent.

Write comprehensive, principled tests for code.