Vox Calibre, the Upland house writing style for claude.ai chat, which has no output styles. The rules load as a skill whenever you ask for writing. In Claude Code, install vox-calibre instead.
1 skill
Writing standards for documents, in four skills that share one house language. technical-doc-writer writes runbooks, READMEs and architecture docs that a non-engineer can read and an on-call engineer can act on. primer-writer turns someone else's long engineering doc into a short plain-language primer that traces every claim to its source. executive-brief-writer writes phase-gate charters, decision briefs, proposals and readouts where every figure carries its source and every risk its handling. adr-writer writes and retrofits architecture decision records: YAML front matter, a summary of the problem, options, recommendation and decision needed, then the engineering detail.
Plugin doc-standards from marketplace mgstegmaier in mgstegmaier/claude-plugins. Commands read from the repo's manifest — 10 days ago.
adr-writerWrite, update, or retrofit an architecture decision record (ADR) in the house shape - YAML front matter, a plain-language summary a non-engineer can act on (the problem, the options and what each costs, the recommendation, the decision needed and who owes it), then the full engineering detail below.
executive-brief-writerHouse standard for writing to executives: project charters in a phase-gate row format, decision briefs, proposals, funding asks, pilot readouts, and phase-gate readouts. Use whenever the audience is a sponsor or above and the document asks someone to decide something. Triggers on "write a charter",
primer-writerTurn a long engineering doc, design doc, or white paper (usually written by someone else) into a short primer that executives and non-technical teammates can read. The primer leads with the point in plain language, uses a diagram, table, or chart only where the source earns one, traces every claim t
technical-doc-writerStandards for technical documentation — pipelines, runbooks, READMEs, architecture docs, procedure/system docs. Use whenever writing or substantially updating technical documentation ("document this", "write a runbook", "update the docs", creating *_DOCUMENTATION.md), or when reviewing docs for qual
Vox Calibre, the Upland house writing style for claude.ai chat, which has no output styles. The rules load as a skill whenever you ask for writing. In Claude Code, install vox-calibre instead.
1 skill
A mod that asks before a send re-writes a cold prompt cache: a dialog shows the estimated cost with Proceed and Start new session buttons, and Start new session runs /clear and puts your prompt back. Adapted from Karan Bansal's cache-tax (MIT), without keepwarm. Needs Claude Code 2.1.287 or later.
A mod for the Claude desktop app and the terminal: a card above the prompt showing how full the context window is, what the session has cost at API rates, and what fills it (system prompt, tools, MCP, memory, skills, and the conversation split into prompts, injected context, replies and tool results), in Anthropic's palette. Click to expand the legend; hover a row for what it holds and what fills it most. Needs Claude Code 2.1.288 or later.
A mod for the Claude desktop app and the terminal: a /tether pane with folding sections for a working-on note, the context bar, the assumptions Claude is making (Approve or Reject each), work it put off, decisions and needs-you tasks (everything Claude is waiting on you for), subagents and cost. Buttons draft into the prompt box; nothing sends until you press Enter. Needs Claude Code 2.1.289 or later. Adapted from ClariSortAi's Terminal Desk (MIT).
Vox Calibre, the Upland house writing style for Claude Code: plain language with a human voice. It is the output style for every reply while the plugin is enabled. For claude.ai chat, install vox-calibre-chat instead.
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.