brand-voice
Brand Voice
Govern BRAND-VOICE.md — the canonical writing voice document for a brand. Two layers: YAML frontmatter (machine-readable normative rules consumed by writing skills) plus eleven prose sections (human-readable rationale). Same split as DESIGN.md and the same design-system skill pattern: a canonical file at the project root, CLI-style subcommands for the lifecycle.
Additional context from the user: $ARGUMENTS
Subcommand routing
Parse the first positional token of $ARGUMENTS. If it matches a verb below, load the referenced file and follow its workflow. Otherwise fall through to the default workflow at the end of this document.
| First token | Mode | Reference |
|---|---|---|
extract |
Ingest sources, synthesise canonical voice doc, write to ./BRAND-VOICE.md |
steps/extract.md |
update |
Refresh an existing voice doc from new sources, preserve manual sections | steps/update.md |
diff |
Show what changed between two versions of the voice doc (git-aware) | steps/diff.md |
validate (aliases: lint, check) |
Lint a voice doc against canonical-format.md — verdict + errors + warnings + fix suggestions, CI-friendly exit codes |
steps/validate.md |
show |
Print the flat list of testable rules from the voice doc | steps/show.md |
| (none) | See Default workflow below | (this file) |
More from coroboros/agent-skills
markitdown
Convert any document to Markdown with Microsoft's `markitdown` CLI — PDF, Word, Excel, PowerPoint, HTML, CSV, JSON, XML, ZIP, EPub, images (OCR/EXIF), audio (transcription), and YouTube URLs. Use whenever the user wants to extract text from a binary document, transcribe audio, OCR an image, scrape a YouTube transcript, or pre-process a file for an LLM context window — even when they just say "convert this pdf", "what's in this docx", "transcribe this mp3", or "get the text out of this".
19design-system
Govern the DESIGN.md — Google's open standard for design tokens (YAML frontmatter + eight prose sections). Auto-activates during UI edits to enforce token-only sourcing for colors, typography, spacing, and corner radius. Also exposes six CLI-backed subcommands — audit (lint + fix proposals), diff (regression check), export (Tailwind / DTCG), spec (canonical spec emission), migrate (port from legacy Stitch format), init (minimal scaffold). When a UI/UX change is requested, DESIGN.md is updated first, audited, then code propagates.
4award-design
Build award-winning websites (Awwwards SOTD 7.5+, FWA, CSSDA). Recommends the best design archetype for the brief, calibrates atmosphere, and produces a complete DESIGN.md. Applies anti-AI-slop rules and targets real judging criteria. Use when building landing pages, portfolios, product sites, or any web interface that needs to look exceptional — not for dashboards or internal tools.
4write-clear-readme
Author, audit, or polish a project README — clarity, structure (Pattern A grouped collapse / Pattern B per-entry collapse), wording concision, anchor integrity. Reads the repo first, proposes diffs, applies on approval.
4humanize-en
Strip AI writing tells from English prose — em-dash overuse, rule of three, negative parallelisms, AI vocabulary (delve, tapestry, crucial, pivotal, underscore, showcase), vague attributions, promotional tone, conjunctive padding (moreover, furthermore, indeed), hedging, signposting, chatbot artifacts. Preserves meaning, structure, code blocks, links, anchors, and frontmatter — rewrites only the flagged phrasing. Operates on inline text or a prose file path. Optionally loads a `BRAND-VOICE.md` via `-f` (produced by `/brand-voice`) to apply brand-specific rules on top of the universal patterns. Based on Wikipedia's Signs of AI writing (canonical taxonomy) with pattern extensions and the voice-calibration approach from github.com/blader/humanizer.
3fix-grammar
Fix grammar, spelling, and typos in files while preserving formatting, meaning, and technical terms. Corrections only — no rephrasing, no style improvements, no translation.
3