/brandware
Central brand and style registry manager for the knowledgeware plugin (formerly "steez"). Houses the canonical brandbook .md files, derived token JSONs, and brand assets (logos, wordmarks) that the slideware, knowledgebase, and chartware skills resolve named brands/styles from.
$ npx -y skills add andisab/swe-marketplace --skill brandware --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/brandware
Context preview
The summary Claude sees to decide when to auto-load this skill.
Central brand and style registry manager for the knowledgeware plugin (formerly "steez"). Houses the canonical brandbook .md files, derived token JSONs, and brand assets (logos, wordmarks) that the slideware, knowledgebase, and chartware skills resolve named brands/styles from.
SKILL.md
brandware.SKILL.mdname: brandware
description: Central brand and style registry manager for the knowledgeware plugin (formerly "steez"). Houses the canonical brandbook .md files, derived token JSONs, and brand assets (logos, wordmarks) that the slideware, knowledgebase, and chartware skills resolve named brands/styles from. Load this skill when (a) a consumer skill needs to resolve a brand/style referenced by name (e.g., "use the Provectus brand", "in the AAB style"), (b) the user asks to add, import, derive, edit, or audit a brandbook, or to set or change the default brand/style, (c) the user wants to derive a style from a live website or import one from a file/Google Drive, (d) the user wants brand assets like logos gathered for a brand, or (e) the user says "brandware" or "steez". Do NOT trigger on generic mentions of branding, marketing, or visual design that aren't about applying or managing a stored visual identity.
brandware — Brand & Style Registry
One registry, many consumers. Brandbooks live here once; slideware decks, knowledgebase sites, and chartware diagrams all render from the same visual identity.
**Plugin root**: `${CLAUDE_PLUGIN_ROOT}` — two directories above this skill's folder (`../../` from here). All paths below are relative to it.
Layout
styles/ # the registry (plugin root)
├── *.md # 5 default generic styles (style-1..style-5) — marketplace-safe
├── tokens/ # derived JSON token caches for defaults
└── brands/ # brandbooks — brand-specific / proprietary (NOT in the plugin repo,
│ # except the checked-in acmecorp example)
├── DEFAULT # optional one-line marker: the registry name to use when no style is named
├── <name>.md # canonical brandbook — THE source of truth per brand
├── tokens/<name>.json # derived token cache (regenerable; never hand-edit)
└── <name>/assets/ # per-brand assets: logo-light.svg, wordmark.png, ... (never mixed across brands)
$KNOWLEDGEWARE_BRANDS_DIR/ # OPTIONAL user-owned brands directory — same layout as styles/brands/
│ # (DEFAULT marker, <name>.md, tokens/, <name>/assets/). Lives anywhere
│ # the user chooses, so it SURVIVES plugin updates. Entries here shadow
│ # plugin entries on name collision; its DEFAULT marker wins too.
scripts/ # shared tooling (plugin root)
├── load-style.js # style/brandbook → tokens (with cache)
├── list-styles.js # discover what's installed
├── derive-style.js # live website → brandbook .md (heuristic)
├── install-fonts.sh # install a brand's Google Fonts locally (see §Fonts)
└── fetch-resource.sh # Google Drive URL → local file
skills/brandware/references/
├── brandbook-spec.md # the .md format every style and brandbook follows
├── consumer-mappings.md # how each consumer skill maps tokens onto its medium
└── chart-styling.md # how to style data charts (bar/line/pie/KPI) from a brandbookRules
1. **The `.md` is canonical.** Tokens JSON is a derived cache (regenerate with `node scripts/load-style.js <name> -o styles/brands/tokens/<name>.json`). If they disagree, the `.md` wins; consumers auto-invalidate stale caches by mtime. 2. **Brands are private; styles are public.** The 5 default styles ship with the plugin. Brandbooks under `styles/brands/` are proprietary/brand-specific content, kept out of the plugin repository (`.gitignore`d) and copied in from a private source repo. Never commit a brandbook to the plugin repo. 3. **Graceful degradation.** Consumers must work when no brand is installed: slideware falls back to its five default styles, knowledgebase to its default palette, chartware to its default catalog. Brands add named identities; they are never a hard dependency. 4. **Brand shadows default.** On a name collision: `$KNOWLEDGEWARE_BRANDS_DIR/<name>.md` wins over `styles/brands/<name>.md`, which wins over `styles/<name>.md`. 5. **Prefer the user directory when it exists.** Anything inside the plugin install (`styles/brands/`) is wiped by plugin updates. When `KNOWLEDGEWARE_BRANDS_DIR` is set, write new brandbooks, token caches, assets, and the DEFAULT marker there. When it isn't set and the user imports a brand, warn them it won't survive updates and suggest setting the env var (in `~/.claude/settings.json` under `"env"`, so it's present in every session).
Resolution contract (for consumer skills)
0. **No name given?** Check the `DEFAULT` marker — a one-line file containing a registry name. `$KNOWLEDGEWARE_BRANDS_DIR/DEFAULT` wins if the env var is set; otherwise `styles/brands/DEFAULT`. If it exists and resolves (steps 1–3 below), use that identity and tell the user; if it's absent or names a missing entry, use the consumer's bundled defaults.
Given a brand/style name: 1. Check `$KNOWLEDGEWARE_BRANDS_DIR/<name>.md` (if the env var is set). 2. Check `styles/brands/<name>.md` (plugin root). 3. Check `styles/<name>.md` (the 5 defaults). 4. Fall back to the consumer's bundled defaults, and say so.
The registry scripts (`load-style.js`, `list-styles.js`, and slideware html's converter) implement this order natively — pass a name and they search all three locations.
Run `node scripts/list-styles.js` for the live inventory (`--default` / `--brands` / `--names` / `--json`). Consumers read the brandbook `.md` (or the token cache when fresh) and map it onto their medium per `references/consumer-mappings.md`:
| Consumer | What it consumes | Mapping | |---|---|---| | **slideware** (pptx format) | tokens JSON natively (`scripts/load-style.js` understands the registry) | built-in | | **slideware** (html format) | YAML-frontmatter `style.md` via its converter (`skills/slideware/html/scripts/load-style.js`) | built-in | | **knowledgebase** | palette + type → template CSS variables + Mermaid themeVariables | consumer-ma
Read more
name: brandware description: Central brand and style registry manager for the knowledgeware plugin (formerly "steez"). Houses the canonical brandbook .md files, derived token JSONs, and brand assets (logos, wordmarks) that the slideware, knowledgebase, and chartware skills resolve named brands/styles from. Load this skill when (a) a consumer skill needs to resolve a brand/style referenced by name (e.g., "use the Provectus brand", "in the AAB style"), (b) the user asks to add, import, derive, edit, or audit a brandbook, or to set or change the default brand/style, (c) the user wants to derive a style from a live website or import one from a file/Google Drive, (d) the user wants brand assets like logos gathered for a brand, or (e) the user says "brandware" or "steez". Do NOT trigger on generic mentions of branding, marketing, or visual design that aren't about applying or managing a stored visual identity.
brandware — Brand & Style Registry
One registry, many consumers. Brandbooks live here once; slideware decks, knowledgebase sites, and chartware diagrams all render from the same visual identity.
**Plugin root**: `${CLAUDE_PLUGIN_ROOT}` — two directories above this skill's folder (`../../` from here). All paths below are relative to it.
Layout
styles/ # the registry (plugin root)
├── *.md # 5 default generic styles (style-1..style-5) — marketplace-safe
├── tokens/ # derived JSON token caches for defaults
└── brands/ # brandbooks — brand-specific / proprietary (NOT in the plugin repo,
│ # except the checked-in acmecorp example)
├── DEFAULT # optional one-line marker: the registry name to use when no style is named
├── <name>.md # canonical brandbook — THE source of truth per brand
├── tokens/<name>.json # derived token cache (regenerable; never hand-edit)
└── <name>/assets/ # per-brand assets: logo-light.svg, wordmark.png, ... (never mixed across brands)
$KNOWLEDGEWARE_BRANDS_DIR/ # OPTIONAL user-owned brands directory — same layout as styles/brands/
│ # (DEFAULT marker, <name>.md, tokens/, <name>/assets/). Lives anywhere
│ # the user chooses, so it SURVIVES plugin updates. Entries here shadow
│ # plugin entries on name collision; its DEFAULT marker wins too.
scripts/ # shared tooling (plugin root)
├── load-style.js # style/brandbook → tokens (with cache)
├── list-styles.js # discover what's installed
├── derive-style.js # live website → brandbook .md (heuristic)
├── install-fonts.sh # install a brand's Google Fonts locally (see §Fonts)
└── fetch-resource.sh # Google Drive URL → local file
skills/brandware/references/
├── brandbook-spec.md # the .md format every style and brandbook follows
├── consumer-mappings.md # how each consumer skill maps tokens onto its medium
└── chart-styling.md # how to style data charts (bar/line/pie/KPI) from a brandbookRules
1. **The `.md` is canonical.** Tokens JSON is a derived cache (regenerate with `node scripts/load-style.js <name> -o styles/brands/tokens/<name>.json`). If they disagree, the `.md` wins; consumers auto-invalidate stale caches by mtime. 2. **Brands are private; styles are public.** The 5 default styles ship with the plugin. Brandbooks under `styles/brands/` are proprietary/brand-specific content, kept out of the plugin repository (`.gitignore`d) and copied in from a private source repo. Never commit a brandbook to the plugin repo. 3. **Graceful degradation.** Consumers must work when no brand is installed: slideware falls back to its five default styles, knowledgebase to its default palette, chartware to its default catalog. Brands add named identities; they are never a hard dependency. 4. **Brand shadows default.** On a name collision: `$KNOWLEDGEWARE_BRANDS_DIR/<name>.md` wins over `styles/brands/<name>.md`, which wins over `styles/<name>.md`. 5. **Prefer the user directory when it exists.** Anything inside the plugin install (`styles/brands/`) is wiped by plugin updates. When `KNOWLEDGEWARE_BRANDS_DIR` is set, write new brandbooks, token caches, assets, and the DEFAULT marker there. When it isn't set and the user imports a brand, warn them it won't survive updates and suggest setting the env var (in `~/.claude/settings.json` under `"env"`, so it's present in every session).
Resolution contract (for consumer skills)
0. **No name given?** Check the `DEFAULT` marker — a one-line file containing a registry name. `$KNOWLEDGEWARE_BRANDS_DIR/DEFAULT` wins if the env var is set; otherwise `styles/brands/DEFAULT`. If it exists and resolves (steps 1–3 below), use that identity and tell the user; if it's absent or names a missing entry, use the consumer's bundled defaults.
Given a brand/style name: 1. Check `$KNOWLEDGEWARE_BRANDS_DIR/<name>.md` (if the env var is set). 2. Check `styles/brands/<name>.md` (plugin root). 3. Check `styles/<name>.md` (the 5 defaults). 4. Fall back to the consumer's bundled defaults, and say so.
The registry scripts (`load-style.js`, `list-styles.js`, and slideware html's converter) implement this order natively — pass a name and they search all three locations.
Run `node scripts/list-styles.js` for the live inventory (`--default` / `--brands` / `--names` / `--json`). Consumers read the brandbook `.md` (or the token cache when fresh) and map it onto their medium per `references/consumer-mappings.md`:
| Consumer | What it consumes | Mapping | |---|---|---| | **slideware** (pptx format) | tokens JSON natively (`scripts/load-style.js` understands the registry) | built-in | | **slideware** (html format) | YAML-frontmatter `style.md` via its converter (`skills/slideware/html/scripts/load-style.js`) | built-in | | **knowledgebase** | palette + type → template CSS variables + Mermaid themeVariables | consumer-ma
Showing the first part of this file.
A curated Claude Code plugin marketplace for practical, everyday usage in software engineering — 13 plugins, 53 specialist agents, 14 skills, 3 commands. A few opinionated choices that set it apart from larger awesome-style lists: Curated, not exhaustive.
Repo: andisab/swe-marketplace
Other skills on swe-marketplace.
- /dispatch
Shared multi-model CLI dispatch infrastructure for the adv plugin. Houses dispatch.sh, preflight.sh, run-phase.sh, scope.sh, and reviewer prompt templates used by the adv-review agent and adv-* commands.
Open skill - /agent-dev
Use this skill when creating or refining Claude Code sub-agent definitions. Helps design specialized AI assistants with proper YAML frontmatter, system prompts, tool access, and example-driven descriptions. Automatically invoked when user requests "create an agent", "design a
Open skill - /command-dev
Use this skill when creating or refining custom Claude Code slash commands. Slash commands are user-invoked reusable prompts that can accept arguments, reference files, and execute bash operations. Helps design command syntax, argument handling, file references, bash execution,
Open skill - /hook-dev
Use this skill when creating or refining Claude Code hooks. Hooks are shell commands that execute at specific lifecycle events (tool use, prompt submit, notifications, session events). Helps design event handlers for notifications, formatting, logging, feedback, and permission
Open skill - /mcp-server-dev
Create MCP servers — multi-tool services exposed via Model Context Protocol. Use this skill whenever users mention MCP servers, building servers, server scaffolding, tool registration, or want to package tools for distribution via uvx or npx. Also use when the conversation
Open skill - /mcp-tool-dev
Create MCP tools — individual tool functions exposed via Model Context Protocol. Use this skill whenever users mention MCP tools, tool handlers, tool functions, tool definitions, or want to add capabilities to an MCP server. Also use when the conversation involves designing tool
Open skill

