Define Loop
yc-software/qm
Define a Loop — a durable scaffold that works a queue of recurring tasks autonomously (Sentry issues, Front tickets, small perf PRs) with its outputs held for human review.
Define a brand's visual system, core assets and representative applications in Brand Studio.
MITAuto-check passed
Install Pneuma Brand
$ npx skills add pandazki/pneuma-skills --skill pneuma-brand -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pandazki/pneuma-skills pneuma-brand --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/pandazki/pneuma-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/modes/brand/skill .claude/skills/pneuma-brand && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "pneuma-brand" agent skill from https://github.com/pandazki/pneuma-skills/tree/main/modes/brand/skill into .claude/skills/pneuma-brand/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pneuma-brand", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/pandazki/pneuma-skills/tree/main/modes/brand/skillType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add pandazki/pneuma-skills --skill pneuma-brand -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pandazki/pneuma-skills pneuma-brand --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pandazki/pneuma-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/modes/brand/skill .agents/skills/pneuma-brand && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pneuma-brand" agent skill from https://github.com/pandazki/pneuma-skills/tree/main/modes/brand/skill into .agents/skills/pneuma-brand/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pneuma-brand", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pandazki/pneuma-skills --skill pneuma-brand -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pandazki/pneuma-skills pneuma-brand --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pandazki/pneuma-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/modes/brand/skill .cursor/skills/pneuma-brand && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "pneuma-brand" agent skill from https://github.com/pandazki/pneuma-skills/tree/main/modes/brand/skill into .cursor/skills/pneuma-brand/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pneuma-brand", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/pandazki/pneuma-skills.git --path modes/brand/skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add pandazki/pneuma-skills --skill pneuma-brand -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pandazki/pneuma-skills pneuma-brand --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pandazki/pneuma-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/modes/brand/skill .gemini/skills/pneuma-brand && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "pneuma-brand" agent skill from https://github.com/pandazki/pneuma-skills/tree/main/modes/brand/skill into .gemini/skills/pneuma-brand/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pneuma-brand", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install pandazki/pneuma-skills pneuma-brandInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add pandazki/pneuma-skills --skill pneuma-brand -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pandazki/pneuma-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/modes/brand/skill .github/skills/pneuma-brand && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "pneuma-brand" agent skill from https://github.com/pandazki/pneuma-skills/tree/main/modes/brand/skill into .github/skills/pneuma-brand/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pneuma-brand", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pandazki/pneuma-skills --skill pneuma-brand -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pandazki/pneuma-skills pneuma-brand --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pandazki/pneuma-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/modes/brand/skill .opencode/skills/pneuma-brand && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "pneuma-brand" agent skill from https://github.com/pandazki/pneuma-skills/tree/main/modes/brand/skill into .opencode/skills/pneuma-brand/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pneuma-brand", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
pneuma-brand- GitHub stars
- 161
- Token cost
- ~1.7k tokens
- SKILL.md length
- 911 words
- Files
- 8 (incl. scripts, references)
- Skills in repo
- 30
- Repo updated
- First seen
- Licence
- MIT
At a glance
Define a brand's visual system, core assets and representative applications in Brand Studio.
- Works in 8 steps: Read the project, current references and… → Write the brief, application contexts… → Develop a coherent identity: mark,… → …
- Reviewing a brand that downstream makers will adapt
- SKILL.md covers Scene, Viewer contract, Core rules and Workflow, plus 2 more sections
- Runs TypeScript scripts from its folder; calls bun
What it does
Pneuma Brand is an agent skill from pandazki/pneuma-skills. Define a brand's visual system, core assets and representative applications in Brand Studio. Use when creating, extending or reviewing a brand that downstream makers will adapt.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts and reference files (for example `references/brand-development.md`, `references/image-workflow.md` and `references/project-format.md`).
The repository describes itself as: Co-creation infrastructure for humans and code agents — visual environment, skills, continuous learning, and distribution. The licence is MIT.
When your agent uses it
- Reviewing a brand that downstream makers will adapt
Example prompts
- “/pneuma-brand”
Requirements
- Node.js
Workflow steps
8 steps, taken from the first numbered list in SKILL.md.
- Read the project, current references and existing user decisions. Ask only for
- Write the brief, application contexts and initial work plan into brand.json so
- Develop a coherent identity: mark, palette roles, typography, graphic language,
- Create core reusable assets and representative applications. For each context,
- Review images at full size and the assembled brand book. Check legibility,
- Validate with bun "/scripts/check.ts" .
- Prepare handoff: brand.json, original core assets, examples, and their guidance.
- Point to the work with a viewer locator, and distinguish the brand system delivered
What it can do on your machine
Read from SKILL.md and the folder at commit 0023d3c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 4 files in scripts/ (TypeScript), which the agent can run.
Shell commands in SKILL.md call:
bun
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Pneuma Brand loads about 1.7k tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 48 tokens; SKILL.md has 911 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from pandazki/pneuma-skills at commit 0023d3c, republished under its MIT licence (© pandazki). 911 words, ~1,728 tokens.
Download SKILL.mdSave it as
.claude/skills/pneuma-brand/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- pneuma-brand
- description
- Define a brand's visual system, core assets and representative applications in Brand Studio. Use when creating, extending or reviewing a brand that downstream makers will adapt.
Brand Studio
Scene
You and the user are designing a brand. The brand itself is the deliverable: a recognizable point of view, visual rules, core assets, and examples showing how the system behaves in different contexts. The user sees these together in the workbench. Downstream designers and application builders use this system to produce their own materials. A polished example is evidence of a direction, not a promise that every production asset or application has already been built.
Viewer contract
Each project lives in a directory with brand.json and local artifacts. The
viewer groups work into references, identity, core assets and application
examples. Application-context filters answer “where will this brand live?”
Inspecting a work exposes its references, generation brief and optional image
regions. Compare opens the first reference alongside the selected work.
ViewerAddress vocabulary
| Key | Kind | Meaning |
|---|---|---|
contentSet | Framework reserved | Project directory prefix |
item | Coarse | Stable work ID from brand.json, independent of order or filename |
region | Optional fine | ID of a declared normalized image rectangle |
Use navigate-to with { address: { contentSet: "morrow", item: "brand-world" } }.
Use compare for a work with references. Reuse the address in a viewer locator
or framework capture. A region highlights that portion of the image; capture
still shows the work with the highlighted region, not a cropped asset.
File changes update the viewer. The viewer does not generate images or write
brand decisions itself. Read-only sharing hides agent controls.
Core rules
- Define the audience, promise, personality and intended application contexts before expanding the visual language. A mascot is optional, not a brand prerequisite.
- Separate invariants from flexibility: wordmark geometry, character proportions, palette roles, type hierarchy, composition, photography, voice, and usage limits.
- Explain what an example demonstrates and what the downstream maker must adapt. Do not default to building an App, business website, complete campaign or print run.
- Read actual reference images. Record the role of each reference; a layout example is not permission to replace the brand's identity with that reference's identity.
- Use existing image generation/editing tools for raster art. Prefer a native image tool when available; otherwise use the installed shared scripts when configured. Keep consistent anchors for character identity. Do not redraw a detailed mascot with approximate CSS geometry in downstream examples.
- Keep core source assets separate from their application mockups. A character on a poster is not a transparent reusable cutout; a mockup is not a print-ready dieline.
- Preserve versions when exploring. Stable IDs and
referenceIdsretain lineage. Never overwrite a source reference just to make a comparison look successful. - Only mark work
readyafter the file exists and has been inspected.generatingmeans a real request is in progress.failedrecords a useful error. A timeout leaves remote completion uncertain; do not blindly repeat a paid request. - Paths are relative to the project. Keep assets local and do not depend on expiring URLs, absolute filesystem paths, or undocumented external rendering services.
Show full SKILL.md (433 more words)Show less
Workflow
- Read the project, current references and existing user decisions. Ask only for missing facts that would change the brand: audience, promise, character, use scenes.
- Write the brief, application contexts and initial work plan into
brand.jsonso the user can see the direction before every asset is finished. - Develop a coherent identity: mark, palette roles, typography, graphic language, image treatment, and optional character rules. Explore meaningful alternatives; explain their tradeoffs, and preserve the chosen rules.
- Create core reusable assets and representative applications. For each context, state what stays fixed, what may change, and what its example demonstrates. App onboarding, packaging, social posts and retail can be examples of one brand; none requires implementing a complete product inside this mode.
- Review images at full size and the assembled brand book. Check legibility, consistency, factual copy and whether another maker could apply the rules. Use capture or browser evidence; text-only inspection cannot verify visual fidelity.
- Validate with
bun "<SKILL_DIR>/scripts/check.ts" <project-directory>. On a fresh installed skill, first runbun install --cwd "<SKILL_DIR>/scripts"to install the declared validation dependency. Substitute the actual skill path. - Prepare handoff:
brand.json, original core assets, examples, and their guidance. Runbun "<SKILL_DIR>/scripts/export-site.ts" <project-directory>to produce a self-containedbrand-book.htmlwith an A4 landscape print layout. PDF is the primary reading deliverable: open Export book → Print / Save PDF and choose Save as PDF in the browser dialog, with background graphics enabled and browser headers/footers disabled. The book includes its own page numbers. Inspect the actual PDF pages for clipping and readable images before handoff. The shared WebCraft export workbench also offers Screenshot PNG, HTML, a source ZIP, viewport previews, and Vercel / Cloudflare Pages deployment. PNG captures the full book; PDF preserves selectable text and page breaks. Both wait for images and fonts; resolve any missing assets before exporting. Refresh the book after changes; it is a generated deliverable, not another source of identity rules. Deliver original core assets alongside the PDF so downstream makers can reuse them without extracting images from a page. - Point to the work with a viewer locator, and distinguish the brand system delivered from the downstream production work still needed.
Commands
| ID | Response |
|---|---|
define | Resolve the brand promise and use contexts; update brief and rules. |
generate | Develop identity or core assets from the selected references. |
apply | Produce a representative application that tests the brand in a named context. |
audit | Review identity consistency, asset reuse and clarity of downstream guidance. |
References
| When | Read |
|---|---|
| Authoring or repairing project data | Project format |
| Planning identity and applications | Brand development |
| Generating core assets and examples | Image workflow |
© pandazki, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 7 other files (scripts, references) in modes/brand/skill of pandazki/pneuma-skills.
- SKILL.md
- references/brand-development.md
- references/image-workflow.md
- references/project-format.md
- scripts/check.ts
- scripts/export-site.ts
- scripts/model.ts
- scripts/package.json
Open the folder on GitHubat commit 0023d3c
Compare with similar skills
Pneuma Brand next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Pneuma Brand this skillpandazki/pneuma-skills | 161 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Define Loopyc-software/qm | 15k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Deploying Software Defined Perimetermukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Flow Definenyldn/claude-octopus | 4.2k | 1 repos | ~6.5k | Automated safety check: Pass | MIT | |
| Define My Content Pillarssickn33/agentic-awesome-skills | 47k | 1 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Define Feature Flagmacro-inc/macro | 4.6k | — | ~780 | Automated safety check: Pass | AGPL-3.0 |
Similar skills
Deploying Software Defined Perimeter
mukul975/Anthropic-Cybersecurity-Skills
Deploys a Software-Defined Perimeter per the CSA v2.0 specification, configuring Single Packet Authorization, mutual TLS, and SDP controller/gateway components to enforce zero trust network access.
Flow Define
nyldn/claude-octopus
Multi-AI requirements scoping using available external providers (Double Diamond Define phase).
Define My Content Pillars
sickn33/agentic-awesome-skills
Find the three to five subjects someone can post about repeatedly, from what they have published and know first-hand.
Define Feature Flag
macro-inc/macro
Define a frontend feature flag with defineFlag and wire its readers.
Define Errors
EpicenterHQ/epicenter
defineErrors from wellcrafted: variant factories, extractErrorMessage, InferErrors/InferError, call site patterns.
More from pandazki/pneuma-skills
All 30 skills in this repoPneuma Bansho
pandazki/pneuma-skills
Explain something by writing it on a board. An agent skill from pandazki/pneuma-skills.
Pneuma Clipcraft
pandazki/pneuma-skills
AI-orchestrated video production on @pneuma-craft. An agent skill from pandazki/pneuma-skills.
Pneuma Lucid
pandazki/pneuma-skills
Pneuma Lucid Mode workspace guidelines. An agent skill from pandazki/pneuma-skills.
Pneuma Plotwise
pandazki/pneuma-skills
Pneuma Plotwise workspace guidelines. An agent skill from pandazki/pneuma-skills.
Pneuma Sprite
pandazki/pneuma-skills
Pneuma Sprite Mode workspace guidelines. An agent skill from pandazki/pneuma-skills.
Pneuma Webcraft
pandazki/pneuma-skills
Pneuma WebCraft Mode workspace guidelines with Impeccable.style design intelligence.
Questions about Pneuma Brand
What does Pneuma Brand do?
Define a brand's visual system, core assets and representative applications in Brand Studio. Pneuma Brand is an agent skill from pandazki/pneuma-skills. Define a brand's visual system, core assets and representative applications in Brand Studio.
When should I use Pneuma Brand?
Pneuma Brand fits situations like: reviewing a brand that downstream makers will adapt.
How do I install Pneuma Brand in Claude Code?
Run `npx skills add pandazki/pneuma-skills --skill pneuma-brand -a claude-code`. Or copy the skill folder (modes/brand/skill in pandazki/pneuma-skills) into .claude/skills/pneuma-brand in your project. Claude Code loads it when a task matches its description.
How do I install Pneuma Brand in Codex?
Run `npx skills add pandazki/pneuma-skills --skill pneuma-brand -a codex`. Or copy the skill folder (modes/brand/skill in pandazki/pneuma-skills) into .agents/skills/pneuma-brand in your project. Codex loads it when a task matches its description.
Can I use Pneuma Brand in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pandazki/pneuma-skills --skill pneuma-brand -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pneuma-brand, .gemini/skills/pneuma-brand, .github/skills/pneuma-brand and .opencode/skills/pneuma-brand in your project.
What does Pneuma Brand need to run?
Going by SKILL.md and its folder, Pneuma Brand needs TypeScript for the scripts in its folder and the command-line tools its instructions call (bun). Our summary lists: Node.js.
Does Pneuma Brand access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Pneuma Brand safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Pneuma Brand use?
Pneuma Brand is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Pneuma Brand use?
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.
What are the alternatives to Pneuma Brand?
Skills that share tags, products or a category with Pneuma Brand: Define Loop (yc-software/qm, 15k stars), Deploying Software Defined Perimeter (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Flow Define (nyldn/claude-octopus, 4.2k stars) and Define My Content Pillars (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Pneuma Brand?
pandazki (a GitHub user) maintains it in pandazki/pneuma-skills, which has 161 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 9, 2026.
Source: pandazki/pneuma-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.