Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Pika-Labs/Pika-Plugins --skill build-a-brandgit clone --depth 1 https://github.com/Pika-Labs/Pika-PluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pika-labs/pika-plugins/build-a-brand)<a href="https://agentmods.dev/skills/pika-labs/pika-plugins/build-a-brand"><img src="https://agentmods.dev/badge/skills/pika-labs/pika-plugins/build-a-brand/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pika-labs/pika-plugins/build-a-brand"><img src="https://agentmods.dev/badge/skills/pika-labs/pika-plugins/build-a-brand.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 68 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00192 | $0.14177 |
| Opus 5 | $0.00096 | $0.07089 |
| Sonnet 5 | $0.00038 | $0.02835 |
| Haiku 4.5 | $0.00019 | $0.01418 |
Grade A, and why
build-a-brand scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 749 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a Brand
Tools below are Pika MCP tools, named bare — call each under whatever prefix your session exposes for the Pika MCP.
Take any input — an idea, a website, a list of reference brands, product photos, or an existing brand to refresh — and produce a usable brand identity.
This is a standalone brand-building workflow focused on strategy, identity, design, and copy. The default output is a quick brand deliverable that can be finished in minutes. The full 14-16-page brand guidelines PDF is still available, but only when the user explicitly asks for full depth or chooses to go deeper after the quick pass.
Reference files
Load these only when the relevant phase starts:
references/brand-directions.md— strategy angle structure and differentiated positioning boards.references/brand-identity.md— logo pipeline, symbol rules, concept lanes, and board-copy budgets.references/brand-guidelines.md— full guidelines layout, render contract, page structure, and QA rules.references/brand-md-template.md— required machine-readablebrand.mdstructure.
Execution Model — Local First, Cloud Only Where Needed
This skill is local-first. Keep deterministic production work on the user's machine:
- Local: workspace setup, downloaded fonts, generated image files after download, image compression, transparent-background cleanup, 16x16 favicon tests, HTML/CSS page builds, PDF rendering, PNG/JPG QA screenshots, logo asset assembly, token/prompt files, and final zip packaging.
- Cloud: paid generation only (
gpt-image-2for symbols, mood images, photography, illustration, and ambient textures) and URL/source research when the brief requires it.
Do not use a cloud PDF renderer or upload PDFs by default. Save quick PDFs, board PDFs, guidelines PDFs, and brand-kit zips to ~/Desktop on Mac, or the project working directory when Desktop is unavailable. Only upload/share via CDN if the user explicitly asks for a hosted file.
PDF asset hygiene: never embed full-size gpt-image-2 PNGs directly in board or guidelines PDFs. This previously produced huge PDFs and ASSET_FETCH_TIMEOUT failures when renderers tried to fetch multi-MB CDN images. Download every generated image, down-raster/downsample it to the slot size, and save a local JPEG target of about 85-180KB before using it in render HTML. Keep transparent PNG only for logo/symbol source assets and favicon/logo export, not for photographic page imagery. Never put a CSS filter:/backdrop-filter: (warm grade, sepia, saturate, brightness, blur) on a photo or background-image in the render HTML — it forces Chromium to rasterize that element to a full-resolution lossless bitmap in the PDF, which cancels out the JPEG step above and re-bloats the file (a warm-graded mood-board page alone took a deck to 70 MB). Bake any color grade into the JPEG itself (in the gpt-image-2 prompt or when you img.save(..., 'JPEG', ...)); drop-shadow() on a transparent logo PNG is the only filter that's safe.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 749 lines · 192 tokens per session scan A 26a2a415073d
build-a-brand is a skill published in the GitHub repository Pika-Labs/Pika-Plugins (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 192 tokens to every session and 14,177 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.