forcedotcom/sf-skills is a collection of reusable instructions that help AI coding agents build and work with Salesforce applications and platform features. Developers use it for Agentforce agents, Lightning apps, Flow, Apex, SOQL, Lightning Web Components, and related Salesforce configuration. The catalogue entries are the repository’s skills, plugins, commands, MCP servers, and agents for AI tools that support skills.
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 forcedotcom/sf-skills --skill experience-cms-brand-creategit clone --depth 1 https://github.com/forcedotcom/sf-skillsWrote 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/forcedotcom/sf-skills/experience-cms-brand-create)<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/experience-cms-brand-create"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-cms-brand-create/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/forcedotcom/sf-skills/experience-cms-brand-create"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-cms-brand-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00228 | $0.02746 |
| Opus 5.5 | $0.00091 | $0.01098 |
| Sonnet 5.5 | $0.00046 | $0.00549 |
| Haiku 4.5 | $0.00023 | $0.00275 |
Grade A, and why
experience-cms-brand-create 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 1mo 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a Brand for the Brand Toolkit
Generates a Digital Experience brand — one brand.json file — from a user's
description, and writes it where the VS Code Brand Toolkit will discover it,
so the user can immediately load, edit, and preview the brand.
A brand is a single JSON object of design tokens: colors (colorScheme), a font
catalog and base font (fontFamily / baseFontFamily), size/spacing/border
scales, per-role typography, and buttonStyleGroup definitions. Most of it is
fixed structure with internal references; you create a brand by starting from a
known-good template and changing only the leaf values (colors, font choice,
border radius, base size) plus a unique name.
The Brand Toolkit owns everything downstream: it computes derived hover colors,
compiles the --tm-* CSS, and manages the active-brand config on Save. Your job
is just the brand.json.
Related: This skill creates a new brand definition. To apply an existing brand's voice, tone, and guidelines to generated content, use the
experience-cms-brand-applyskill instead.
Reference material
Read each reference when its step arrives — don't inline everything up front:
assets/brand-template.json— the known-good full brand to clone. This is your starting point for EVERY brand. Copy it, then change leaves.references/brand-anatomy.md— which fields are literals you should edit vs references you must leave intact; thecolorSchemeguide; the font catalog and which fonts actually render in the preview; the derived-colors rule. Read before editing values.references/disk-contract.md— exactly where the file goes (.digitalExperience/brands/<slug>.brand.json), the title→slug rule, and what the toolkit generates so you don't. Read before writing the file.
Interactive flow
Walk these steps in order. When you have an interactive user, ask before assuming and confirm the design back before writing; in a single-turn, headless, or CLI run with no user to answer, state the choices you inferred and write in the same run rather than waiting for a confirmation that cannot arrive (see Step 3). Steps 1–5 create the brand file and complete the task. After they finish, an optional post-completion action — opening the Brand Toolkit to preview/edit — is described in "After completion" below; it is not part of the required workflow.
What ships with it
3 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.
- 1mo ago Changed · -1 tokens per session a09128ae7b22
- 1mo ago First seen · 198 lines · 229 tokens per session scan A 015f208c33e2
experience-cms-brand-create is a skill published in the GitHub repository forcedotcom/sf-skills (1,097 stars, last pushed today), licensed Apache-2.0. It adds 228 tokens to every session and 2,746 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-09-03.
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.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
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.