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-accessibility-validategit 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-accessibility-validate)<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/experience-accessibility-validate"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-accessibility-validate/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-accessibility-validate"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-accessibility-validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
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 →
- low Excessive Agency · line 40 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00227 | $0.02431 |
| Opus 5.5 | $0.00091 | $0.00972 |
| Sonnet 5.5 | $0.00045 | $0.00486 |
| Haiku 4.5 | $0.00023 | $0.00243 |
Grade A, and why
experience-accessibility-validate 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 13d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Component Accessibility
Accessibility (a11y) patterns and remediation guidance for web components. Reference any time work involves the visible or interactive surface of a component — generating, modifying, reviewing, or styling HTML, JS, or CSS — to apply WCAG 2.2 standards.
Review Context
Conduct a review specifically focused on enhancing web accessibility, guided by the WCAG (Web Content Accessibility Guidelines).
In order to mark code as a violation, it must have a direct correlation to the WCAG rule cited such that it is a clear violation of the criteria.
Key Review Criteria:
- Focus Exclusively on Accessibility:
- Evaluate the component solely for accessibility.
- Only consider compliance with the cited WCAG Success Criteria, ignoring violations that can be attributed to other criteria.
- Avoid addressing general code style, patterns, or issues unrelated to accessibility.
- Ensure Minimum and Sufficient Accessibility:
- Identify accessibility issues that prevent the component from meeting the minimum requirements outlined by WCAG.
- Avoid suggesting enhancements that go beyond the scope of WCAG compliance unless strictly necessary.
- WAI-ARIA Usage:
- Use WAI-ARIA attributes only when strictly required to achieve accessibility that cannot otherwise be addressed with semantic HTML.
- Avoid unnecessary complexity or potential regressions caused by incorrect or overuse of ARIA attributes.
- Component Library Usage
- Assume that well-known component libraries (e.g., Salesforce Lightning, Material UI, Chakra UI) are accessible out of the box when correctly implemented. Unless they are used specifically in conflict with WCAG, library-provided components can be ignored for this review, as they are implemented in an accessible way beneath the abstraction.
- Lightning base components (
lightning-input,lightning-combobox,lightning-textarea,lightning-icon, and similar components) provide accessible labeling, ARIA, and error handling through dedicated attributes such aslabelandalternative-text. Alabelremains programmatic even withvariant="label-hidden"; do not require a sibling or wrapper<label>to target the component. Navigation, button-icon, and other self-labeling base components likewise expose supplied label text as their accessible name and treat their internal icon as decorative. Do not report a missing association merely because that implementation is hidden inside the component. - The same self-labeling logic applies to imported or custom control components in any framework (React/JSX, Angular, Vue, Web Components), not only Lightning. A capitalized or imported component tag (
<Input>,<TextField>,<Button>,<Select>,<Checkbox>,<SearchField>, and design-system wrappers from Material UI, Chakra, Radix, or an internal library) is not a bare HTML element — assume it renders its own accessible label, ARIA, and error handling beneath the abstraction (see the component-library grounding rule). When such a component is given a labeling prop —label,aria-label,aria-labelledby,title, or visible child text/children— treat it as already programmatically labeled and do not flag it for a missing<label>, a missingfor/idassociation, or a missing accessible name. Only flag when no labeling prop or text is supplied, or the supplied value is clearly empty or nonsensical. Do not demand a native<label for>for a component whose internal control you cannot see. - Resolve dynamic
id/htmlFor/forexpressions before judging a label association. When a<label htmlFor={X}>(orfor={X}) and its control'sid={X}are bound to the same expression — the same variable, prop,useId()value, or template literal (e.g. bothhtmlForandidset to the same interpolation such as${id}-email) — treat the association as matching, even though the literal string cannot be resolved at review time. A dynamicid/htmlForpair is a mismatch only when the two expressions are demonstrably different. Do not flag identical dynamicid/htmlForexpressions as unmatched or mismatched labels.
What ships with it
29 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.
- references/reviewers/sc-1-1-1-non-text-content.md 7.5 KB
- references/reviewers/sc-1-3-1-i-lists.md 7.0 KB
- references/reviewers/sc-1-3-1-ii-tables.md 12 KB
- references/reviewers/sc-1-3-1-iii-form-labels.md 6.2 KB
- references/reviewers/sc-1-3-1-iv-regions.md 5.1 KB
- references/reviewers/sc-1-3-1-v-groups.md 9.4 KB
- references/reviewers/sc-1-3-5-identify-input.md 8.7 KB
- references/reviewers/sc-1-4-3-contrast.md 12 KB
- references/reviewers/sc-2-1-1-keyboard.md 7.7 KB
- references/reviewers/sc-2-4-4-link-purpose.md 5.8 KB
- references/reviewers/sc-2-4-6-headings-labels.md 8.0 KB
- references/reviewers/sc-2-5-1-pointer-gestures.md 6.4 KB
- references/reviewers/sc-2-5-2-pointer-cancellation.md 7.5 KB
- references/reviewers/sc-2-5-3-label-in-name.md 9.9 KB
- references/reviewers/sc-2-5-7-dragging-movement.md 7.0 KB
- references/reviewers/sc-3-2-1-on-focus.md 7.1 KB
- references/reviewers/sc-3-2-2-on-input.md 8.1 KB
- references/reviewers/sc-3-3-1-error-identification.md 12 KB
- references/reviewers/sc-3-3-2-labels-instructions.md 6.3 KB
- references/reviewers/sc-3-3-3-error-suggestion.md 8.4 KB
- references/reviewers/sc-4-1-2-i-name.md 15 KB
- references/reviewers/sc-4-1-2-ii-role.md 8.7 KB
- references/reviewers/sc-4-1-2-iii-value.md 9.4 KB
- references/vision/sc-1-1-1-non-text-content.md 4.2 KB
- references/vision/sc-1-4-1-use-of-color.md 5.2 KB
- references/vision/sc-1-4-10-resize-reflow.md 1022 B
- references/vision/sc-1-4-11-non-text-contrast.md 2.8 KB
- references/vision/sc-1-4-3-contrast.md 1.5 KB
- scripts/contrast-ratio.py 5.0 KB runs code
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.
- 13d ago Changed · +3 lines a51c0acbec7e
- 1mo ago First seen · 114 lines · 227 tokens per session scan A ca01ccaf5119
experience-accessibility-validate is a skill published in the GitHub repository forcedotcom/sf-skills (1,128 stars, last pushed yesterday), licensed Apache-2.0. It adds 227 tokens to every session and 2,431 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…