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-ui-bundle-localizegit 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-ui-bundle-localize)<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/experience-ui-bundle-localize"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-ui-bundle-localize.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Privilege Escalation · line 112 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 75 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00225 | $0.05539 |
| Opus 5 | $0.00112 | $0.02769 |
| Sonnet 5 | $0.00045 | $0.01108 |
| Haiku 4.5 | $0.00022 | $0.00554 |
Grade A, and why
experience-ui-bundle-localize 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 3d 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Localize a UI Bundle
Localize a UI Bundle: extract user-facing strings into Salesforce Custom Labels, wire a runtime i18n library over the Platform SDK backend, and verify labels across locales.
This file is the framework-neutral workflow + guardrail spine. The framework-specific detail — which i18n library, the translation call convention, the files scanned, the wiring shape, and the depth docs — lives in a per-framework reference.
The one-paragraph mental model
A UI Bundle can't use compile-time label imports the way LWC does (@salesforce/label/*
resolves inside the platform's compiler, which your standalone bundle doesn't go through).
Instead, your app fetches labels at runtime through the Salesforce GraphQL UI API and
hands them to a standard i18n library to render. The Platform SDK provides the runtime
plumbing: a detector that reads the user's language, a backend that fetches labels over
GraphQL, and a context fetch. You write two thin files — a short init that wires the SDK
pieces into your i18n library, and a manifest listing which labels your app uses — then
author the labels themselves as Salesforce Custom Labels metadata. The exact library and
call convention are framework-specific; see your framework reference.
Step 0: Route the task
| The task is… | Go to |
|---|---|
| Bundle doesn't exist yet | experience-ui-bundle-frontend-generate skill |
| Deploying the app with its labels | experience-ui-bundle-deploy skill |
Configuring site languages or sfdc_cms__languageSettings |
experience-ui-bundle-site-generate skill |
| Localizing an existing bundle | Determine the framework (below), then the workflow |
Determine the framework. It is normally already decided by the calling context — passed down by the coordinator skill that invoked this one, or stated in the user's request. Use that.
The frameworks this skill supports are exactly the reference folders under
<SKILL_DIR>/references/, each containing a localize.md (so react →
<SKILL_DIR>/references/react/localize.md). This is the single source of truth — adding a
framework means adding a reference folder, nothing here changes.
What ships with it
17 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/angular/check-i18n-wired.sh 8.9 KB runs code
- references/angular/i18n-setup.md 10 KB
- references/angular/interpolation.md 6.0 KB
- references/angular/localize.md 5.4 KB
- references/common/gotchas.md 14 KB
- references/common/label-xml.md 12 KB
- references/common/platform-sdk-i18n.md 7.6 KB
- references/common/verifying.md 15 KB
- references/react/check-i18n-wired.sh 11 KB runs code
- references/react/i18n-setup.md 11 KB
- references/react/interpolation.md 10 KB
- references/react/localize.md 3.8 KB
- scripts/check-manifest-registered.sh 8.2 KB runs code
- scripts/check-org-api-version.sh 2.1 KB runs code
- scripts/detect-bundle-type.sh 6.4 KB runs code
- scripts/detect-framework.sh 2.2 KB runs code
- scripts/tests/test-detect-bundle-type.sh 9.1 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.
- 3d ago Changed · +17 lines · +1 tokens per session 97d17d139140
- 8d ago First seen · 318 lines · 224 tokens per session scan A 9447584f8482
experience-ui-bundle-localize is a skill published in the GitHub repository forcedotcom/sf-skills (969 stars, last pushed 3d ago), licensed Apache-2.0. It adds 225 tokens to every session and 5,539 once invoked, about $0.0011 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
extract-source-sample
Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…
ss-motion
Apply a named StyleSeed motion to a component — either one of the 5 personality seeds (Spring/Silk/Snap/Float/Pulse × entrance/exit/hover/press/layout) or a distinctive keyword move from the motion library (toggle-flip, toggle-curtain, reveal-blur, pop-in, shimmer, …). Translates vibe words into framer-motion code…
json-ui
CRITICAL: Use for json-ui component rendering and development. Triggers on: json-ui, json render, component catalog, report render, HTML report, I18nString, i18n, bilingual, language switch, dual language, PaperHeader, AuthorList, Abstract, MetricsGrid, Section, Highlight, Zod schema, catalog.ts, cli.ts…
i18n
Add full internationalization (i18n) to a Next.js project using next-intl. Supports 14+ languages, SEO-friendly locale routing, hreflang sitemaps, and bulk translation. Use when the user asks to "internationalize", "add i18n", "add translations", "multi-language", "localize", "add language support", or "translate my…
i18n-date-patterns
Implements internationalization (i18n) in React applications. Covers user-facing strings, date/time handling, locale-aware formatting, ICU MessageFormat, and RTL support. Use when building multilingual UIs or formatting dates/currency.
software-localisation
Implements production-grade i18n/l10n for React, Vue, Angular, and Next.js with ICU format and RTL support. Use when setting up or debugging localisation.