Hermes Agent Skill Authoring
NousResearch/hermes-agent
Author in-repo SKILL.md files: frontmatter and structure. An agent skill from NousResearch/hermes-agent.
A skill your agent uses to author a complete HXL WidgetBundle (UEM body + schema.json + -meta.xml).
$ npx skills add forcedotcom/sf-skills --skill platform-widget-generate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install forcedotcom/sf-skills platform-widget-generate --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/forcedotcom/sf-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/platform-widget-generate .claude/skills/platform-widget-generate && 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 "platform-widget-generate" agent skill from https://github.com/forcedotcom/sf-skills/tree/main/skills/platform-widget-generate into .claude/skills/platform-widget-generate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "platform-widget-generate", 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/forcedotcom/sf-skills/tree/main/skills/platform-widget-generateType 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 forcedotcom/sf-skills --skill platform-widget-generate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install forcedotcom/sf-skills platform-widget-generate --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/forcedotcom/sf-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/platform-widget-generate .agents/skills/platform-widget-generate && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "platform-widget-generate" agent skill from https://github.com/forcedotcom/sf-skills/tree/main/skills/platform-widget-generate into .agents/skills/platform-widget-generate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "platform-widget-generate", 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 forcedotcom/sf-skills --skill platform-widget-generate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install forcedotcom/sf-skills platform-widget-generate --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/forcedotcom/sf-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/platform-widget-generate .cursor/skills/platform-widget-generate && 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 "platform-widget-generate" agent skill from https://github.com/forcedotcom/sf-skills/tree/main/skills/platform-widget-generate into .cursor/skills/platform-widget-generate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "platform-widget-generate", 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/forcedotcom/sf-skills.git --path skills/platform-widget-generate--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 forcedotcom/sf-skills --skill platform-widget-generate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install forcedotcom/sf-skills platform-widget-generate --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/forcedotcom/sf-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/platform-widget-generate .gemini/skills/platform-widget-generate && 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 "platform-widget-generate" agent skill from https://github.com/forcedotcom/sf-skills/tree/main/skills/platform-widget-generate into .gemini/skills/platform-widget-generate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "platform-widget-generate", 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 forcedotcom/sf-skills platform-widget-generateInstalls 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 forcedotcom/sf-skills --skill platform-widget-generate -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/forcedotcom/sf-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/platform-widget-generate .github/skills/platform-widget-generate && 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 "platform-widget-generate" agent skill from https://github.com/forcedotcom/sf-skills/tree/main/skills/platform-widget-generate into .github/skills/platform-widget-generate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "platform-widget-generate", 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 forcedotcom/sf-skills --skill platform-widget-generate -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install forcedotcom/sf-skills platform-widget-generate --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/forcedotcom/sf-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/platform-widget-generate .opencode/skills/platform-widget-generate && 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 "platform-widget-generate" agent skill from https://github.com/forcedotcom/sf-skills/tree/main/skills/platform-widget-generate into .opencode/skills/platform-widget-generate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "platform-widget-generate", 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.
platform-widget-generateA skill your agent uses to author a complete HXL WidgetBundle (UEM body + schema.json + -meta.xml).
Platform Widget Generate is an agent skill from forcedotcom/sf-skills. Use this skill to author a complete HXL WidgetBundle (UEM body + schema.json + -meta.xml). TRIGGER when: user asks for a widget, mosaic, fragment, card, or rich UI surface for any subject, domain, feature, or entity noun; the prompt names only an entity or data shape without invoking Lightning Types, CLTs, or Apex-backed types. DO NOT TRIGGER when: the prompt explicitly says 'Lightning Type', 'CLT', 'Custom Lightning Type', 'Apex-backed type', or references '@apexClassType/...' (use…
Its SKILL.md is about 5.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `examples/conditional.json`, `examples/formulas.json` and `examples/list-with-foreach.json`).
The repository describes itself as: Salesforce's curated collection of agent skills for building applications. Optimized for Agentforce Vibes, compatible with all AI tools. The licence is Apache-2.0.
2 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 3c15867. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are json and typescript).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Platform Widget Generate loads about 5.8k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 174 tokens; SKILL.md has 2,107 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.
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); files beside SKILL.md are not scanned.
The full file from forcedotcom/sf-skills at commit 3c15867, republished under its Apache-2.0 licence (© forcedotcom). 2,107 words, ~5,757 tokens.
.claude/skills/platform-widget-generate/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.Author a complete WidgetBundle: a UEM tree (tile/widget), a JSON Schema describing the widget's input contract, and the .uiwidget-meta.xml that registers the bundle.
Use when the user asks for a widget, mosaic, fragment, or card-style rich UI surface. Do not use this skill for custom-LWC renderers or for renderer.json files inside a Custom Lightning Type bundle — those belong to platform-custom-lightning-type-generate.
widgetName (required) — camelCase identifier; becomes the directory name under uiWidgets/.lightningTypeSchema — { path, apexClassFqn } for an existing Apex-backed Lightning Type. The FQN takes one of two forms: outer-class (<namespace>__<ClassName>) where the outer class is the payload, or inner-class (<namespace>__<ClassName>$<InnerClass>) where the named inner class is the payload. Passed in by the platform-lightning-type-widget-coordinate orchestrator. When present, derive per references/schema-from-lightning-type.md.lightningTypeSchema is passed, infer the shape directly from what the user wrote: a pasted JSON payload, an enumerated field list ("id as string, total as number"), or descriptive prose. The output is the same ordered list of { name, type, required } either way.If neither source yields a shape, STOP and ask the user before proceeding.
Three files in <pkgDir>/uiWidgets/<widgetName>/:
| File | Content |
|---|---|
<widgetName>.json | Widget envelope — { "type": "lightning__agentforceWidget", "contentBody": { "widgetBody": { UEM tree rooted at tile/widget } } } |
schema.json | JSON Schema — root has type: "object" + properties.attributes wrapper carrying lightning:type: "lightning__objectType" and the field properties |
<widgetName>.uiwidget-meta.xml | <UiWidgetBundle> element with <masterLabel>, <description>, and <widgetType>JSON</widgetType> |
See references/widget-bundle-layout.md for the <pkgDir> resolution procedure and the exact <widgetName>.uiwidget-meta.xml shape.
A widget body is a UEM tree of blocks nested under contentBody.widgetBody. The root node is tile/widget. Every node — root and non-root — has the same shape: no type key; just definition, optional attributes, optional meta, and optional children. Block shape:
interface Block {
definition: string // {namespace}/{blockName} — root is "tile/widget"
attributes?: Record<string, any>
meta?: { // see references/widget-meta-directives.md
forEach?: string
forItem?: string
if?: string
}
children?: Block[]
}The first child of tile/widget.children SHOULD be a single tile/column. All widget content typically goes inside that first child for predictable vertical structure across surfaces.
Purpose: Discover the palette of blocks available for composition.
Required parameters: actionName: "discoverUiComponents", metadataType: "FRAGMENT", parameters.pageType: "FRAGMENT". Optional: searchQuery to filter by name/description.
Returns: list of { definition, description, label, attributes? }.
Purpose: Fetch JSON schemas (property types, required vs optional, validation) for selected blocks.
Required parameters: actionName: "getUiComponentSchemas", metadataType: "FRAGMENT", parameters.pageType: "FRAGMENT", parameters.componentDefinitions: ["namespace/definition", ...]. Optional: includeKnowledge (default true).
Returns: componentSchemas[] — success entries carry the JSON schema, failure entries carry an error message. Partial failures are supported.
Never pass
tile/widgettogetUiComponentSchemas— it is a fixed wrapper, not a queryable component.
{!$attrs.<attrName>}. <attrName> MUST match a property name in schema.json.forEach, reference the loop variable instead — e.g. "text": "{!$item.name}". See references/widget-meta-directives.md.references/widget-formulas.md for the full supported-function list, syntax, and gotchas.tile/button supports an actions attribute that dispatches an action node on an event. Two action definitions are supported:
| Action | Timing | Required attributes | Effect |
|---|---|---|---|
action/openLink | synchronous | url (string). Optional target (_blank|_self, default _blank) | Opens a URL |
action/sendMessage | asynchronous | content (string) | Posts a new user message back to the agent and earns a fresh turn |
{
"definition": "tile/button",
"attributes": {
"label": "Button Label",
"variant": "primary",
"actions": { "click": [ { "definition": "action/sendMessage", "attributes": { "content": "content" } } ] }
}
}{
"definition": "tile/button",
"attributes": {
"label": "Button Label",
"variant": "primary",
"actions": { "click": [ { "definition": "action/openLink", "attributes": { "url": "https://www.example.com", "target": "_blank" } } ] }
}
}A tile/button with no actions attribute renders disabled — a button exists to trigger an action, so always attach a click action to a button meant to be interactive.
These conventions cover widget structure — how blocks are grouped and stacked.
| Primitive | Purpose | When to use |
|---|---|---|
tile/column | Vertical stack of children | Root wrapper, and any group of blocks that should stack |
tile/row | Horizontal stack of children | Two or more blocks that belong on the same line |
tile/spacer | Whitespace between blocks | When extra space is needed between content groups |
tile/column inside a tile/row (or vice versa) when the visual orientation actually changes for that subgroup.discoverUiComponents output — do not assume a block name from this table without seeing it in the discovery response.Widgets express intent, not pixels. Each surface provides a default look and feel; brand/theme overrides apply automatically.
variant, size, and other enum-typed attributes (primary, destructive, success, warning). Do not pin literal colors or pixel values.tile/button with variant: primary. Use secondary or destructive for additional actions (see the tile/button schema for the full variant enum).tile/button needs a click action. See Actions above — an action-less button renders disabled.h1 per widget. Use h2/h3 for sub-section headings, body for prose, caption for helper text.tile/badge, tile/callout).gap, size unless there is a specific reason to override.width unless a content constraint requires it."check", "alert-circle"); other icon libraries are not supported.Resolve the widget spec — an ordered list of { name, type, required }. Source depends on which input was provided (see Inputs):
lightningTypeSchema was passed by the orchestrator → derive per references/schema-from-lightning-type.md.Discover blocks (REQUIRED — do NOT skip). Call the discoverUiComponents metadata action via execute_metadata_action. Use property types from the widget spec to seed searchQuery (text → "text", number → "number"). If discoverUiComponents returns success: false, an error, or an empty list, STOP and surface the error verbatim — do not improvise block names from memory, prior runs, or training data. Re-run discover with a different searchQuery only if the failure is search-query-specific.
Select blocks. Choose one block per widget-spec property, plus structural primitives from Layout Best Practices.
Get block schemas (REQUIRED — do NOT skip). Call the getUiComponentSchemas metadata action via execute_metadata_action for the selected blocks. Review property metadata. If componentSchemas returns all-failure or empty, STOP and surface the error — do not improvise from existing widgets in the project.
Build the UEM tree (example reads REQUIRED — do NOT skip). First, identify which patterns match the widget spec and read each matching example file from this skill's own examples/ directory (<skill-root>/examples/):
| Pattern in the spec | Example to read |
|---|---|
| Single object (no iteration) | <skill-root>/examples/single-object.json |
| Any list iteration (root-level array, nested list, or list embedded in a single-object widget) | <skill-root>/examples/list-with-foreach.json |
Conditional rendering (if bound to a boolean or formula) | <skill-root>/examples/conditional.json |
Computed values, text/number transforms, or if driven by a formula (not a bare boolean field) | <skill-root>/examples/formulas.json |
A spec may match multiple patterns (e.g. a list of items where some items render conditionally reads both list-with-foreach.json and conditional.json). Read every matching example, and only those — do not skip the read because the pattern feels familiar.
Before writing any formula, read references/widget-formulas.md in full — it is the authoritative list of supported operators and functions; do not improvise a function name or operator that isn't documented there.
Then:
tile/column. Collection → wrap repeating block in forEach/forItem. See references/widget-meta-directives.md.{!$attrs.X} (or {!$item.X} inside forEach)."if" on meta — either a bare lightning__booleanType property, or a formula expression that evaluates to boolean. See references/widget-formulas.md.{!...} per references/widget-formulas.md — do not invent a new schema property to hold a value that can be computed from existing ones.Author schema.json. Build the JSON Schema from the widget spec. Fields live one level deep under an attributes wrapper:
{
"title": "<Widget Display Name>",
"description": "<one line about what the widget shows>",
"type": "object",
"properties": {
"attributes": {
"lightning:type": "lightning__objectType",
"properties": {
"<propertyName>": {
"title": "<label>",
"description": "<short description>",
"lightning:type": "<lightning__textType | lightning__numberType | ...>"
}
}
}
}
}Required root keys: title, type: "object", properties.attributes (with lightning:type: "lightning__objectType" and a nested properties map). See references/schema-from-lightning-type.md for full primitive type guidance.
Author <widgetName>.uiwidget-meta.xml. See references/widget-bundle-layout.md for the exact shape.
Resolve <pkgDir> and write the bundle. Follow the procedure in references/widget-bundle-layout.md (## Resolving <pkgDir>). A widget bundle is a three-file set — all three files must be written in the same step; a bundle with fewer than three files is incomplete and will not deploy.
<pkgDir>/uiWidgets/<widgetName>/<widgetName>.json # widget envelope — UEM tree (primary artifact)
<pkgDir>/uiWidgets/<widgetName>/schema.json # attribute contract for the envelope
<pkgDir>/uiWidgets/<widgetName>/<widgetName>.uiwidget-meta.xml # UiWidgetBundle registrationEach file has a distinct role:
<widgetName>.json — the widget envelope with the tile/widget UEM tree. This is the primary artifact; schema.json is its companion contract, not a substitute.schema.json — the JSON Schema for the attributes referenced by {!$attrs.X} bindings in the envelope.<widgetName>.uiwidget-meta.xml — the UiWidgetBundle element that registers the bundle for source tracking and deployment.Write all three before proceeding to self-validation.
Self-validate. Before reporting, confirm each check below and report each result individually (pass or fail (<reason>)). Do not summarize as a single "all passed" line — list every check so a reviewer can spot a silent skip.
schema-parses — <pkgDir>/uiWidgets/<widgetName>/schema.json parses as JSON.schema-root-keys — root has title (string), type: "object", and properties.attributes (object) — where properties.attributes carries lightning:type: "lightning__objectType" and a nested properties map. No unevaluatedProperties: false.schema-leaf-types — every leaf under properties.attributes.properties carries a lightning:type. Singular nested inner-class fields carry lightning:type set to the inner Apex class reference (@apexClassType/<namespace>__<OuterClass>$<InnerClass>); the nested shape is not redeclared. List<InnerClass> fields carry lightning:type: "lightning__listType" with items.lightning:type set to the inner Apex class reference (@apexClassType/<namespace>__<OuterClass>$<InnerClass>), not a redeclared field map — see references/schema-from-lightning-type.md. When the list has no Apex-backed type (schema inferred from the prompt), items.lightning:type: "lightning__objectType" MUST carry an inline nested properties map for every item field the body binds via {!$item.X}.bindings-resolve — every {!$attrs.X} (or {!$attrs.<outerField>.<innerField>} for nested objects) in <widgetName>.json resolves to a property under schema.json properties.attributes.properties, and every {!$item.X} resolves to a forItem loop variable defined upstream. This applies to $attrs/$item references inside formula expressions too.formulas-supported — every function name used inside a {!...} expression appears in the Supported functions list in references/widget-formulas.md.body-envelope — <widgetName>.json root has type: "lightning__agentforceWidget" and a contentBody object whose widgetBody carries the UEM tree rooted at tile/widget. No node in the tree — root or non-root — carries a type key.metaxml-wellformed — <widgetName>.uiwidget-meta.xml parses as well-formed XML.metaxml-elements — <widgetName>.uiwidget-meta.xml has root <UiWidgetBundle> and contains <masterLabel> (non-empty), <description> (non-empty), and <widgetType>JSON</widgetType>.files-present — all three files exist at the resolved <pkgDir>/uiWidgets/<widgetName>/ path.button-actions-present — every tile/button in <widgetName>.json has an actions.click action node whose definition is action/openLink or action/sendMessage.| Constraint | Rationale |
|---|---|
Block definitions follow {namespace}/{blockName} and must match discoverUiComponents output | Runtime resolves blocks by exact definition string |
Never pass tile/widget to getUiComponentSchemas | It is a fixed wrapper, not a queryable component |
Always supply parameters (with required keys) when calling execute_metadata_action | Missing parameters cause hard failure, not partial result |
Every {!$attrs.X} in the body resolves to a property in the widget schema.json | No invented fields |
Every tile/button carries an actions.click entry using action/openLink or action/sendMessage only | These are the only two supported tile action definitions; an action-less button renders disabled |
No $(…), backticks, <(…), brace expansion {a,b,c}, or eval/exec in any Bash tool call | Vibes' safe-shell filter forces manual approval on these patterns even in Bypass mode. Emit separate commands (mkdir -p a && mkdir -p b) or print each value with its own command and reason about the output — do not capture into a shell variable |
| Issue | Resolution |
|---|---|
getUiComponentSchemas returns a partial-failure entry | Pick a different block from discoverUiComponents; do not silently continue without a schema |
Body references {!$attrs.foo} but foo is not under schema.json properties.attributes.properties | Add foo to schema.json properties.attributes.properties OR remove the body reference |
Output written outside <pkgDir>/uiWidgets/<widgetName>/ | <pkgDir> = <packageDirectories[].path>/main/default (see references/widget-bundle-layout.md). Dropping the main/default/ segment is the common cause of widgets landing at force-app/uiWidgets/... instead of force-app/main/default/uiWidgets/... |
if bound directly to a raw string or number relies on truthiness and is unreliable | Bind to a lightning__booleanType property, or use a formula comparison that evaluates to boolean |
tile/button renders but does nothing when clicked | No actions.click entry was set — an action-less button renders disabled by design. Add one (see Actions above) |
Using action/sendMessage for pure navigation, or action/openLink when the agent should respond | action/openLink is synchronous and does not consume a turn; action/sendMessage is asynchronous and earns a fresh turn. Pick the one matching the intended UX |
| File | When to read |
|---|---|
references/widget-meta-directives.md | For forEach / forItem (iteration) and if (conditional rendering), including nested loops |
references/schema-from-lightning-type.md | When lightningTypeSchema is provided; how to derive the widget schema.json from an Apex-backed Lightning Type |
references/widget-bundle-layout.md | Folder layout, -meta.xml shape, <pkgDir> resolution rules |
references/widget-formulas.md | Supported formula functions and operators |
examples/single-object.json | Single-object pattern (root binding via {!$attrs.X}, no iteration) |
examples/list-with-foreach.json | Any list-iteration case — root-level collections, nested lists, and lists embedded inside a single-object widget (e.g. iterating a List<InnerClass> inside an outer Apex payload) |
examples/conditional.json | Conditional pattern (if on meta, including if + forEach together) |
examples/formulas.json | Formula usage — text/arithmetic/date transforms, IF/AND/NOT driving both a tile/text and meta.if |
© forcedotcom, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 8 other files (references) in skills/platform-widget-generate of forcedotcom/sf-skills.
Open the folder on GitHubat commit 3c15867
Platform Widget Generate 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 |
|---|---|---|---|---|---|---|
| Platform Widget Generate this skillforcedotcom/sf-skills | 1.1k | — | ~5.8k | Automated safety check: Pass | Apache-2.0 | |
| Hermes Agent Skill AuthoringNousResearch/hermes-agent | 252k | — | ~3.6k | Automated safety check: Pass | MIT | |
| Configuring Oauth2 Authorization Flowmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Detecting Broken Object Property Level Authorizationmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~4k | Automated safety check: Pass | Apache-2.0 | |
| Makepad Widgetssickn33/agentic-awesome-skills | 47k | 2 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Implementing GCP Binary Authorizationmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~2k | Automated safety check: Pass | Apache-2.0 |
NousResearch/hermes-agent
Author in-repo SKILL.md files: frontmatter and structure. An agent skill from NousResearch/hermes-agent.
mukul975/Anthropic-Cybersecurity-Skills
Configures secure OAuth 2.0 authorization flows, including Authorization Code with PKCE, Client Credentials, and Device Authorization Grant, covering flow selection, PKCE implementation, token…
mukul975/Anthropic-Cybersecurity-Skills
Detect and test for OWASP API3:2023 Broken Object Property Level Authorization (BOPLA), covering excessive data exposure in API responses and mass assignment via injected request-body properties.
sickn33/agentic-awesome-skills
Version: makepad-widgets (dev branch) | Last Updated: 2026-01-19 Check for updates: https://crates.io/crates/makepad-widgets
mukul975/Anthropic-Cybersecurity-Skills
Implements GCP Binary Authorization end to end, including creating KMS-backed attestors, Container Analysis notes, deploy-time policies, and signing image attestations, so that only trusted…
nexu-io/open-design
Self-contained floating chat widget with welcome screen, social links, meeting button, and message input.
forcedotcom/sf-skills
Declared architecture snapshot for one Agentforce agent: planner, topics, actions, flows, Apex, prompt templates, and NGA plugins.
forcedotcom/sf-skills
Data Cloud 360° view of a single Agentforce session. An agent skill from forcedotcom/sf-skills.
forcedotcom/sf-skills
Apply a Salesforce sandbox post-copy automation JSON config against a target org.
forcedotcom/sf-skills
Apply a Salesforce sandbox post-copy automation JSON config against a target org.
forcedotcom/sf-skills
Apply SLDS-compliant UI using the correct blueprints, styling hooks, utility classes, and icons.
forcedotcom/sf-skills
Lightning Web Components with PICKLES methodology and 165-point scoring.
A skill your agent uses to author a complete HXL WidgetBundle (UEM body + schema.json + -meta.xml). Platform Widget Generate is an agent skill from forcedotcom/sf-skills.xml).
Platform Widget Generate fits situations like: author a complete HXL WidgetBundle (UEM body + schema.json + -meta.xml); : user asks for a widget; rich UI surface for any subject; the prompt names only an entity.
Run `npx skills add forcedotcom/sf-skills --skill platform-widget-generate -a claude-code`. Or copy the skill folder (skills/platform-widget-generate in forcedotcom/sf-skills) into .claude/skills/platform-widget-generate in your project. Claude Code loads it when a task matches its description.
Run `npx skills add forcedotcom/sf-skills --skill platform-widget-generate -a codex`. Or copy the skill folder (skills/platform-widget-generate in forcedotcom/sf-skills) into .agents/skills/platform-widget-generate in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add forcedotcom/sf-skills --skill platform-widget-generate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/platform-widget-generate, .gemini/skills/platform-widget-generate, .github/skills/platform-widget-generate and .opencode/skills/platform-widget-generate in your project.
SKILL.md names no scripts, command-line tools or credentials: Platform Widget Generate is instructions for the agent only.
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.
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. Review the folder before installing.
Platform Widget Generate is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.8k tokens (SKILL.md is roughly 23k 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 6.7k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Platform Widget Generate: Hermes Agent Skill Authoring (NousResearch/hermes-agent, 252k stars), Configuring Oauth2 Authorization Flow (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Detecting Broken Object Property Level Authorization (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Makepad Widgets (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.
forcedotcom (a GitHub organization) maintains it in forcedotcom/sf-skills, which has 1,058 GitHub stars. The repository holds 248 skills in this directory. The repository was last updated on October 3, 2026.
Source: forcedotcom/sf-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.