Agent skill

Platform Lightning Type Widget Coordinate

by forcedotcom in forcedotcom/sf-skills

Orchestrate Apex-backed Lightning Type + HXL widget generation.

Apache-2.0Auto-check passed

Install Platform Lightning Type Widget Coordinate

skills CLI
$ npx skills add forcedotcom/sf-skills --skill platform-lightning-type-widget-coordinate -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install forcedotcom/sf-skills platform-lightning-type-widget-coordinate --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/forcedotcom/sf-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/platform-lightning-type-widget-coordinate .claude/skills/platform-lightning-type-widget-coordinate && rm -rf skills-src

Use ~/.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/

Facts

Skill name
platform-lightning-type-widget-coordinate
GitHub stars
1.1k
Token cost
~4.7k tokens
SKILL.md length
2,129 words
Files
6 (incl. references)
Skills in repo
251
Repo updated
First seen
Licence
Apache-2.0

At a glance

Orchestrate Apex-backed Lightning Type + HXL widget generation.

  • Works in 6 steps: Path selection → Lightning Type discovery… → Build plan + approval gate → …
  • Ly when the prompt EXPLICITLY invokes Lightning Types: user says Lightning Type
  • SKILL.md covers Scope, Phase Graph, Phase 1 — Path selection and Phase 2 — Lightning Type…, plus 6 more sections
  • Calls sf and jq

What it does

Platform Lightning Type Widget Coordinate is an agent skill from forcedotcom/sf-skills. Orchestrate Apex-backed Lightning Type + HXL widget generation. TRIGGER only when the prompt EXPLICITLY invokes Lightning Types: user says 'Lightning Type', 'CLT', 'Custom Lightning Type', 'Apex-backed type', references '@apexClassType/...', asks to build a widget or card for a named Lightning Type, asks to create a new Lightning Type and widget together, or grounds a widget in a specific Apex class as its schema. DO NOT TRIGGER when the prompt names only a subject, domain, feature, or entity noun. Also DO NOT…

Its SKILL.md is about 4.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `examples/existing-lightning-type-with-widget-prompt.md`, `examples/new-lightning-type-with-widget-prompt.md` and `references/build-plan-format.md`).

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.

When your agent uses it

  • Ly when the prompt EXPLICITLY invokes Lightning Types: user says Lightning Type
  • Custom Lightning Type
  • Apex-backed type
  • References @apexClassType/...

Example prompts

  • “Lightning Type”
  • “Custom Lightning Type”
  • “Apex-backed type”
  • “/platform-lightning-type-widget-coordinate”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Path selection
  2. Lightning Type discovery (existing-lightning-type-with-widget only)
  3. Build plan + approval gate
  4. Generation
  5. Validation gates
  6. Summary

What it can do on your machine

Read from SKILL.md and the folder at commit e5164d9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Shell commands in SKILL.md call:

    • sf
    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Platform Lightning Type Widget Coordinate loads about 4.7k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 218 tokens; SKILL.md has 2,129 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~218
When it runs · the whole SKILL.md, loaded when a task matches
~4.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from forcedotcom/sf-skills at commit e5164d9, republished under its Apache-2.0 licence (© forcedotcom). 2,129 words, ~4,745 tokens.

Download SKILL.mdSave it as .claude/skills/platform-lightning-type-widget-coordinate/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
platform-lightning-type-widget-coordinate
description
Orchestrate Apex-backed Lightning Type + HXL widget generation. TRIGGER only when the prompt EXPLICITLY invokes Lightning Types: user says 'Lightning Type', 'CLT', 'Custom Lightning Type', 'Apex-backed type', references '@apexClassType/...', asks to build a widget or card for a named Lightning Type, asks to create a new Lightning Type and widget together, or grounds a widget in a specific Apex class as its schema. DO NOT TRIGGER when the prompt names only a subject, domain, feature, or entity noun. Also DO NOT TRIGGER when: authoring only a Custom Lightning Type (use platform-custom-lightning-type-generate), only an Apex class (use platform-apex-generate), editing an existing widget without any Lightning Type change, or grounding a widget on an object/JSON-based Lightning Type (lightning__objectType with primitives).
metadata.version
1.3
metadata.domains
Platform, Agentforce
metadata.minApiVersion
68.0
metadata.relatedSkills
platform-apex-generate, platform-custom-lightning-type-generate, platform-widget-generate

Building a Lightning Type With a Widget

Coordinate Lightning Type, Apex class, and HXL widget generation across the two paths below. This skill never authors content directly — it loads and invokes leaf skills in dependency order, gates progress on user approval, and runs validation gates before reporting completion.

Scope

Apex-backed Lightning Types only — root lightning:type of the form @apexClassType/<namespace>__<ClassName> (outer class). The class itself carries the @AuraEnabled fields that define the payload shape; nested list-element types live as inner classes referenced by List<Inner> fields on the outer class. Object/JSON-based Lightning Types (root lightning__objectType with primitive properties) are out of scope; route those to platform-custom-lightning-type-generate and platform-widget-generate separately.


Phase Graph

PhasePurposeRuns inOutput
1 — Path selectionPick the path (existing-lightning-type-with-widget · new-lightning-type-with-widget) from the user prompt.All pathspath
2 — Lightning Type discoveryLocal project first; then sf project retrieve --metadata LightningTypeBundle:<name>; ambiguity resolution; in-scope verification.existing-lightning-type-with-widget onlylightningTypeSchema (path + SHA-256 + Apex class FQN)
3 — Build planPrint the plan in full; proceed unless the next reply explicitly pushes back.All pathsprinted plan
4 — GenerationLoad and invoke leaf skills per path.All pathsfiles written
5 — ValidationRun hard gates (block) and warn gates (advisory).All pathsgate report
6 — SummaryFiles, validations, preview readiness, next steps.All pathssummary

Per-phase pattern:

StepWhat to do
1. Load skillInvoke the named skill. Even if you remember its content, skills evolve — always load fresh.
2. ExecuteFollow the loaded skill's workflow.
3. VerifyConfirm outputs exist and match the spec.
4. CheckpointConfirm phase completion before moving on.

Phase 1 — Path selection

Determine the path from the user prompt and pick the corresponding leaf-skill load order:

PathTriggerPhase 4 sub-skill load order
existing-lightning-type-with-widgetPrompt names a Lightning Type and treats it as existing (no create, generate, or new qualifier on the type). Phase 2 confirms it exists and is in scope.platform-widget-generate (renderer wiring is authored inline per the Phase 4 "Renderer.json wiring step" — no separate skill load)
new-lightning-type-with-widgetPrompt asks for a new Lightning Type (verbs: create, generate, build, make a new) or Phase 2 finds nothing in the local project or in the org.platform-apex-generate → platform-custom-lightning-type-generate (schema authoring) → platform-widget-generate (renderer wiring authored inline afterwards per the Phase 4 "Renderer.json wiring step")

If the prompt names no Lightning Type at all (just a widget against prompt-provided fields or sample data), this orchestrator should not have been triggered — route the user to platform-widget-generate directly.

If the prompt is ambiguous between the two paths, ask one clarifying question max and pick. The new-lightning-type-with-widget path's platform-apex-generate step is engaged automatically — do not prompt the user to confirm Apex.


Phase 2 — Lightning Type discovery (existing-lightning-type-with-widget only)

Skipped for new-lightning-type-with-widget (the Lightning Type does not yet exist).

For existing-lightning-type-with-widget, FIRST Read references/lightning-type-discovery.md (REQUIRED — do NOT skip; do not run Phase 2 from this summary alone), then execute its find → verify → ensure-class procedure step by step. The bullets below are a reminder, not a substitute for the reference:

  • Local project first: search force-app/**/lightningTypes/<TypeName>/schema.json.
  • If not found, run sf project retrieve --metadata LightningTypeBundle:<TypeName> against the connected org.
  • If multiple candidates surface, list them with FQNs and paths. Ask the user to pick.
  • After locating the schema, verify it is in scope (root lightning:type starts with @apexClassType/). If the type is object/JSON-based, surface that and stop.
  • Ensure the backing Apex class is in the local project. Parse <ClassName> from the @apexClassType/<ns>__<ClassName> root. If <pkgDir>/classes/<ClassName>.cls is absent, run sf project retrieve --metadata ApexClass:<ClassName>. This runs whether the Lightning Type was found locally or retrieved from the org — a locally-present Lightning Type can still reference an absent class. If the class exists nowhere, surface it and stop (the type is unrenderable). See the reference for the full procedure.
  • If retrieval fails, surface the CLI error and offer: (a) ask the user to run retrieve manually and re-run, or (b) downgrade to new-lightning-type-with-widget if appropriate. Never silently downgrade.
  • If retrieval finds nothing, prompt the user to confirm flipping to new-lightning-type-with-widget before continuing.

Capture the Lightning Type schema.json SHA-256 and the Apex class FQN (parsed from @apexClassType/...) at the end of this phase. The Phase 5 lightning-type-unchanged gate compares the SHA against the on-disk SHA at end of Phase 4 to enforce no silent schema edits.

Staleness: do NOT maintain a cross-session cache. Always read the local project fresh and always re-retrieve from the org per session.


Phase 3 — Build plan + approval gate

Print a build plan using the template in references/build-plan-format.md. The plan must list:

  • A one-line developer-facing summary of what will be built (the PLAN: line in the template).
  • Lightning Type name and source (existing in local project · retrieved from org · newly created), plus the Apex class FQN it references.
  • Files about to be created or modified, with absolute paths.
  • Sub-skills that will run after approval.
  • Validations that will run after generation.

The plan is read by the developer. Keep it concrete: name the artifacts, files, sub-skills, and validations.

Print the plan in full, then proceed unless the user's next reply explicitly pushes back. Explicit pushback = no, stop, wait, change X, use Y instead, or an equivalent rejection / revision request. Explicit approval (yes, approve, go, looks good, ok) is welcome but NOT required — silence, an unrelated follow-up, or the natural continuation of a single-turn eval all count as implicit approval. The plan being visible in the transcript is the invariant; blocking on interactive approval is not. If pushback arrives, revise the plan and re-print before moving on.


Phase 4 — Generation

Execute the sub-skill load order from the chosen path's row in the Phase 1 table. For each sub-skill:

  1. Load the skill.
  2. Execute the leaf skill's authoring workflow against the spec from Phase 3. The leaf skill is authoritative for its own deliverables.
  3. Verify the outputs match what the build plan promised.
  4. Checkpoint before invoking the next sub-skill.

new-lightning-type-with-widget handoff contract:

  • Apex authors a class whose @AuraEnabled fields define the desired Lightning Type shape. Inner classes are used only for nested list-element types. Capture the outer class FQN (<namespace>__<ClassName>).
  • The Custom Lightning Type references the outer class via lightning:type: "@apexClassType/<namespace>__<ClassName>".
  • Widget grounds on the outer class's @AuraEnabled fields and binds attributes via {!$attrs.X}.
  • After the widget bundle is written, author the Lightning Type's renderer wiring per the renderer.json wiring step below.

existing-lightning-type-with-widget handoff contract:

  • Hand the widget skill the Lightning Type schema.json path and the Apex class FQN captured in Phase 2. The widget skill derives its own schema.json from the Apex class's @AuraEnabled fields (see platform-widget-generate/references/schema-from-lightning-type.md).
  • After the widget bundle is written, author the Lightning Type's renderer wiring per the renderer.json wiring step below. The Lightning Type schema.json is NOT modified (lightning-type-unchanged enforces this) — only renderer.json is written.

Renderer.json wiring step (BOTH flows — never optional):

First, Read platform-custom-lightning-type-generate/references/widget-rendition.md (REQUIRED — do NOT skip; do not author renderer.json from memory or by copying an existing project sample, which may use a deprecated shape).

After the widget bundle exists, author <pkgDir>/lightningTypes/<TypeName>/renderer.json using the widget-rendition pattern documented in platform-custom-lightning-type-generate/references/widget-rendition.md. The renderer file is a thin wrapper — its first child references the widget via "definition": "@widget/c/<widgetName>" and maps every widget schema property to the Lightning Type instance's matching attribute via {!$attrs.<schemaPropertyName>}. Do NOT duplicate the widget body inside renderer.json; the widget bundle is the single source of truth for the rendering tree.

Existing-renderer handling (existing-lightning-type-with-widget only): if renderer.json already exists at the target path, read it first.

  • If it already references the same widget (same @widget/c/<widgetName>) with the same attribute mapping, leave it alone.
  • If it references a different widget OR uses a custom-LWC root override (c/<componentName>), STOP and surface the conflict to the user before overwriting. Do not silently replace the user's existing rendition.
  • If the file exists but is not a widget-rendition (e.g. property-level overrides only), surface that and ask whether to merge or replace.

Without this wiring the widget is unreachable from the Lightning Type — the widget bundle ships dead. renderer-wires-widget enforces existence and binding correctness.


Show full SKILL.md (807 more words)Show less

Phase 5 — Validation gates

Read references/validation-gates.md and run every gate. The orchestrator runs cross-skill gates only — widget-bundle-internal checks (schema parse, root keys, leaf lightning:type, {!$attrs.X} resolution, .uiwidget-meta.xml well-formedness, <UiWidgetBundle> root, <masterLabel>, <description>, and <widgetType>JSON</widgetType>) are owned by platform-widget-generate and run as part of its own self-validation step.

Hard — block on failure:

  1. lightning-type-unchanged — existing-lightning-type-with-widget only. Recompute SHA-256 of the on-disk Lightning Type schema.json and compare against the SHA captured in Phase 2. Mismatch = orchestrator silently edited the type.
  2. renderer-wires-widget — both paths. Confirm <pkgDir>/lightningTypes/<TypeName>/renderer.json exists, parses as JSON, wires this widget via componentOverrides["$"].definition === "@widget/c/<widgetName>", and componentOverrides["$"].attributes binds every widget schema property as {!$attrs.<schemaPropertyName>}. See "renderer.json wiring step" in Phase 4 and validation-gates.md for the required shape.

Warn — advisory:

  1. field-trace — both paths. RUN the trace procedure in references/validation-gates.md (grep @AuraEnabled from the outer .cls, jq widget schema property keys, print both lists, classify INVENTED vs OMITTED). PRINT both lists in the gate report — asserting pass without printing the lists is a hard violation. Silent omissions (Apex field absent from widget AND absent from the Phase 3 Properties omitted: plan) warn.
  2. deploy-check — new-lightning-type-with-widget only. RUN sf project deploy --check-only --source-dir <pkgDir>/classes/<ClassName>.cls,<pkgDir>/lightningTypes/<TypeName> and report the result. Reporting pass without running this command is a hard violation. See validation-gates.md for the "not yet deployed is not a valid skip reason" rule.

Report each gate result by name in Phase 6 (pass, fail (<reason>), warn (<reason>), not run). Do not summarize as "all passed" — list each gate explicitly.


Phase 6 — Summary

Report. The summary is read by the developer — list only the files actually written; group by bundle so the developer can locate them quickly.

text
Lightning Type + Widget Build Complete: <widgetName>

FILES GENERATED:
  Widget bundle:
    <pkgDir>/uiWidgets/<widgetName>/<widgetName>.json
    <pkgDir>/uiWidgets/<widgetName>/schema.json
    <pkgDir>/uiWidgets/<widgetName>/<widgetName>.uiwidget-meta.xml

  Lightning Type bundle:
    <pkgDir>/lightningTypes/<TypeName>/schema.json                # only when newly created
    <pkgDir>/lightningTypes/<TypeName>/renderer.json              # always — wires the Lightning Type to the widget

  Apex (only when newly created):
    <pkgDir>/classes/<ClassName>.cls
    <pkgDir>/classes/<ClassName>.cls-meta.xml

VALIDATIONS:
  widget self-validation (platform-widget-generate gates): <pass | fail — see sub-skill report>
  Lightning Type schema unchanged from before this run: <pass | fail | n/a (newly created)>
  Lightning Type renderer wires this widget: <pass | fail (<reason>)>
  widget↔apex field trace (INVENTED + OMITTED lists printed): <pass | warn (<reason>) | fail (invented: <list>)>
  sf project deploy --check-only: <pass | warn | n/a (no new Apex or Lightning Type to deploy)>

NEXT STEPS:
  - Deploy: sf project deploy start --source-dir <pkgDir>
  - Preview: <preview-surface guidance>

Hard Rules (always apply)

  1. Plan-first, then proceed. Print the full Phase 3 build plan before writing any file. If the next turn contains explicit rejection or a change request, stop and revise; otherwise continue to Phase 4. The invariant is the plan being visible in the transcript — not an interactive human approval — so this rule holds in manual chat, in agent-to-agent flows, and in single-turn eval runs where no follow-up user message arrives.
  2. No silent schema edits to existing Lightning Types. Phase 5 lightning-type-unchanged enforces this for existing-lightning-type-with-widget.
  3. No silent Apex changes to existing Apex. If Phase 4 needs to modify a pre-existing class, surface it in Phase 3. A leaf skill that hits a shape gap mid-Phase-4 MUST stop and surface to the orchestrator instead of editing .cls directly — Phase 3 covers gaps the orchestrator already knew about; this clause covers gaps discovered later by a leaf skill.
  4. No invented fields, no silent omissions. Every {!$attrs.X} must trace to the widget schema.json, and the widget schema.json must be a subset of the Apex class's @AuraEnabled fields. Default disposition for every Apex field is include; omission requires the field to appear in the Phase 3 build plan's Properties omitted: section with a rationale the user has approved. field-trace prints both APEX_FIELDS and WIDGET_PROPS lists and warns on silent omissions. List<InnerClass> fields are NEVER candidates for silent omission.
  5. One clarification at most when Lightning Type lookup is ambiguous.
  6. Always load the leaf skill before generation. Do not author from memory.
  7. Out-of-scope types stop the orchestrator. If Phase 2 discovers an object/JSON-based Lightning Type, route the user to platform-custom-lightning-type-generate and platform-widget-generate separately.
  8. Run gates, do not describe them. Phase 5 gates are concrete checks/commands. Reporting pass without executing the gate is a hard violation; report not run instead.
  9. Lightning Type rendition is mandatory, never optional. Both paths end with <pkgDir>/lightningTypes/<TypeName>/renderer.json wiring the Lightning Type to the widget via @widget/c/<widgetName> with attribute mapping per the widget-rendition pattern. Without this, the widget bundle ships dead. renderer-wires-widget enforces existence and binding.
  10. No shell metacharacters that trigger the Vibes safe-shell filter. In every Bash tool call emitted by this orchestrator and by any leaf skill it invokes, do NOT use command substitution ($(…) or backticks), process substitution (<(…), >(…)), brace expansion ({a,b,c} or {1..N}), or eval / exec. These patterns force manual approval even under Bypass mode and stall the eval. Instead: run separate commands (mkdir -p a && mkdir -p b, not mkdir -p {a,b}); print each intermediate value with its own command and reason about the result rather than capturing it (jq … file on its own, not X=$(jq … file)); use plain shell variables (X=literal) or here-strings when a value must be reused across commands.

Reference File Index

FileWhen to read
references/lightning-type-discovery.mdPhase 2 — local-project scan, org retrieve, ambiguity handling, in-scope verification, and ensuring the backing Apex class is in the local project.
references/build-plan-format.mdPhase 3 — plan template the model fills before STOP.
references/validation-gates.mdPhase 5 — full hard / warn gate table with error→fix mapping.
examples/existing-lightning-type-with-widget-prompt.mdPhase 3 — before drafting the build plan, read this for a complete existing-lightning-type-with-widget walkthrough.
examples/new-lightning-type-with-widget-prompt.mdPhase 3 — before drafting the build plan, read this for a complete new-lightning-type-with-widget walkthrough.

© 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

Files

SKILL.md and 5 other files (references) in skills/platform-lightning-type-widget-coordinate of forcedotcom/sf-skills.

  • SKILL.md
  • examples/existing-lightning-type-with-widget-prompt.md
  • examples/new-lightning-type-with-widget-prompt.md
  • references/build-plan-format.md
  • references/lightning-type-discovery.md
  • references/validation-gates.md

Open the folder on GitHubat commit e5164d9

Compare with similar skills

Platform Lightning Type Widget Coordinate 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.

Platform Lightning Type Widget Coordinate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Platform Lightning Type Widget Coordinate this skillforcedotcom/sf-skills1.1k—~4.7kAutomated safety check: PassApache-2.0
Orchestratesickn33/agentic-awesome-skills47k1 repos~692Automated safety check: PassMIT
Team Agent Orchestrationaffaan-m/ECC275k1 repos~1.2kAutomated safety check: PassMIT
Orca Orchestrationstablyai/orca87k—~916Automated safety check: PassMIT
Agent Orchestrator Taskruvnet/ruflo74k3 repos~1kAutomated safety check: PassMIT
Swarm Orchestrationruvnet/ruflo74k—~261Automated safety check: PassMIT

Similar skills

  • Orchestrate

    sickn33/agentic-awesome-skills

    Coordinate focused subagents on substantial work, keep their ownership non-overlapping, and integrate verified results.

    47k GitHub starsUsed in 1 repo~692 tokens
    Agent WorkflowsAuto-check passed
  • Run team-based orchestration for agent squads: work items with owners and scope, agent Kanban state, branch isolation, control pane visibility, and merge gates.

    275k GitHub starsUsed in 1 repo~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Orca Orchestration

    stablyai/orca

    Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator…

    87k GitHub stars~916 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Agent skill for orchestrator-task - invoke with $agent-orchestrator-task

    74k GitHub starsUsed in 3 repos~1k tokens
    Agent WorkflowsAuto-check passed
  • Multi-agent swarm coordination for complex tasks. An agent skill from ruvnet/ruflo.

    74k GitHub stars~261 tokensUpdated today
    DevelopmentAuto-check passed
  • Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.

    74k GitHub starsUsed in 2 repos~779 tokens
    Agent WorkflowsAuto-check passed

More from forcedotcom/sf-skills

All 251 skills in this repo
  • Agentforce Architecture Analyze

    forcedotcom/sf-skills

    Declared architecture snapshot for one Agentforce agent: planner, topics, actions, flows, Apex, prompt templates, and NGA plugins.

    1.1k GitHub stars~4.5k tokensUpdated today
    Auto-check passed
  • Agentforce D360 Analyze

    forcedotcom/sf-skills

    Data Cloud 360° view of a single Agentforce session. An agent skill from forcedotcom/sf-skills.

    1.1k GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Apply a Salesforce sandbox post-copy automation JSON config against a target org.

    1.1k GitHub stars~5.3k tokensUpdated today
    Auto-check: notes
  • Apply a Salesforce sandbox post-copy automation JSON config against a target org.

    1.1k GitHub stars~5.4k tokensUpdated today
    Auto-check: notes
  • Design Systems Slds Apply

    forcedotcom/sf-skills

    Apply SLDS-compliant UI using the correct blueprints, styling hooks, utility classes, and icons.

    1.1k GitHub stars~3.7k tokensUpdated today
    Auto-check passed
  • Experience Lwc Generate

    forcedotcom/sf-skills

    Lightning Web Components with PICKLES methodology and 165-point scoring.

    1.1k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

Questions about Platform Lightning Type Widget Coordinate

What does Platform Lightning Type Widget Coordinate do?

Orchestrate Apex-backed Lightning Type + HXL widget generation. Platform Lightning Type Widget Coordinate is an agent skill from forcedotcom/sf-skills. Orchestrate Apex-backed Lightning Type + HXL widget generation.

When should I use Platform Lightning Type Widget Coordinate?

Platform Lightning Type Widget Coordinate fits situations like: ly when the prompt EXPLICITLY invokes Lightning Types: user says Lightning Type; custom Lightning Type; apex-backed type; references @apexClassType/...

How do I install Platform Lightning Type Widget Coordinate in Claude Code?

Run `npx skills add forcedotcom/sf-skills --skill platform-lightning-type-widget-coordinate -a claude-code`. Or copy the skill folder (skills/platform-lightning-type-widget-coordinate in forcedotcom/sf-skills) into .claude/skills/platform-lightning-type-widget-coordinate in your project. Claude Code loads it when a task matches its description.

How do I install Platform Lightning Type Widget Coordinate in Codex?

Run `npx skills add forcedotcom/sf-skills --skill platform-lightning-type-widget-coordinate -a codex`. Or copy the skill folder (skills/platform-lightning-type-widget-coordinate in forcedotcom/sf-skills) into .agents/skills/platform-lightning-type-widget-coordinate in your project. Codex loads it when a task matches its description.

Can I use Platform Lightning Type Widget Coordinate in Cursor, Gemini CLI or GitHub Copilot?

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-lightning-type-widget-coordinate -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-lightning-type-widget-coordinate, .gemini/skills/platform-lightning-type-widget-coordinate, .github/skills/platform-lightning-type-widget-coordinate and .opencode/skills/platform-lightning-type-widget-coordinate in your project.

What does Platform Lightning Type Widget Coordinate need to run?

Going by SKILL.md and its folder, Platform Lightning Type Widget Coordinate needs the command-line tools its instructions call (sf and jq).

Does Platform Lightning Type Widget Coordinate access the network?

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.

Is Platform Lightning Type Widget Coordinate safe to install?

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.

What licence does Platform Lightning Type Widget Coordinate use?

Platform Lightning Type Widget Coordinate 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.

How many tokens does Platform Lightning Type Widget Coordinate use?

About 4.7k tokens (SKILL.md is roughly 19k 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 5.8k tokens, read only when the agent opens those files.

What are the alternatives to Platform Lightning Type Widget Coordinate?

Skills that share tags, products or a category with Platform Lightning Type Widget Coordinate: Orchestrate (sickn33/agentic-awesome-skills, 47k stars), Team Agent Orchestration (affaan-m/ECC, 275k stars), Orca Orchestration (stablyai/orca, 87k stars) and Agent Orchestrator Task (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Platform Lightning Type Widget Coordinate?

forcedotcom (a GitHub organization) maintains it in forcedotcom/sf-skills, which has 1,060 GitHub stars. The repository holds 251 skills in this directory. The repository was last updated on October 7, 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.