Web Asset Generator
alonw0/web-asset-generator
Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn.
Configure settings on an already-existing Enhanced MessagingChannel (any type — WhatsApp, Text/SMS, LINE, Apple, Facebook, EmbeddedMessaging), given its {CHANNELID}.
$ npx skills add forcedotcom/sf-skills --skill service-de-channel-settings-configure -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install forcedotcom/sf-skills service-de-channel-settings-configure --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/service-de-channel-settings-configure .claude/skills/service-de-channel-settings-configure && 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 "service-de-channel-settings-configure" agent skill from https://github.com/forcedotcom/sf-skills/tree/main/skills/service-de-channel-settings-configure into .claude/skills/service-de-channel-settings-configure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "service-de-channel-settings-configure", 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/service-de-channel-settings-configureType 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 service-de-channel-settings-configure -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install forcedotcom/sf-skills service-de-channel-settings-configure --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/service-de-channel-settings-configure .agents/skills/service-de-channel-settings-configure && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "service-de-channel-settings-configure" agent skill from https://github.com/forcedotcom/sf-skills/tree/main/skills/service-de-channel-settings-configure into .agents/skills/service-de-channel-settings-configure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "service-de-channel-settings-configure", 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 service-de-channel-settings-configure -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install forcedotcom/sf-skills service-de-channel-settings-configure --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/service-de-channel-settings-configure .cursor/skills/service-de-channel-settings-configure && 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 "service-de-channel-settings-configure" agent skill from https://github.com/forcedotcom/sf-skills/tree/main/skills/service-de-channel-settings-configure into .cursor/skills/service-de-channel-settings-configure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "service-de-channel-settings-configure", 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/service-de-channel-settings-configure--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 service-de-channel-settings-configure -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install forcedotcom/sf-skills service-de-channel-settings-configure --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/service-de-channel-settings-configure .gemini/skills/service-de-channel-settings-configure && 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 "service-de-channel-settings-configure" agent skill from https://github.com/forcedotcom/sf-skills/tree/main/skills/service-de-channel-settings-configure into .gemini/skills/service-de-channel-settings-configure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "service-de-channel-settings-configure", 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 service-de-channel-settings-configureInstalls 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 service-de-channel-settings-configure -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/service-de-channel-settings-configure .github/skills/service-de-channel-settings-configure && 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 "service-de-channel-settings-configure" agent skill from https://github.com/forcedotcom/sf-skills/tree/main/skills/service-de-channel-settings-configure into .github/skills/service-de-channel-settings-configure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "service-de-channel-settings-configure", 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 service-de-channel-settings-configure -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 service-de-channel-settings-configure --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/service-de-channel-settings-configure .opencode/skills/service-de-channel-settings-configure && 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 "service-de-channel-settings-configure" agent skill from https://github.com/forcedotcom/sf-skills/tree/main/skills/service-de-channel-settings-configure into .opencode/skills/service-de-channel-settings-configure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "service-de-channel-settings-configure", 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.
service-de-channel-settings-configureConfigure settings on an already-existing Enhanced MessagingChannel (any type — WhatsApp, Text/SMS, LINE, Apple, Facebook, EmbeddedMessaging), given its {CHANNELID}.
Service De Channel Settings Configure is an agent skill from forcedotcom/sf-skills. Configure settings on an already-existing Enhanced MessagingChannel (any type — WhatsApp, Text/SMS, LINE, Apple, Facebook, EmbeddedMessaging), given its {CHANNELID}. Covers five facets: consent (ConsentType + per-language keyword records), automated responses, messaging keywords, session-inactivity timeouts, and pre-chat parameters. Consent + a matching language-keyword record are required for activation's readiness check. TRIGGER when setting or changing settings on a channel that already exists (opt-out…
Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/channel-settings-facets.md`, `references/gotchas.md` and `references/language-keywords.md`).
It works with WhatsApp. 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.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 4bbae5c. 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.
Shell commands in SKILL.md call:
sfFrom 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.
Service De Channel Settings Configure loads about 3.8k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 265 tokens; SKILL.md has 1,322 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 4bbae5c, republished under its Apache-2.0 licence (© forcedotcom). 1,322 words, ~3,755 tokens.
.claude/skills/service-de-channel-settings-configure/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.Configures settings on an already-existing Enhanced MessagingChannel (identified by {CHANNEL_ID}), for any message type. It groups five facets; you only run the ones the caller asks for.
| # | Facet | Write surface | Applies to |
|---|---|---|---|
| 1 | Consent — ConsentType + OptInPrompt/DoubleOptInPrompt on the channel, plus per-language MsgChannelLanguageKeyword records | Data/SObjects API (sf data update/create record) | all Enhanced types |
| 2 | Automated responses — <automatedResponses> (initial, agent-engaged/-ended, opt-in prompt/confirmation, help, opt-out, inactive/idle) | Metadata API deploy | all Enhanced types |
| 3 | Messaging keywords — <messagingKeywords> (OptIn/OptOut/Help keyword groups per language) | Metadata API deploy | all Enhanced types |
| 4 | Session inactivity — endUserIdleTimeOut, endUserIdleAction, endInactiveSessionTimeOut, isAgentMessageResetInactivityEnabled | Metadata API deploy | MIAW-only (reset-flag also Apple/Facebook) |
| 5 | Pre-chat parameters — <customParameters> / <standardParameters> | Metadata API deploy | MIAW pre-chat only (rare) |
This skill is mixed-surface. Consent (facet 1) is written with the Data API on the live record. Facets 2–5 live only in the channel's metadata and are configured by retrieving the channel's .messagingChannel-meta.xml, editing it, and deploying it back. Verified live on sdb6 (2026-09): every Data/Connect/Tooling read of the facet-2–5 fields fails INVALID_TYPE/"No such column" — they are Metadata-API-only.
Per-type applicability is verified, not assumed (from a live retrieve of real channels of each type). Facets 2 and 3 are genuinely type-agnostic. Facet 4's four timeout fields appear only on MIAW; only isAgentMessageResetInactivityEnabled extends to Apple/Facebook, and SMS/WhatsApp/LINE carry no inactivity fields at all. Facet 5 appears only on MIAW channels that use pre-chat. Scope per-type accordingly — do not deploy a facet a type doesn't support.
Trigger this skill when the user wants to configure or change settings on a channel that already exists, e.g.:
DO NOT TRIGGER — hand off instead:
service-digital-engagement-channel-configure. That skill creates an Embedded Messaging channel from XML; this skill only configures a channel that already exists (it needs a live {CHANNEL_ID}, prefix 0Mj).service-de-channel-create.service-de-channel-routing-configure.service-de-channel-activate.Part of the Enhanced-channel headless pipeline: service-de-channel-create → service-de-channel-routing-configure → this skill → service-de-channel-activate. Activation's readiness check requires both routing and consent, so at minimum run facet 1 before activating. The service-de-headless-channel-configure orchestrator sequences the pipeline automatically; invoke this skill directly to configure settings on their own. For the MIAW-specific channel-creation-from-XML flow, see the sibling service-digital-engagement-channel-configure.
| Reference file | Load when |
|---|---|
references/language-keywords.md | Facet 1: creating/updating MsgChannelLanguageKeyword records — field list, CSV keyword semantics, create-vs-update, Unified-SMS help/custom rules. |
references/channel-settings-facets.md | Facets 2–5: the Metadata-API retrieve→edit→deploy flow, the full <automatedResponses> type/shape catalog (12 types, 2 content shapes), <messagingKeywords>, the inactivity fields, and per-type applicability. |
references/gotchas.md | Troubleshooting an unexpected result, or before modifying this skill. |
references/worked-examples.md | Reference runs of the ImplicitOptIn/ExplicitOptIn/DoubleOptIn consent paths. |
PlatformType=Enhanced channels only. Stage 1 confirms this and stops otherwise.service-de-channel-create first; this skill expects a real MessagingChannel.Id (prefix 0Mj).{CHANNEL_ID} — a 15/18-char MessagingChannel.Id (prefix 0Mj). Must already exist and be Enhanced.{FACETS} — optional; which facets to configure (consent, auto-responses, keywords, inactivity, parameters). If omitted, infer from the request or ask.{CONSENT_TYPE} — optional (facet 1); ImplicitOptIn | ExplicitOptIn | DoubleOptIn.{LANGUAGE} — optional; locale for keyword/response records (e.g. en_US). Default en_US.{ORG_ALIAS} — optional; sf target-org alias. Default: sf config get target-org.Facet-specific values (prompts, keyword lists, response text, timeout minutes) are collected interactively per facet, or accepted if pre-supplied.
Success:
{"ok": true, "channelId": "0Mj...", "messageType": "WhatsApp",
"facetsConfigured": ["consent","auto-responses"],
"consent": {"consentType": "ExplicitOptIn", "languageKeywordId": "3Or...", "activationReady": true},
"metadataDeploy": {"status": "Succeeded", "facets": ["auto-responses","keywords"]}}No change needed / precondition / failure:
{"ok": true, "noop": true, "message": "Requested settings already configured"}
{"ok": false, "kind": "not-enhanced", "hint": "settings apply to Enhanced channels only; this channel is PlatformType=<x>"}
{"ok": false, "kind": "facet-not-applicable", "hint": "<facet> is not supported on <messageType> channels"}
{"ok": false, "kind": "channel-patch-failed" | "keyword-record-failed" | "metadata-deploy-failed" | "verify-failed", "message": "..."}Read the channel; confirm it exists and is Enhanced; capture MessageType (drives per-type applicability).
sf data query --target-org '{ORG_ALIAS}' \
--query "SELECT Id, DeveloperName, PlatformType, MessageType, MessagingPlatformKey, ConsentType, OptInPrompt, DoubleOptInPrompt, IsRequireDoubleOptIn FROM MessagingChannel WHERE Id = '{CHANNEL_ID}'" \
--json > /tmp/cs-channel.jsonError: Channel {CHANNEL_ID} not found — check the id, or run service-de-channel-create first.PlatformType != 'Enhanced' → emit {ok:false, kind:"not-enhanced", ...} and stop.Decide which facets to run from {FACETS} or the request. For each requested facet, check per-type applicability (table above / references/channel-settings-facets.md); if a facet doesn't apply to this MessageType, emit {ok:false, kind:"facet-not-applicable", ...} for that facet (or skip it and note it) rather than deploying an unsupported field.
sf CLI is slow, not broken. Calls to this org routinely take 2–4 minutes (heavy CLI startup + slow round-trip). Run each sf command with a generous timeout; a slow return is normal, not a hang.
Run when consent is requested (and always before activation). Read the existing keyword records:
sf data query --target-org '{ORG_ALIAS}' \
--query "SELECT Id, MasterLanguage, OptInKeywords, DoubleOptInKeywords, OptInConfirmation, OptOutKeywords, OptOutConfirmation, HelpKeywords, HelpResponse, CustomKeywords, CustomResponse FROM MsgChannelLanguageKeyword WHERE MessagingChannelId = '{CHANNEL_ID}'" \
--json > /tmp/cs-keywords.jsonNo-op check: if ConsentType is non-null AND an existing keyword record already satisfies the readiness matrix for that ConsentType, don't overwrite — this facet is already activation-ready.
Choose the ConsentType (prompt if {CONSENT_TYPE} absent — do not auto-pick), then satisfy this contract (the exact server-side activation-readiness rule — source in references/gotchas.md):
| ConsentType | MessagingChannel fields | MsgChannelLanguageKeyword (≥1 record) |
|---|---|---|
| ImplicitOptIn | (none required) | OptOutKeywords + OptOutConfirmation |
| ExplicitOptIn | OptInPrompt¹ | above + OptInKeywords |
| DoubleOptIn | OptInPrompt¹ + DoubleOptInPrompt + IsRequireDoubleOptIn=true | above + DoubleOptInKeywords |
¹ OptInPrompt is optional for readiness on Unified SMS / WhatsApp / RCS (MessageType IN ('Text','WhatsApp','Rcs') on Enhanced); still recommend setting it. ImplicitOptIn is never a no-op — it still needs an opt-out keyword record.
Write the channel fields in one PATCH, then create/update the language-keyword record per references/language-keywords.md.
Quoting rule (load-bearing): sf data ... --values splits on spaces — wrap every multi-word value in single quotes inside the double-quoted string: OptInPrompt='Reply YES to receive messages'. Unquoted fails with Malformed key=value pair.
# ExplicitOptIn example
sf data update record --target-org '{ORG_ALIAS}' --sobject MessagingChannel \
--record-id '{CHANNEL_ID}' --values "ConsentType=ExplicitOptIn OptInPrompt='{OPT_IN_PROMPT}'" --json > /tmp/cs-patch.jsonOn non-zero status: emit {ok:false, kind:"channel-patch-failed"|"keyword-record-failed", message: ...}. Then verify by re-reading (Stage 5).
WhatsApp rich content rejects ExplicitOptIn server-side — surface the message, don't retry (see
references/gotchas.md).
Run when auto-responses and/or keywords are requested. These are type-agnostic (all Enhanced types). Load references/channel-settings-facets.md and follow it — it has the retrieve→edit→deploy flow, the 12 <automatedResponses> type values, the two content shapes (TextResponse vs MessageDefinition), the EndUserIdleResponse <responseTimeoutInMins> rule, XML escaping, and the <messagingKeywords> OptIn/OptOut/Help groups.
Outline:
sf project retrieve start -m MessagingChannel:{DeveloperName}).<automatedResponses> / <messagingKeywords> blocks in the retrieved .messagingChannel-meta.xml (add/replace by <type> / <keywordType>+<language>; XML-escape response text).sf project deploy start -m MessagingChannel:{DeveloperName}).{ok:false, kind:"metadata-deploy-failed", message: <componentFailures>}.Never emit <actionParameterMappings> (0 occurrences across a 191-channel scan — it's a Tooling-only mapping done in the UI post-deploy).
Run only when requested and applicable to this MessageType:
endUserIdleTimeOut 5–30, endUserIdleAction = Inactivate|End|InactivateAndEnd, endInactiveSessionTimeOut, isAgentMessageResetInactivityEnabled) are top-level siblings of <embeddedConfig>, not inside it. Full four fields → MIAW only; isAgentMessageResetInactivityEnabled also valid on Apple/Facebook; not applicable on SMS/WhatsApp/LINE → emit facet-not-applicable. (On 262-line pods only endUserIdleTimeOut deploys — see references/gotchas.md.)<customParameters> (name, masterLabel, externalParameterName, parameterDataType=String, optional maxLength) and <standardParameters> — MIAW pre-chat only, rare. Skip unless the caller explicitly configures pre-chat.Both use the same retrieve→edit→deploy flow as Stage 3 (references/channel-settings-facets.md).
For facet 1, re-read the channel + keyword records and confirm every required field for the chosen ConsentType is non-null (channel and ≥1 language record); else {ok:false, kind:"verify-failed", hint:"..."}. For metadata facets, confirm the deploy status is Succeeded, then re-retrieve the channel metadata and confirm the edited <automatedResponses> / <messagingKeywords> / inactivity / parameter blocks are present; if a deploy reports Succeeded but the re-retrieved block is missing, emit {ok:false, kind:"verify-failed", hint:"..."}.
Emit the JSON envelope. If invoked directly (leaf), render a short summary:
Success — configured {facets} on channel {CHANNEL_ID} ({MessageType}). (add Activation-ready. when consent passed)Info: requested settings already configured — no changes. (no-op)Warning: {facet} is not supported on {MessageType} channels — skipped. (facet-not-applicable)Warning: this channel is PlatformType={x}, not Enhanced — these settings don't apply. (not-enhanced)Error: {kind}: {message} (failures)© 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 4 other files (references) in skills/service-de-channel-settings-configure of forcedotcom/sf-skills.
Open the folder on GitHubat commit 4bbae5c
Service De Channel Settings Configure 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 |
|---|---|---|---|---|---|---|
| Service De Channel Settings Configure this skillforcedotcom/sf-skills | 1.1k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | |
| Web Asset Generatoralonw0/web-asset-generator | 514 | 1 repos | ~6.6k | Automated safety check: Pass | MIT | |
| Deskcomm Contribuirmelgarafael/DeskcommCRM | 4.5k | — | ~3.6k | Automated safety check: Notes | MIT | |
| Send User MessageTinyAGI/tinyagi | 3.6k | — | ~829 | Automated safety check: Pass | MIT | |
| Wacliopenclaw/wacli | 2.8k | — | ~811 | Automated safety check: Pass | MIT | |
| Deskcomm Extensaomelgarafael/DeskcommCRM | 4.5k | — | ~2.7k | Automated safety check: Pass | MIT |
alonw0/web-asset-generator
Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn.
melgarafael/DeskcommCRM
Guia de contribuição ao DeskcommCRM para quem vai mexer no código e abrir um pull request, sobretudo de um fork.
TinyAGI/tinyagi
Send a proactive message to a paired user via their channel (Discord, Telegram, or WhatsApp).
openclaw/wacli
wacli: WhatsApp linked devices, stores, sync/auth/send, repo/release work.
melgarafael/DeskcommCRM
Guia para criar uma extensão do DeskcommCRM — o pacote declarativo — em vez de abrir um PR no núcleo.
gokapso/agent-skills
Connect WhatsApp to your product with Kapso: onboard customers with setup links, detect connections, receive events via webhooks, and send messages/templates/media.
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.
Works with
Configure settings on an already-existing Enhanced MessagingChannel (any type — WhatsApp, Text/SMS, LINE, Apple, Facebook, EmbeddedMessaging), given its {CHANNELID}. Service De Channel Settings Configure is an agent skill from forcedotcom/sf-skills. Configure settings on an already-existing Enhanced MessagingChannel (any type — WhatsApp, Text/SMS, LINE, Apple, Facebook, EmbeddedMessaging), given its {CHANNELID}.
Service De Channel Settings Configure fits situations like: changing settings on a channel that already exists (opt-out keyword; double opt-in confirmation; initial/help auto-responses; optIn/OptOut keywords.
Run `npx skills add forcedotcom/sf-skills --skill service-de-channel-settings-configure -a claude-code`. Or copy the skill folder (skills/service-de-channel-settings-configure in forcedotcom/sf-skills) into .claude/skills/service-de-channel-settings-configure in your project. Claude Code loads it when a task matches its description.
Run `npx skills add forcedotcom/sf-skills --skill service-de-channel-settings-configure -a codex`. Or copy the skill folder (skills/service-de-channel-settings-configure in forcedotcom/sf-skills) into .agents/skills/service-de-channel-settings-configure 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 service-de-channel-settings-configure -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/service-de-channel-settings-configure, .gemini/skills/service-de-channel-settings-configure, .github/skills/service-de-channel-settings-configure and .opencode/skills/service-de-channel-settings-configure in your project.
Going by SKILL.md and its folder, Service De Channel Settings Configure needs the command-line tools its instructions call (sf).
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.
Service De Channel Settings Configure 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 3.8k tokens (SKILL.md is roughly 15k 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 7.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Service De Channel Settings Configure: Web Asset Generator (alonw0/web-asset-generator, 514 stars), Deskcomm Contribuir (melgarafael/DeskcommCRM, 4.5k stars), Send User Message (TinyAGI/tinyagi, 3.6k stars) and Wacli (openclaw/wacli, 2.8k 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 1,067 GitHub stars. The repository holds 252 skills in this directory. The repository was last updated on October 9, 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.