forcedotcom/sf-skills/experience-search-coordinate
Claude Code and agent skill by forcedotcom/sf-skills
- community
Checking that the SKILL.md file is still in the repository.
Searches for and retrieves existing content and media (articles, blogs, news, FAQs, events, products, images, logos, icons, photos, graphics, banners, hero images, audio clips, videos, documents) from Salesforce CMS or other connected sources. Use this skill ANY TIME a user says \"find\", \"search\", \"get\", \"fetch\", \"retrieve\", \"look up\", \"locate\", \"show me\", \"list\", or \"I need\" followed by content or media words like \"blog\", \"article\", \"news\", \"FAQ\", \"event\", \"produc…
Install
npx vskill@latest install forcedotcom/sf-skills/experience-search-coordinateSKILL.md
The same SKILL.md was published earlier as forcedotcom/sf-skills/experience-search-coordinate.
Search Coordinator
Routes search requests to the correct sub-workflow — structured CMS content or media — and runs both when a request mixes the two.
A `→ Read` pointer below is a required action, not FYI — open that file before continuing past that point; this skill has drifted before from steps followed off memory.
Scope
This skill is for SEARCHING FOR existing content or media, not creating new content or images.
Use this skill when the user wants to:
- Search for articles, blog posts, news, FAQs, events, products, or custom content
- Search for images, logos, icons, photos, graphics, banners, hero images, audio clips, videos, or documents
- Reuse existing assets instead of creating new ones, or any combination of the above in one request
DO NOT use this skill when the user wants to:
- Generate new content (use
experience-cms-content-generate) - Generate new images (use image generation tools)
- Define content type schemas (use
experience-cms-content-type-generate) - Apply brand guidelines (use
experience-cms-brand-apply) - Create, edit, or publish content records
Step 1: Determine Channel Scope
Mandatory on every request that reaches it — never skip straight to Step 2. No phrasing of the request ("just find me an article," a plain keyword search, etc.) skips this step's local-file scan. If you're about to call search_metadata in Step 2 without having scanned for uiBundles/*/public/content-metadata.json this turn, STOP and come back here first.
- Explicit `channelId` given — use it directly, skip discovery entirely, proceed to the scope rule below.
- Named uiBundle/app, no `channelId` — resolve that uiBundle's
channelId; if it doesn't resolve, fall through to point 3 as if nothing was named. - Otherwise, discover from the local project — scan every
uiBundles/*/public/content-metadata.jsonfile (never gate this on server-side deployment status) and collect thechannelIds found. Zero → public channels only. Exactly one → public plus that channel. More than one → ask the user which one viaask_followup_question.
→ Read references/scope-resolution.md § "Step 1 points 1-3" for the full discovery mechanics before acting on points 1-3 above. Proceed to Step 2 once scope is determined.
Scope rule (applies whether the `channelId` was user-provided or discovered): scope is always public channels (contentAccessScope: "Public", no channelIds field) plus that one channelId (a separate call with channelIds set to it, no contentAccessScope field) — never resolve a separate ID to represent "public," and never send contentAccessScope and channelIds in the same call. This scope decides how many search calls Steps 3 and 4 make: no channelId in scope → one search call (public channels only). A channelId in scope → two search calls (public channels, then that specific channelId), with results merged before presenting.
Step 2: Determine Content Type and Route
Precondition: Step 1 must have already run in this turn (its channel-scope result is what point 5 below carries into Step 3/4). Step 1 runs unconditionally — even for a plain keyword search with no obvious channel angle, not only when the request names a channel or app.
- Identify one or more distinct search intents in the request (e.g. "find a press release about our launch and a hero image for the page" is two intents). Run the rest of this step once per intent.
If intents span both routes, sequence the routes — never interleave or merge them: run the Media Route (Step 4) to full completion for every media intent first, then the Content Route (Step 3) for every content intent. See Step 5.
- Call `search_metadata` on the
metadata-groundingMCP server using the intent itself as the query. No `filters` array support —metadataTypeis the only narrowing parameter, passed top-level:
``javascript search_metadata({ query: "<the user's intent>", metadataType: "ContentTypeBundle", limit: 100 }) ``
Each candidate already includes a full composite identifier (e.g. 00DVW00000CfBQP2A3::0T1VW000008sow60AA::ContentTypeBundle) — use it as returned; never reconstruct it.
Check the outcome before doing anything else:
- `metadata-grounding` is unavailable (the call errors/times out) — you MUST call
get_content_types_for_workspace(the workspace content-type fallback) before any Step 3/4 search tool; do not attemptquery_metadata, there's nothing to look up, and do not skip straight to a search tool on an assumed FQN. - Zero candidates returned — ask the user one clarifying question to narrow the intent (
ask_followup_question, same question/options as the "intent itself is ambiguous" case at the end of this step), then retrysearch_metadataonce with the clarified query: - Still zero candidates after that one retry — apply the workspace content-type fallback. Do not ask a second clarifying question.
- One or more candidates on the retry — continue to point 3.
- One or more candidates on the first call — continue to point 3.
Fallback chain when `search_metadata` doesn't produce a usable candidate list → Read references/content-type-discovery.md before running it: "Workspace content-type fallback" first, then "Wording fallback" as a last resort.
- Call `query_metadata` with each candidate's identifier from point 2 (cap at top 5, batched into one
metadataIdentifiersarray):
``javascript query_metadata({ metadataIdentifiers: ["00DVW00000CfBQP2A3::0T1VW000008sow60AA::ContentTypeBundle"] }) ``
Read each entry's typeDetails[].properties — mixins, typeClasses, and apiName live there, not in the search_metadata response.
- Filter for supported types first, THEN decide the route among survivors — do not conflate the two:
- Discard any candidate whose
properties.mixinslackssfdc_cms:deliveryApiEnabled— only delivery-API-enabled types are searchable. - Of the remainder, discard any whose `properties.typeClasses` lacks `sfdc_cms__structured`. This is the single "supported for search" gate, not a content/media split —
sfdc_cms__structuredappears on both structured-content types and media types, so it only separates searchable types from unsearchable ones (e.g.sfdc_cms__emailcarriessfdc_cms__contentbut notsfdc_cms__structured, and must be discarded). - Zero survive — tell the user which types were found but aren't supported, then stop (don't guess a route). Some, but not all, survive — tell the user which got filtered out (plain statement, not a question), then continue with survivors. All survive — no message needed. → Read
references/content-type-discovery.md§ "Filter-result messages" for exact wording. - Route on the top-ranked survivor's `properties.typeClasses` (order returned by
search_metadata): containssfdc_cms__media→ Media Route (Step 4); otherwise → Content Route (Step 3). - Collect the FQN(s) — the top-ranked survivor's
properties.apiName. Add other surviving candidates' FQNs too if clearly relevant to the same intent and sharing the same classification, passing all as one comma-separatedcontentTypeFqnvalue rather than searching per type.
- Carry the scope from Step 1 (public channels only, or public channels plus a
channelId) into whichever route is invoked — see thechannelIdsfield in each route below.
If intent itself is ambiguous (e.g. "find me some content" with no hint of type or subject) → Read references/content-type-discovery.md § "Intent itself is ambiguous" for the exact question/options before calling search_metadata. Do not guess.
Step 3: Content Route
Follow this sequence for each intent Step 2 routed here. The content type FQN(s) are already known from Step 2.
- Present search sources via `ask_followup_question` before any tool call — only sources whose tools you have, plus "Other"; wait for the choice. → Read
references/content-route.md§ "Presenting available search sources". - Build the query, then confirm before searching:
- Search using keywords (
search_content_cms_channels): - Extract keywords — concrete nouns and named subjects likely in the title or body, plus domain synonyms; max 10, joined with
OR. E.g. "blog posts about sustainable business practices" →sustainable OR sustainability OR business OR environmental. - Extract taxonomies — descriptive qualities, categories, or topical tags only (not concrete nouns), stringified as
{"OR": ["term1", "term2"]}, or"{}"if none. - Payload:
assets/search-payload-template.json,contentTypeFqn= the comma-separated FQN list from Step 2.contentAccessScopeandchannelIdsare mutually exclusive — never both in one call — so they're set per call in point 3. - Search using Data 360 hybrid search (
search_digital_content): verbatimsearchQuery; bare ISOsearchLanguageonly if the schema lists it. On zero results or a language error, ask the user before one retry without it →references/content-route.md. - Other — ask for a direct URL, asset library path, or system to check (no tool call, no confirmation).
Confirm via the two-message pattern (Yes - search now / Edit search / Cancel). → Read references/content-route.md § "Confirming the query before searching".
- Execute the search call(s) — keyword search: one call for public-only scope, two (public + channel-scoped) when a
channelIdis in scope. Hybrid: one call, no channel scope. → Readreferences/content-route.md§ "Executing the search call(s)" (keyword) or the hybrid section (field mapping) before parsing results. - Present up to 5 unique results total (de-duplicated by
managedContentKeyfor display only — an item found under more than one channel still appears once here), grouped by content type, with aLoad Moreoption if more remain (keyword search only). Each item shows its Channel as a per-item field — never the grouping key:
```text I found 3 content items:
Editorial (c__Editorial):
- <title> — Channel: Public
- <title> — Channel: <uiBundle>
Blog (sfdc_cms__blog):
- <title> — Channel: Public
```
Only one content type FQN in scope → the heading may be omitted (still one group); the per-item Channel field is always shown. If an item exists under multiple channels, show its first/primary channel here — the choice between channels happens after selection (point 5), not at presentation time.
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/experience-search-coordinate/SKILL.md
Popularity
- Repository stars
- 1,134
- Repository forks
- 386
- 7-day trend score
- 40
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/forcedotcom/sf-skills/experience-search-coordinate)