agentleFS
Sign inStart free
process-streetprocess-street/ps-skills/skills/discovery/ps-search/SKILL.md

ps-search

Skill1 starsChanged 5 months agoMITView on GitHub

Search a Process Street org for workflows, runs, data sets, folders, pages, or users by keyword/criteria — PS MCP tools first, REST API as fallback. The "where is that thing" skill, not for building. Use when someone says "ps search", "search ps", "find that workflow", "find the workflow about [X]", "what runs are active for [company]", "search my ps org", "look up workflow", "find workflow run", or "find dataset".

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search across a Process Street org for workflows, runs, data sets, folders, pages, or users by keyword/criteria.

    line 10
  2. Distinctive:

    Clarify scope: if ambiguous. ("All orgs? Just yours?

    line 55
  3. Very specific:

    Pick the narrowest tool: Don't call listWorkflows if the user gave a folder.

    line 56
  4. Distinctive:

    Default to a markdown table.

    line 65
  5. Distinctive:

    If 1 result → expand inline with id + folderId.

    line 73

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

PS Org Search Skill

Purpose

Search across a Process Street org for workflows, runs, data sets, folders, pages, or users by keyword/criteria. Uses the PS MCP server first — falls back to the REST API only when MCP can't filter the way you need.

This is the "where is that thing" skill. Not for building. Not for inspecting one workflow deeply (use ps-audit for that).

When to Use

  • "Find that workflow about onboarding"
  • "Show me all active runs for [company]"
  • "What's in the [folder name] folder"
  • "Is there a data set for inspector assignments"
  • "Which workflows have a code task that calls [external system]"
  • "Find the run where the form field 'County' = 'Berkeley'"

Reference Docs (read first if unsure of tool/endpoint)

  • the API reference (reference/api-reference.md) — full endpoint list, MCP tools, and quirks

Search Routing

What you wantFirst-choice toolNotes
Find workflow by name/keywordlistWorkflows (MCP)Filter results client-side by name
List workflows in a folderlistWorkflows (MCP)Pass folderId
Active runs for a company/keywordsearchWorkflowRuns (MCP)Max 200 results per call — paginate
Runs by status (Active/Completed/Archived)searchWorkflowRuns (MCP)status param
Runs by form field valuesearchWorkflowRuns (MCP)Use formFieldFilters
Find data set by namelistDataSets (MCP)Filter results client-side
Records inside a data setlistDataSetRecords (MCP)Paginate by cursor
Find folderlistFolders (MCP)
Find a page (SOP)listPages (MCP)
Find user by name/emaillistUsers (MCP)
Find scheduled workflowslistScheduledWorkflows (MCP)
Find workflow incoming webhookslistWorkflowIncomingWebhooks (MCP)
Search inside task widget contentREST API + grepMCP doesn't filter widget bodies — get workflow revision, walk widgets

Standard Flow

  1. Clarify scope if ambiguous. ("All orgs? Just yours? A specific folder?")
  2. Pick the narrowest tool. Don't call listWorkflows if the user gave a folder.
  3. Paginate. searchWorkflowRuns caps at 200. Always check for nextPageToken / cursor.
  4. Return a tight table. Columns: name, id, link, last activity, status. Hide stuff the user didn't ask for.
  5. Include the PS deep link for each result so the user can click straight in.

Output Shape

Default to a markdown table. Always include the PS deep link so the user can click in.

| Name | Folder | Status | Last activity | Link |
|------|--------|--------|---------------|------|
| Daily Inspection | Operations | Active | 2026-05-20 | [open](https://app.process.st/...) |

If 1 result → expand inline with id + folderId. If >20 results → ask the user to narrow before dumping.

Common Gotchas

  • searchWorkflowRuns formFieldFilters requires the form field ID, not label. Use the CLI template-fields (lists fields + IDs) first if the user gives a label.
  • MCP listWorkflows returns archived workflows mixed in. Filter archived: false unless the user asks for archived.
  • Workflow names are not unique across folders — show folder in the table.

Related Skills

  • ps-audit (or the CLI template-export) — read out one workflow in full
  • the CLI template-fields (lists fields + IDs) — pull field IDs from a run before filtering by field value
  • data-set — CRUD on the data sets you found here

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free