agentleFS
process-streetprocess-street/ps-skills/skills/build/ps-edit/SKILL.md

ps-edit

Skill1 starsChanged 5 months agoMITView on GitHub

Edit or maintain an existing Process Street workflow using natural language — add/remove steps and fields, change logic, due dates, assignments, or add media. Use when the user wants to change a workflow they already have.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    If a change looks wrong after publish: process_street.py restore-revision <workflowId> <previousRevisionId>.

    line 64

≈ “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

Edit a Process Street workflow

Translate a natural-language change request into safe API operations with a draft → publish → rollback flow.

CLI: python3 "${CLAUDE_PLUGIN_ROOT}/scripts/process_street.py" <command> (plugin) or scripts/process_street.py (repo). Needs PROCESS_STREET_API_KEY. Detail: reference/api-reference.md.

Use the CLI even if the Process Street MCP is connected. edit-workflow runs draft → publish → rollback and prints a restore-revision command; raw MCP edits skip that safety net. Don't substitute MCP ops for the edit flow.

1. Load current state

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/process_street.py" template-export <workflowId>

This returns steps, fields, logic rules, and the current published revision (the rollback target — note it).

2. Interpret the request → operations

Map the ask to edit-plan ops:

opdoes
add-task / update-task / delete-taskadd, change (name/type/stop/hidden/dueOffset), or remove a step
add-widget / update-widget / delete-widgetadd a field (any of 17 types) or content widget; change; remove
add-rule / delete-ruleconditional logic
set-due-date-rule / set-checklist-due-date-ruledynamic due dates
set-assignment-rules / set-task-permissionswho owns / who can see a task

Positioning: "afterTask": "Existing Step Name". Field types & operators: see reference/api-reference.md.

3. Preview, confirm, apply

Show a before/after of the operations and the rollback command. After the user confirms:

echo '<edit-plan-json>' | python3 "${CLAUDE_PLUGIN_ROOT}/scripts/process_street.py" edit-workflow

Edit-plan shape:

{"workflowId": "<id>", "operations": [
  {"op": "add-task", "name": "QA Review", "taskType": "Approval", "stop": true, "afterTask": "Build"},
  {"op": "add-widget", "taskName": "Intake", "fieldType": "Select", "label": "Region", "options": ["EU", "US"]},
  {"op": "set-assignment-rules", "taskName": "QA Review", "rules": [{"email": "qa@company.com"}]},
  {"op": "add-rule", "rule": {"action": "Show",
     "condition": {"or": [{"and": [{"widgetId": "$widget:Intake:Region", "operator": "Is", "value": "EU"}]}]},
     "targets": {"taskIds": ["$task:GDPR Step"]}}}
]}

The CLI creates a draft, applies ops, publishes, and prints a rollback command. Relay it to the user.

Adding media / polish

add-media <wf> <rev> <taskId> --logo-domain <domain> | --stock "kw" | --video <url> | --embed <url> | --text '<md>'. Create a draft revision first; publish after.

Limits to flag

Required-field flag, brand theming, org/SSO, deep integration config are UI-only. Editing existing embedded instruction text in place is limited (you can add new content widgets). File → use MultiFile.

Rollback

If a change looks wrong after publish: process_street.py restore-revision <workflowId> <previousRevisionId>.

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.