agentleFS
process-streetprocess-street/ps-skills/skills/help/ps-help/SKILL.md

ps-help

Skill1 starsChanged 5 months agoMITView on GitHub

Answer "how do I…" and "what is…" questions about Process Street, grounded in the official help docs and bundled best-practices. Use when the user asks how Process Street works, how to do something in it, or for guidance/best practices.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    If a fetch fails or web access is unavailable, say so and answer from bundled knowledge, clearly labeling what's general guidance vs.

    line 16
  2. Very specific:

    If the question is really a "do it for me" (build/edit/audit/organize), answer briefly then offer to run the matching skill (ps-build, …

    line 22
  3. Distinctive:

    Don't invent features, plan names, pricing, or limits.

    line 24

≈ “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

Answer Process Street questions (help docs + best practices)

Answer the user's Process Street question accurately, grounded in real sources — not guesses.

Sourcing order

  1. Bundled knowledge first — check reference/best-practices.md (design guidance) and reference/api-reference.md (what the API can/can't do). These are authoritative for "should I…" and "can the API…" questions.
  2. Live help docs — for product/how-to questions ("how do I add a member field", "how do approvals work", "what plan includes X"), fetch the official help center. Use a web fetch on:
    • https://www.process.st/help/ (help home / search)
    • Specific articles under https://www.process.st/help/docs/... when you know or can find the slug (e.g. code-task, ai-task, conditional-logic, approvals, data-sets, webhooks). If a fetch fails or web access is unavailable, say so and answer from bundled knowledge, clearly labeling what's general guidance vs. confirmed from docs.

How to answer

  • Give the direct answer first, then a short "how" (steps or the relevant CLI command if it's something this toolkit can do).
  • Cite the source: link the specific help article you used, or say "from the bundled best-practices guide."
  • If the question is really a "do it for me" (build/edit/audit/organize), answer briefly then offer to run the matching skill (ps-build, ps-edit, ps-audit, ps-organize).
  • Be honest about limits: required-field flag, brand theming (colors/cover/fonts), org/SSO, and deep native-integration config are UI-only, not API-driven.
  • Don't invent features, plan names, pricing, or limits. If you can't confirm something, say what you'd check and offer to fetch it.

Examples

  • "How do I make a field required?" → It's set in the workflow editor UI (toggle on the field); the public API can't set it. (api-reference.md)
  • "What's the best way to structure an onboarding workflow?" → Summarize from best-practices.md (front-load capture, conditional sections, approval gate, dynamic due dates), then offer ps-build.
  • "How do Code tasks work?" → Fetch https://www.process.st/help/docs/code-task/, explain inputData/outputData, and note this toolkit can build one via ps-build.

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.