agentleFS
Sign inStart free
process-streetprocess-street/ps-skills/skills/build/ps-audit/SKILL.md

ps-audit

Skill1 starsChanged 5 months agoMITView on GitHub

Audit and optimize an existing Process Street workflow — score it against best practices, surface issues, and optionally apply the fixes. Use when the user wants to review, improve, tighten, or optimize a workflow.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If you only have a name, process_street.py workflows to find the ID.

    line 18
  2. Very specific:

    Use the scorecard in reference/best-practices.md.

    line 22
  3. Distinctive:

    Projected improvement: if adopted.

    line 36
  4. Distinctive:

    Ask which to implement. For the API-doable ones, build an edit plan and hand off to the ps-edit flow (draft → preview → publish → rollback).

    line 40

≈ “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

Audit & optimize a Process Street workflow

Analyze a workflow, score it, recommend improvements grounded in reference/best-practices.md, and (with consent) apply the fixes via ps-edit.

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

1. Load the workflow

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

If you only have a name, process_street.py workflows to find the ID.

2. Score against the 10-point scorecard

Use the scorecard in reference/best-practices.md. For each step and field, check:

  • Structure: outcome-based name? 6–15 well-ordered, verb-named steps? any step doing two jobs?
  • Data quality: right field types, or free text where a Select/Date/Number belongs? fields no one needs? missing required fields?
  • Flow: would conditional logic hide irrelevant steps? are stops/approvals justified or just friction? are approvals configured with subject tasks?
  • Accountability: does every task have an owner (assignment rule)? dynamic due dates?
  • Automation: any human re-keying data between systems that a Code/AI task or webhook could remove? hard-coded option lists that should be a Data Set?
  • Polish: branded first step, help text where ambiguous?

3. Present findings

Give a short report:

  • Current score (X/10) with the 2–3 biggest gaps.
  • Recommendations, each tagged: [quick win] (apply now via API), [redesign] (needs restructuring), or [UI-only] (required flag, theming, integrations).
  • Projected improvement if adopted.

4. Offer to apply

Ask which to implement. For the API-doable ones, build an edit plan and hand off to the ps-edit flow (draft → preview → publish → rollback). Re-export to confirm. List any UI-only items the user must do themselves.

Almost every structural fix is API-applicable: change field types, add logic, add due-date/assignment rules, add/remove steps and fields, add content. Only required-field flagging, theming, org settings, and deep integrations are UI-only.

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