agentleFS
zhouey314-cloudzhouey314-cloud/ai-agent-skills/skills/workflow-planner/SKILL.md

workflow-planner

Skill0 starsChanged 48 days agoMITView on GitHub

Design stateful agent or human workflows with gates, retries and failure paths before implementation.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when a task spans multiple actors, tools, approvals or irreversible steps.

    line 14
  2. Distinctive:

    Write every transition with actor, precondition, data change and idempotency rule.

    line 27
  3. Distinctive:

    Place a human gate before irreversible publication, payment or high-impact decisions.

    line 28
  4. Distinctive:

    Check reachability and create one normal, one failure and one unauthorized-path test.

    line 30
  5. Very specific:

    If a state has no safe recovery or ownership, flag it UNRESOLVED instead of hiding the gap.

    line 34
  6. Very specific:

    Run python3 tests/validate.py from the repository root to check this skill's contract and example provenance.

    line 42

≈ “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

Workflow Planner

Purpose

Make workflow behavior inspectable before code or automation is deployed.

When to Use

Use when a task spans multiple actors, tools, approvals or irreversible steps.

Inputs

goal, actors[], inputs[], external_systems[], failure_risks[].

Outputs

states[], transitions[], human_gates[], failure_states[], verification[].

Workflow

  1. Identify the initial, success, rejection and blocked states.
  2. Write every transition with actor, precondition, data change and idempotency rule.
  3. Place a human gate before irreversible publication, payment or high-impact decisions.
  4. Specify timeout, retry budget, compensation and escalation for external failures.
  5. Check reachability and create one normal, one failure and one unauthorized-path test.

Failure Handling

If a state has no safe recovery or ownership, flag it UNRESOLVED instead of hiding the gap. Never define auto-publish as a default.

Example

synthetic_unverified: draft → review → approved; missing source → blocked; no auto-publish.

Tests

Run python3 tests/validate.py from the repository root to check this skill's contract and example provenance. This is a structural test, not model-quality evidence.

Limitations

A diagram does not verify the runtime; implement transition tests before release.

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.