agentleFS
rpraharajrpraharaj/ai-sdlc/skills/map-process/SKILL.md

map-process

Skill0 starsChanged 16 days agoMITView on GitHub

Map current and future business process — steps, owners, and systems. Use when the user asks for a process map, as-is/to-be flow, journey across teams, or /map-process. Do not write architecture or product code.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Do not implement. Do not invent owners or systems.

    line 18
  2. Distinctive:

    If neither a spec nor a described current process exists, stop and ask which process to map.

    line 36
  3. Very specific:

    Read AGENTS.md if present.

    line 45
  4. Distinctive:

    Read the PRD/requirements if named.

    line 46

≈ “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

Map process

Show who does what, in which system, today and after. This is not architecture (write-architecture), not requirements (write-requirements), and not a UI spec.

Do not implement. Do not invent owners or systems.

Is this the right skill?

SignalDo this instead
Testable functional contractwrite-requirements
System boundaries and storeswrite-architecture
API / event shapewrite-integration-contract
UAT scriptsplan-uat (consume this map first)
Impact of a scope changeassess-change

Required inputs

  • A PRD or requirements path, or a named process the user already runs
  • context/systems-of-record.md if it exists — systems on the map should match it
  • context/glossary.md if it exists

If neither a spec nor a described current process exists, stop and ask which process to map. Do not invent a happy-path.

Human decisions (do not invent)

  • Who owns each step in the business
  • Whether a to-be step is in scope for this initiative

Procedure

  1. Read AGENTS.md if present. Read context/systems-of-record.md and context/glossary.md if present.
  2. Read the PRD/requirements if named. Note actors and systems they already mention.
  3. Find the home: first existing docs/process/, or offer to create it. Name: docs/process/<slug>.md.
  4. Open references/process-template.md. Copy every heading. Write n/a when unused.
  5. Draw current first. Every step has: actor, action, system (or offline), output.
  6. Draw future only for steps this initiative changes. Unchanged steps say unchanged.
  7. List handoffs and failure/exception paths the sources mention. Do not invent exception paths.
  8. Systems not in systems-of-record.md are marked not in systems-of-record.

Output

  • Path: docs/process/<slug>.md
  • Template: references/process-template.md

Quality bar

  • Current path has at least two steps with actors
  • Every step names a system or offline
  • Future path does not silently add systems that are not in context or the spec
  • Exceptions are sourced or none in sources
  • Unused headings are n/a

Done

  1. Path
  2. Step count current / future
  3. Next skill: write-architecture, write-requirements, or plan-uat

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.