agentleFS
OKHP3OKHP3/skillz/.agents/skills/okhp3-process-intake-and-scope/SKILL.md

okhp3-process-intake-and-scope

Skill3 starsChanged 2 months agoMITView on GitHub

Conduct structured process intake and scope definition using BABOK v3 elicitation techniques. Use this skill when the user wants to document a business process from scratch; when they describe a workflow, procedure, or set of steps and need it structured; when they ask to scope a process, define process boundaries, or capture business rules; when they say "help me document this process", "let's scope out this workflow", or "what are the inputs and outputs"; when you need a Process Intake Record (PIR) as input for downstream narrative, modeling, or SOP skills.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 9 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Do not invent process details the user has not provided — record gaps as open_questions

    line 67
  2. Distinctive:

    Ask: *"Before we start, can you give me one sentence: what does this process produce or accomplish?"*

    line 77
  3. Distinctive:

    Ask: *"What causes this process to start — a person doing something, a scheduled date, an incoming message, or a system event?"*

    line 83
  4. Distinctive:

    Ask: *"Who is involved — who does work, makes decisions, or needs to know the outcome?"*

    line 93
  5. Distinctive:

    Ask: *"What does this process need to begin?"* and *"What does it produce when complete?"*

    line 101
  6. Distinctive:

    Ask: *"What is explicitly outside the scope of this process?

    line 107
  7. Distinctive:

    Ask: *"Walk me through what happens, step by step."*

    line 113
  8. Distinctive:

    After the happy path, probe for: notification steps, logging steps, waiting/pause steps.

    line 115
  9. Distinctive:

    Ask: *"What can go wrong? What happens when it does?"*

    line 125
  10. Distinctive:

    Ask: *"Which systems or tools are used?"* and *"Are there any checkpoints, approvals, or audits built in?"*

    line 129
  11. Very specific:

    Run scripts/score-intake-completeness.mjs to compute completeness_score and ready_for_narrative

    line 163
  12. Very specific:

    When ready_for_narrative: false, report missing sections and ask targeted follow-up questions.

    line 174

≈ “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

okhp3-process-intake-and-scope

OverKill Hill P³ · overkillhill.com · github.com/OKHP3

Purpose

This skill guides structured process intake and scope definition using BABOK v3-aligned elicitation techniques. It produces:

  1. Process Intake Record (PIR) — structured YAML with trigger, actors, inputs, outputs, steps, exceptions, business rules, systems, and controls
  2. Scope Statement — concise prose defining process boundaries, exclusions, and success criteria

The PIR is the foundational input consumed by every downstream skill in the BP-SKILL suite.


When to use this skill

  • User wants to document a process they describe in natural language, bullet points, or prose
  • User says "help me scope this," "let's map this process," or "define the boundaries"
  • You need a structured PIR before calling stakeholder-and-role-mapping or process-narrative-authoring
  • User wants to capture business rules, exception paths, or system touchpoints for a workflow

When NOT to use this skill

  • A validated PIR with ready_for_narrative: true already exists — proceed to process-narrative-authoring
  • User wants a diagram without prior discovery — use visual-process-modeling with their description
  • Do not invent process details the user has not provided — record gaps as open_questions

Intake Workflow

Execute the following stages in order. Conduct a natural conversation — do not present these as a checklist. Load references/pir-schema.md for full field reference.

Stage 0 — Orientation

Ask: "Before we start, can you give me one sentence: what does this process produce or accomplish?"

Record as process_name. If vague, probe: "Who benefits when this process runs correctly? What do they get?"

Stage 1 — Trigger

Ask: "What causes this process to start — a person doing something, a scheduled date, an incoming message, or a system event?"

Classify trigger.event_type:

  • Person acts → manual
  • Date/frequency → scheduled
  • Message/request/email → message
  • System condition → system

Stage 2 — Actors

Ask: "Who is involved — who does work, makes decisions, or needs to know the outcome?"

Classify each actor: initiator | performer | approver | reviewer | notified | system.

Minimum: at least one initiator and one performer or approver.

Stage 3 — Inputs and Outputs

Ask: "What does this process need to begin?" and "What does it produce when complete?"

Capture name, source/consumer, and format for each.

Stage 4 — Scope Boundaries

Ask: "What is explicitly outside the scope of this process? Where does it hand off?"

Record out-of-scope items in scope_statement.exclusions.

Stage 5 — Steps (Happy Path)

Ask: "Walk me through what happens, step by step."

After the happy path, probe for: notification steps, logging steps, waiting/pause steps.

Stage 6 — Business Rules and Decision Points

For each decision: "Who makes this? What are the outcomes? Is there a policy or rule that governs it?"

Classify rule source: policy | regulation | contract | practice.

Stage 7 — Exception Paths

Ask: "What can go wrong? What happens when it does?"

Stage 8 — Systems and Controls

Ask: "Which systems or tools are used?" and "Are there any checkpoints, approvals, or audits built in?"

Stage 9 — Open Questions

Record all unresolved gaps as open_questions — do not assume answers.


PIR Completeness Scoring

scripts/score-intake-completeness.mjs returns a 0–100 weighted score.

SectionPoints
process_name5
elicitation_method5
trigger (both fields)10
actors (≥2, initiator + performer/approver)15
inputs (≥1 valid entry)10
outputs (≥1 valid entry)10
steps (≥3 valid entries)15
exceptions (≥1 valid entry)10
business_rules (≥1 valid entry)10
systems (≥1 valid entry)5
controls (≥1 valid entry)5
Total100

Handoff threshold: score ≥ 70 → ready_for_narrative: true


Output Format

  1. Produce pir.yaml using assets/fixtures/intake-purchase-approval.yaml as the schema reference
  2. Run scripts/score-intake-completeness.mjs to compute completeness_score and ready_for_narrative
  3. Produce scope-statement.md summarising process name, trigger, boundary, exclusions, and success criteria

Handoff Instruction

When ready_for_narrative: true:

  • Pass pir.yaml to stakeholder-and-role-mapping to derive the stakeholder register
  • Then pass pir.yaml + stakeholder-register.yaml to process-narrative-authoring

When ready_for_narrative: false, report missing sections and ask targeted follow-up questions.


References

Load on demand:

  • references/pir-schema.md — complete field reference for PIR YAML

Scripts

  • scripts/generate-pir.mjs — scaffolds a blank PIR YAML from a brief process description
  • scripts/validate-pir.mjs — schema completeness and type validation
  • scripts/score-intake-completeness.mjs — 0–100 weighted completeness score

Assets

  • assets/fixtures/intake-purchase-approval.yaml — canonical PIR fixture (purchase approval)

About

Built by Jamie Hill · OverKill Hill P³ Published at github.com/OKHP3 Part of the OKHP3/skillz Agent Skill library. MIT License -- free to use, fork, and adapt. A nod to the source is appreciated.

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.