agentleFS
OKHP3OKHP3/skillz/.agents/skills/okhp3-as-is-process-capture/SKILL.md

okhp3-as-is-process-capture

Skill3 starsChanged 2 months agoMITView on GitHub

Capture and normalise a current-state process description into a structured as-is process YAML with stable step identifiers. Use this skill when the user has a process that is already running and needs to document its current state before gap analysis or redesign; when they provide step lists, SOPs, or process notes that need to be structured; when they say "document what we do today", "capture the current process", or "baseline the process before we change it". Produces a structured as-is process artifact with normalised step IDs.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    No PIR exists — run process-intake-and-scope first to establish scope and boundaries

    line 56
  2. Distinctive:

    Do not include aspirational or proposed changes in the as-is record

    line 58
  3. Very specific:

    Run scripts/assign-step-ids.mjs to assign act-001, act-002, … identifiers.

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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-as-is-process-capture

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

Purpose

Capture and normalise the current-state (as-is) process into a structured YAML artifact. The as-is record uses stable act-NNN step identifiers that persist across revisions, making gap analysis and change tracking tractable.


When to use this skill

  • User describes how a process runs today and wants it documented before redesign
  • You need a baseline artifact before running process-gap-and-exception-analysis
  • PIR exists but steps lack stable IDs — normalise them with scripts/assign-step-ids.mjs
  • User imports existing process notes, SOPs, or procedure documents for structuring

When NOT to use this skill

  • No PIR exists — run process-intake-and-scope first to establish scope and boundaries
  • User wants to design a future state only — skip to future-state-and-change-strategy
  • Do not include aspirational or proposed changes in the as-is record

Capture Workflow

Step 1 — Import and triage

Identify the source: natural language description, bullet list, existing SOP document, or flowchart image. Determine if a PIR already exists. If not, run process-intake-and-scope first.

Step 2 — Extract and sequence steps

Parse all process steps in the order they occur. Each step must have:

  • A single imperative action statement (IEEE 29148)
  • An identified actor or role
  • Entry criteria (what triggers this step)
  • Exit criteria (what signals completion)

Step 3 — Assign stable IDs

Run scripts/assign-step-ids.mjs to assign act-001, act-002, … identifiers. IDs are:

  • Sequential within each process
  • Prefixed act- for activities, gw- for gateways, evt- for events
  • Stable — once assigned, they do not change even if steps are reordered

Step 4 — Identify current-state gaps

Flag steps that are:

  • Undocumented ("we just know to do it")
  • Person-dependent ("only Alice knows this part")
  • Inconsistently executed ("sometimes we skip this")
  • Missing a named actor

Tag these with capture_quality: low | medium | high.

Step 5 — Record as-is metadata

Document:

  • captured_date — when this baseline was recorded
  • capture_method — interview | document-review | observation | workshop
  • process_version — current version of the process if known (default "1.0-baseline")
  • baseline_status — draft | reviewed | approved

Output Schema

The as-is-process.yaml contains:

  • process_id — matches PIR process_id
  • baseline_status — draft | reviewed | approved
  • captured_date, capture_method, process_version
  • steps[] — each with id, description, actor_role_id, entry_criteria, exit_criteria, capture_quality, systems[], notes
  • identified_gaps[] — steps or sections with low capture quality or person-dependency
  • open_questions[] — unresolved items from the capture session

Handoff Instruction

Pass as-is-process.yaml to process-gap-and-exception-analysis to identify deviations, exception paths, and improvement opportunities.

Also pass pir.yaml to process-narrative-authoring when the as-is record is reviewed and approved.


References

Load on demand:

  • references/as-is-capture-rules.md — step ID conventions, capture quality taxonomy, and baseline metadata rules

Scripts

  • scripts/assign-step-ids.mjs — normalises a step list into stable act-NNN / gw-NNN / evt-NNN identifiers

Assets

  • assets/fixtures/as-is-process-example.yaml — canonical as-is capture for purchase-approval baseline

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.