agentleFS
OKHP3OKHP3/skillz/.agents/skills/okhp3-future-state-strategy/SKILL.md

okhp3-future-state-strategy

Skill3 starsChanged 2 months agoMITView on GitHub

Design a target-state process and a structured change strategy from a gap analysis. Use this skill when the user wants to redesign a process after gaps have been identified; when they ask "what should the process look like", "how do we fix this", "design the to-be process", or "build a change plan". Produces a future-state process artifact and a change strategy document. This is a recommended extension skill — use after process-gap-and-exception-analysis has produced a gap analysis. Scope firewall applies: never include employer-proprietary constraints without explicit user authorisation.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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. Very specific:

    No gap analysis exists — run process-gap-and-exception-analysis first

    line 58
  2. Distinctive:

    Do not infer proprietary business rules from industry knowledge without flagging them as assumptions

    line 68
  3. Distinctive:

    Do not include employer-identifying details in any generated artifact

    line 70
  4. Distinctive:

    Check the future-state design covers:

    line 92
  5. Distinctive:

    All structural gaps (missing steps, unowned activities)

    line 93
  6. Distinctive:

    All exception gaps (undefined handling, missing escalation)

    line 94
  7. Distinctive:

    All compliance gaps (absent controls, missing segregation)

    line 95

≈ “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-future-state-strategy

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

Purpose

Design the target-state (to-be) process and a structured change strategy based on gap analysis findings. The future-state artifact documents the intended process design; the change strategy documents how to get there.


When to use this skill

  • gap-analysis.yaml exists with at least one critical or major gap
  • User wants to redesign a process based on identified gaps
  • User needs a change management plan to accompany process redesign
  • Preparing the target-state PNS input for process-narrative-authoring

When NOT to use this skill

  • No gap analysis exists — run process-gap-and-exception-analysis first
  • User wants to document only the current state — use as-is-process-capture
  • Scope firewall: do not include confidential employer constraints, proprietary system names, or commercially sensitive process details without explicit user instruction

Scope Firewall

This skill operates on process abstractions. Before authoring the future state:

  • Confirm all described gaps are based on user-provided information
  • Do not infer proprietary business rules from industry knowledge without flagging them as assumptions
  • Flag all assumed constraints with confidence: assumed in the future-state YAML
  • Do not include employer-identifying details in any generated artifact

Future-State Design Workflow

Step 1 — Prioritise gaps

Rank gaps from gap-analysis.yaml by severity: critical → major → minor → observation.

Focus the future-state design on resolving all critical and major gaps.

Step 2 — Design to-be steps

For each resolved gap, define the replacement or new step:

  • State the intended action in a single imperative statement
  • Assign a named role (not a person)
  • Define entry and exit criteria
  • Specify any system or tool involved

Step 3 — Validate completeness

Check the future-state design covers:

  • All structural gaps (missing steps, unowned activities)
  • All exception gaps (undefined handling, missing escalation)
  • All compliance gaps (absent controls, missing segregation)

Step 4 — Define change approach

For each major change, define:

  • change_type — add | remove | modify | automate | transfer
  • effort — low | medium | high
  • risk — low | medium | high
  • dependencies[] — other changes that must happen first
  • owner_role — who is responsible for implementing this change

Step 5 — Draft change strategy

Structure the change strategy document with:

  1. Change summary — what is changing and why
  2. Stakeholder impact — who is affected, how significantly
  3. Transition plan — sequence and timeline for changes
  4. Risk register — what could go wrong during transition
  5. Communication plan — how and when to inform each stakeholder group
  6. Success criteria — how to know the change has landed

Output Schema

future-state.yaml contains:

  • process_id — matches PIR process_id
  • future_state_version — "0.1-draft" initially
  • design_date, designed_by_role
  • resolved_gaps[] — each gap from gap-analysis.yaml with its resolution
  • to_be_steps[] — id, description, actor_role_id, systems[], confidence
  • open_assumptions[] — assumed constraints flagged for user confirmation
  • change_items[] — each with change_type, effort, risk, dependencies[], owner_role

Handoff Instruction

Pass future-state.yaml to process-intake-and-scope or process-narrative-authoring to create the target-state PNS. The future-state steps map directly to activity_sequence.activities[] in the new PNS.


References

Load on demand:

  • references/change-strategy-framework.md — change type taxonomy, effort/risk classification, ADKAR and Kotter alignment, and scope firewall rules

Scripts

  • scripts/generate-future-state.mjs — scaffolds future-state YAML from gap-analysis input

Assets

  • assets/fixtures/future-state-example.yaml — canonical future-state design for purchase-approval process

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.