agentleFS
OKHP3OKHP3/skillz/.agents/skills/okhp3-process-gap-analysis/SKILL.md

okhp3-process-gap-analysis

Skill3 starsChanged 2 months agoMITView on GitHub

Identify deviations, gaps, and exception paths between an as-is process capture and its intended design. Use this skill when the user wants to find where a process breaks down, where steps are missing or inconsistent, where exception handling is undefined, or where current execution differs from documented procedure. Use when they say "what's wrong with the current process", "find the gaps", "where does this break", or "analyze exceptions". Produces a gap analysis report and exception catalog.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    No as-is capture exists — run as-is-process-capture first

    line 63
  2. Distinctive:

    Do not propose solutions here — record gaps only.

    line 65

≈ “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-gap-analysis

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

Purpose

Systematically identify gaps, deviations, and exception paths in a captured as-is process. The analysis distinguishes:

  1. Structural gaps — missing steps, undefined roles, absent inputs or outputs
  2. Execution gaps — steps performed inconsistently or only by specific individuals
  3. Exception gaps — failure paths with no documented handling
  4. Compliance gaps — steps missing required controls or policy references

When to use this skill

  • You have an as-is-process.yaml and want to identify improvement opportunities
  • User asks where the current process fails, slows down, or creates risk
  • Preparing the input for future-state-and-change-strategy
  • User needs a root cause analysis of a known process failure

When NOT to use this skill

  • No as-is capture exists — run as-is-process-capture first
  • User wants to design the future state immediately — note the gap analysis is needed first, then run future-state-and-change-strategy
  • Do not propose solutions here — record gaps only; solutions belong in the future-state skill

Gap Analysis Framework

scripts/analyze-gaps.mjs analyses the as-is process for the following gap types:

Type 1 — Structural gaps

PatternGap description
Step with no actor_role_idUnowned activity
No start event or end eventMissing process boundary
Input with no sourceUntraced input
Output with no consumerUndelivered output
business_rules emptyUndocumented constraints

Type 2 — Execution gaps

PatternGap description
capture_quality: low on stepPoorly understood activity
Step with notes containing "usually" or "sometimes"Inconsistent execution
Single person as sole performer across >50% of stepsKey-person dependency

Type 3 — Exception gaps

PatternGap description
Decision point with no exception pathUnhandled failure branch
Exception in PIR with no handlingUndefined recovery procedure
Exception path with owner_role_id emptyUnowned error handling

Type 4 — Compliance gaps

PatternGap description
controls empty on processNo governance controls
Approval step with no approver roleMissing segregation of duties
High-risk exception with no escalation pathEscalation path undefined

Severity Classification

SeverityDescription
criticalProcess cannot complete without this being resolved
majorSignificant risk of nonconformity or failure
minorInconsistency or improvement opportunity
observationInformational — no immediate action required

Exception Catalog

For each exception found, record:

  • exception_id — stable identifier
  • description — what goes wrong
  • trigger_condition — what causes this exception
  • affected_steps[] — which act-NNN IDs are affected
  • current_handling — what the process does today (if anything)
  • severity — critical | major | minor | observation
  • recommended_action — brief description (not a full solution)

Handoff Instruction

Pass gap-analysis.yaml and exception-catalog.yaml to future-state-and-change-strategy to prioritise gaps and design the target state.

Also use exception-catalog.yaml to enrich exception_paths[] in process-narrative-authoring.


References

Load on demand:

  • references/gap-analysis-framework.md — gap type taxonomy, severity classification, and root cause analysis templates

Scripts

  • scripts/analyze-gaps.mjs — detects structural, execution, exception, and compliance gaps from as-is-process.yaml

Assets

  • assets/fixtures/gap-analysis-example.yaml — canonical gap analysis for purchase-approval as-is 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.