Skip to content
Back to skills

Audit Outcomes

ASecurity

Trace shipped product outcomes back to the original problem and metrics, PDLC's equivalent of backpropagation. Catches drift where the spec was built faithfully but stopped being the right thing.

  • 10 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 6, 2026
researchgorails

Security analysis

A100/100

Scanned October 6, 2026

npx -y skills add tomzx/agents --skill audit-outcomes --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Audit Outcomes?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Audit Outcomes
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tomzx-audit-outcomes/badge)](https://www.skillsdirectory.com/skills/tomzx-audit-outcomes)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: audit-outcomes
description: Trace shipped product outcomes back to the original problem and metrics, PDLC's equivalent of backpropagation. Catches drift where the spec was built faithfully but stopped being the right thing.
argument-hint: "[initiative-id]"
---

# Audit Outcomes

Walks the PDLC artifact chain in reverse to verify traceability from start to finish: does what shipped trace to a validated opportunity, and do the health metrics justify the original decision? This is the PDLC equivalent of `propagate-changes`, but it judges *outcome coherence*, not spec-to-code consistency.

## Prerequisites

- Apply the shared PDLC conventions in `skills/pdlc/references/shared.md`.
- A shipped or measured initiative (`$1`), or scan all initiatives under `.pdlc/initiatives/`.

## Steps

1. For the target initiative, gather the chain: `opportunity-tree.md` → `experiment-result.md` → `prd.md` → `acceptance-contract.md` → `health-report.md` → `feedback-loop.md`, plus all decision records.
2. Walk it in reverse, from `health-report.md` back to `problems.md`, checking each link:
   - Do the measured outcomes map back to the success metrics defined in `prd.md` / `analytics-spec.md`?
   - Were guardrail metrics defined up front and checked after launch? (A missing guardrail is itself a finding.)
   - Does the shipped scope trace to the acceptance contract, which traces to the PRD outcomes, which trace to a validated opportunity?
   - Does each gate decision still look defensible when reviewed later?
3. Score each link `aligned` / `drifted` / `broken`. A link is `drifted` when the artifact evolved without updating the chain; `broken` when the outcome contradicts the premise.
4. For any `drifted` or `broken` link, regress the relevant gate decision to `pivot` (record in a new decision record) so the forward loop resyncs it.
5. Produce the audit report.

## Findings Categories

- **Traceability gaps** — a shipped outcome with no upstream opportunity, or an opportunity with no measured outcome.
- **Metric drift** — success metrics changed without re-validating the opportunity; guardrails missing or unmeasured.
- **Decision rot** — a gate decision that no longer holds given new evidence.
- **Premature shipping** — launched before the gate chain was complete.

## Output Format

Write the report to `.pdlc/audit-report.md` (repo-only, never mirrored) and summarize:

```
## PDLC Outcome Audit: INIT-N

Chain: problems → opportunity → experiment → prd → acceptance → health → feedback
Links: 6 aligned, 1 drifted, 0 broken

### Findings
- [drifted] Success metric SM-2 has no corresponding measurement in health-report.md
- [decision-rot] Discover gate proceeded on an assumption since invalidated

### Actions
- Regressed the Strategy gate to pivot; re-run set-goals to redefine SM-2
```

## Outcome

If `$OUTCOME_YAML` is set:

| Verdict | When |
|---|---|
| `aligned` | Chain traces from start to finish; no drift |
| `drift-detected` | One or more links drifted or rotted; gates regressed |
| `broken` | A link is broken; major rework or kill warranted |

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…