meridian-advisory

Example: Meridian Advisory (Brightfield Q3 Operations Audit)

A small, fictional professional-services / consulting engagement used to demonstrate that CM-Stack's Five Pillars apply beyond software delivery. Where examples/atlas-api/ is a fictional software project, this example is a fictional consulting engagement: Meridian Advisory running an accounts-payable operations audit for a client, Brightfield Logistics.

This is not a working codebase or a real engagement. It's a folder of realistic non-code inputs (a deliverables tracker, a rework/findings log, a client-escalation log, a workstream throughput export, team notes, a billing proposal, and prior scorecard history) that stand in for the "real" sources each skill's ## Inputs section lists -- just from a consulting practice instead of a software repo.

Try it

Point any CM-Stack-installed agent at this folder and ask it to run a skill, e.g.:

"Load CM-Stack. Run /clarity on the engagement described in examples/meridian-advisory/."

Which fixture feeds which skill

Skill	Fixture(s)	What's in it	Software-project analog
/clarity	vision.md	A partial engagement charter -- vision exists informally, no written plan below the Discovery phase, a real (if narrow) client steering-committee scorecard. Expect a Yellow/Red/Green mix.	atlas-api/vision.md
/quality	deliverables.json, findings.json	5 client deliverables (3 sent via an unreviewed "rush" path) and 3 client-found corrections traced back to that path.	atlas-api/prs.json + defects.json
/stability	incidents.md	4 client escalations in 90 days, only 1 with a written postmortem, no data-refresh check on the rush path.	atlas-api/incidents.md
/postmortem	incidents.md (Escalation 4)	The one escalation in the log that never got a postmortem -- feed just that entry in for a fast-path single-escalation writeup.	atlas-api/incidents.md (Incident 4)
/speed	throughput.csv	12 weeks of closed workstream-item exports: throughput, cycle time, and one oversized epic-tagged item.	atlas-api/throughput.csv
/decompose	throughput.csv (the AP process redesign epic row)	One undersized-ticket, oversized-scope epic ready to be broken down.	atlas-api/throughput.csv (bulk-export epic)
/team	team-notes.md	Retro notes, review-style conflict, and a new analyst routing every question through the partner.	atlas-api/team-notes.md
/onboarding	team-notes.md (new-hire section)	The same new analyst, reframed as a ramp-up-plan request instead of a health check.	atlas-api/team-notes.md (new-hire section)
/values-check	client-proposal.md	A proposal to bill corrective rework as a separately billable workshop -- a values tension baked in on purpose.	atlas-api/client-proposal.md
/scorecard	All of the above, plus scorecard-history.jsonl	Runs all five pillar checks and demonstrates the Trend column against two prior recorded runs.	atlas-api/scorecard-history.jsonl

Why the data looks the way it does

Every fixture has at least one deliberate finding baked in (an unreviewed "rush" deliverable path, a missing postmortem, an overloaded partner, a billing values tension) so a skill run against it always has something concrete to report -- instead of a bland "everything's fine." That mirrors how these skills are meant to be used: pointed at real, messy engagement data, not a clean demo.

Extending this example

Feel free to edit these fixtures to try edge cases -- e.g., delete scorecard-history.jsonl to see how /scorecard behaves with no prior history, or add a second escalation to incidents.md to see /postmortem flag a repeat failure mode.