cm-compound

/cm-compound — Capture a Learning

Append a single, schema-valid learning entry to .agents/learnings/<category>.md so future marketing work in this category starts from prior evidence, not a blank page.

This command is the write side of the compounding loop. The read side is the Prior Learnings Consulted section that wired skills run before producing output. The schema both sides obey is defined in skills/_LEARNINGS_SCHEMA.md — that file is the source of truth; this command must conform to it.

When to use

Run /cm-compound immediately after:

• A campaign, page, launch, or experiment produced a clear result (good or bad).
• An A/B test reached significance — whether it won or lost. Losing tests are often higher-signal than winning ones.
• A round of customer research surfaced a non-obvious pattern.
• A surprise occurred — something behaved opposite to expectation.

Do not run it for routine deliveries that taught nothing new, or for opinions without evidence. The bar is captured evidence, not vibes.

What it does

1. Walks the user through the six required fields for a learning entry.
2. Validates each field against the schema (_LEARNINGS_SCHEMA.md §"Required entry structure").
3. Resolves the correct category file (.agents/learnings/<category>.md), creating it with valid frontmatter if it does not exist.
4. Writes the new entry above existing entries (reverse-chronological).
5. Updates frontmatter (last_updated, entries_count).
6. Reports what was captured and which wired skills will now consume it.

Process

Step 1: Confirm there is a real learning to capture

Ask the user:

• What worked, what didn't, what surprised you, what would you do differently?

If the answer is generic ("the campaign went well") or non-falsifiable ("the brand feels stronger"), stop. Ask for the specific outcome, number, or quote that makes this a learning rather than an impression. A learning without evidence is noise.