Turn feedback and outcomes into proposed skill fixes you approve.
“Our AI skills keep making the same misses, and nobody has time to go fix them. Where do we start?”
Reads QA findings, feedback, and outcomes, then proposes concrete changes to your skills and scoring. You approve, nothing self-edits.
What this skill does
Turns the signals your system is already producing (quality-check findings, feedback reactions, and real outcomes) into a short list of concrete proposed changes to your own skills, scores, and workflows. Each one arrives as a reviewable proposal with the data behind it. You approve; the system updates. It never edits itself. This is the layer that makes a library of skills improve over time instead of drifting.
Inputs
- Works today with: your quality-check findings and any feedback you have collected (thumbs, notes, outcomes). Paste them and the skill drafts the changes.
- More powerful connected to your feedback log: it reads reactions, click-through, and re-asks automatically instead of you summarizing them.
- Sharper with outcome data: cross-references what a skill predicted against what actually happened (did the AT_RISK deals slip, did the high-fit accounts convert).
- Sharper with a version-control connector: writes each proposed change as a reviewable diff you can approve in one click.
How it works
- 1Read both feedback streams
Implicit signals (reactions, click-through, re-asks, outcome attribution) and explicit signals (thumbs plus structured reasons). Neither alone is enough. A single thumbs-down is noise; the same pattern across both streams is a signal worth acting on.
- 2Attribute outcomes honestly
Cross-reference each skill's predictions to what actually happened, controlling for cohort confounds (window size, segment mix, sample size). Never claim a lift without accounting for what else moved. Small samples lie, and a self-improving system that believes its own inflated numbers gets worse, not better.
- 3Propose, never merge
Every change ships as a reviewable proposal with a diff and a rationale tied to data. Four kinds:
- Tighten a rubric: when two tiers converge on the same outcome, collapse or re-cut them.
- Update a trigger or definition: when language in the field has shifted (a new tool named in calls, a new phrase reps use).
- Propose a new workflow: when the same sequence of skills fires together often enough to bundle.
- Retire a skill: when it is unused past RETIRE_DAYS or persistently below ACCURACY_FLOOR.
- 4Name the one thing to review first
Every pass ends by surfacing the single highest-priority change, usually the skill whose accuracy dropped below the floor, with the specific cases to investigate.
Output format
EVOLUTION PASS - week of May 25
4 proposed changes ready for review
1. Tighten the fit rubric
STRONG_FIT converted 82%, FIT 79% (too close). Collapse to one tier
plus an "above-baseline" override.
2. Add a term to the tech-stack list
A tool showed up in 12 calls this month vs 4 last quarter.
3. Propose a new workflow: renewal prep
The same 3 skills fired in the same order 17 times. Bundle them.
4. Retire an unused skill
Invoked twice in 180 days, both tests. Deprecate.
Accuracy (trailing 90 days):
Fit scoring 82%
Deal health 78%
Churn predict 67% <- below the 75% floor
Review first: churn prediction at 67%. Tighten it or lower its confidence.
Tips
- Every proposal has a rationale tied to data. Not "tighten this rubric" but "STRONG_FIT converted at 82% and FIT at 79%, too close to differentiate. Collapse to one tier plus an above-baseline override."
- Nothing auto-merges. Every change is a reviewable proposal you approve before anything updates.
- Outcome claims are honest. No "we improved win rate by 5%" without controlling for cohort confounds.
- A skill is retired only on evidence: low invocation past the window, or precision below the floor, never a hunch.
Make revenue reporting a weekly habit that drives action.
Pairs a where-we-stand-and-why write-up with a list of hot leads and deals to work now, so the report ends in moves, not a screenshot.
Get one forecast-aware brief that names today's priorities.
Composes deal risk, pipeline, coaching, and conversation reads into a single morning brief, in rep or leader mode.