Walk into every 1:1 with the gap already found.
Turns rep data into a specific coaching priority per person, plus the team-level pattern underneath them.
Inside: The per-rep gap logic and the team-pattern rollup.
Install it in one line, or paste it in.
~/.claude/skills/ and runs automatically when it is relevant.Connect your context. Set it to your motion.
opportunities, stages, forecast categories, close dates, and notes, live.
meeting quality from transcripts and real follow-up cadence, not just counts.
Map your own methodology to the completeness check. If your framework has named steps or required fields, list them as the methodology fields and the skill counts completeness against those. The method does not assume any one framework.
| Set this | What it is | Default / Example |
|---|---|---|
| CRM | Where opportunities, stages, and notes live | Any CRM with opportunity and activity objects |
| Methodology fields | The fields or steps your completeness check counts | Your qualification framework's required fields |
| Activity sources | Where meetings, calls, and follow-ups are logged | Meeting tool + CRM tasks/events |
| Win-rate segments | How you split wins to find where a rep wins vs loses | Segmentchanneldeal size |
| Completeness target | The team bar for methodology completeness | 80% |
| Win-rate flag threshold | Win rate below which a segment gets flagged | 40% |
| Multi-thread target | Contacts per deal you expect | 3+ |
| Stage-sticker rule | When a deal counts as stuck | Longer than the rep's own median in that stage |
Everything the skill does, in full.
This skill turns rep data into per-rep coaching priorities. It reads each rep's pipeline, activity, and win history, then surfaces a specific gap for each person plus the team-level patterns underneath them. It answers "who needs help and on what?" with a named topic per rep, not a vague verdict. It watches the people, not the system.
- 1Per rep, the skill computes:
- Methodology completeness rate. The share of open opps that pass your check, plus the field the rep misses most.
- Activity quality. Meeting count times meeting quality (from transcripts) times follow-up cadence. High count of low-quality touches does not score well.
- Deal velocity. Average days in each stage. Surfaces deals sitting longer than the rep's own median.
- Win rate by segment. Where the rep wins and loses. Small samples flagged as small.
- Stale-deal concentration. The share of the book going dark or stale.
- Coaching theme detection. Patterns that hold across the team, not one rep.
The team view rolls these up against your targets and names the reps outside the band.
- Per-rep gap is specific. Not "needs help with methodology," but "completeness 14% (1 of 7 opps), most-missing step is the decision-dynamics field."
- Coaching themes are team-level and statistically meaningful. "3 of 5 reps below 40% mid-market win rate" beats "everyone needs to do better."
- Pre-1:1 brief is forecast-aware. It knows the next forecast call and what the rep called last week.
- Small samples are labeled with their n.
COACHING PRIORITIES, Week of June 1 TOP PRIORITY: Rep A Methodology completeness: 14% (1 of 7 opps), lowest on team Most-missing step: decision-dynamics (5 of 7 opps) Stage-stickers: 3 opps in Solution Validation past 21 days (median 9) 1:1 focus: methodology + multi-thread + activity cadence Rep B, strong but watch: Completeness 87% (highest), win rate 71% (small sample n=7) Concern: working hard, but pipeline math does not get there 1:1 focus: pipeline-creation strategy, not execution TEAM THEMES: 1. Completeness target 80%, team avg 56%. Group training. 2. 3 of 5 reps below 40% mid-market win rate. ICP or messaging check. 3. Multi-thread averaging 1.4 contacts/deal (target 3+).
Defaults to re-tune: completeness target 80%, win-rate flag 40%, multi-thread target 3+, stage-sticker rule judged per rep against their own median. Any win rate carries its n so a hot streak is not mistaken for a trend. Activity quality depends on the meeting tool; with none connected, the skill falls back to CRM activity counts and says so.
Where an operator takes this next.
The read is step one. Here's where an operator takes it once the manual version proves out.
You built the read once; now it runs itself.
Point a scheduled Claude task at Salesforce and Gong the morning of 1:1 day and post each rep's brief to their manager in Slack.
Have the task re-run weekly and flag any rep whose completeness or win rate drops two weeks running.
Feed recurring gaps into a content-brief skill to spin up the enablement session the data is actually asking for.
One skill is the on-ramp.
A single skill does one job. Chained into a playbook, or run as a full build, it becomes a system. Here is where this one plugs in.