claude-skill

Summarize a rep's week of activity into key signals

Difficulty

intermediate

Setup time

30min

For

revops · ae

RevOps

Stack

A Claude Skill that ingests one rep’s calls, emails, and Salesforce activity for the last seven days and outputs a six-bullet signal report: what is heating up, what is cooling, where the rep is stuck, and one specific suggestion for next week. Designed for Friday self-review, not surveillance, and built so the rep — not the manager — receives the brief first. The bundle ships with a working SKILL.md plus three reference templates the team edits to match its own qualification framework, signal thresholds, and tone.

When to use

The narrow case this is built for: an AE wants a five-minute scan of their own week before logging off Friday. They have ten to thirty open opportunities, a CRM that mostly tells them what they already know, and Gong calls they didn’t have time to re-listen to. They don’t need a dashboard; they need three things to act on Monday. The skill produces exactly that — three Heating, two Stuck (or Cooling), one specific suggestion — and the format is intentionally short so reps actually read it. Multi-thousand-row activity exports get skimmed and forgotten; six bullets get acted on.

It also works as a managed weekly cadence run by RevOps on behalf of the team, but only if the output still lands in the rep’s DM first and the rep controls whether to forward to a manager. The privacy posture is the load-bearing piece — if it flips to “manager auto-cc,” reps start gaming the input data within a week and the signal collapses.

When NOT to use

Do not use this skill for cross-team pipeline reviews. Twenty reps means twenty invocations and the cost compounds quickly; a Salesforce dashboard does this work cheaper and the manager’s job is to look across, not into, individual weeks. Do not use it for forecast-call prep — Salesforce reports do numeric roll-ups better and the skill is not built to add up dollars. Do not use it as a surveillance tool (“show me what Bob did this week”); the moment the report goes to the manager without the rep running it, you lose the social contract that keeps reps honest about their own activity. And do not use it for account-level deep dives — that’s a different problem solved by the account-research skill, which goes wide on one account rather than wide across one rep’s portfolio.

Don’t run it on windows shorter than three days; there are too few datapoints for the bucketing rubric to fire cleanly and the output reads like noise. Don’t run it on a rep with fewer than five open opportunities — there isn’t enough signal to bucket.

Setup

The artifact bundle is at apps/web/public/artifacts/activity-summarizer-skill/. It contains SKILL.md (the entry point Claude loads) and three fillable references under references/. Walk through these in order:

Read apps/web/public/artifacts/activity-summarizer-skill/SKILL.md end-to-end. The “Method” section names the engineering choices (why parallel pulls, why the precedence rule, why a 300-second call filter); skim past those at your peril because they’re where the false positives get caught.
Edit apps/web/public/artifacts/activity-summarizer-skill/references/qualification-framework.md. Replace the MEDDPICC defaults with your team’s actual framework — BANT, SPICED, your homegrown variant — and crucially, swap the Salesforce field names (Opportunity.Economic_Buyer__c and so on) for the ones your CRM actually uses. Pull your team’s median time-in-stage from a Salesforce report and drop those numbers into the table; they feed the Stuck detection.
Edit apps/web/public/artifacts/activity-summarizer-skill/references/signal-rubric.md. The defaults (≥ 2 multi-threaded touches for Heating, ≥ 10 days no-touch for Cooling, 1.5x median time-in-stage for Stuck) are sane starting points; tune them after a few weeks of running against your historical data. The min_call_duration_seconds knob defaults to 300 to filter Gong voicemails — leave it unless your team holds many sub-five-minute working sessions on real calls.
Edit apps/web/public/artifacts/activity-summarizer-skill/references/sample-output.md. Drop in one or two of your best historical reports (anonymized) so the skill conditions on your team’s tone. The reference also contains a “bad sample” the skill conditions away from — keep both.
Wire up auth. Salesforce: read-only OAuth scoped to Activity, Opportunity, and OpportunityHistory on the rep’s user. Gong: API key scoped to read calls and transcripts the rep was on. Both as MCP servers or direct API calls — the skill itself is transport-agnostic.
Schedule the run. Friday at 16:00 local is the default; the output goes to the rep’s DM via your team’s Slack or email integration. Manager auto-cc is intentionally not a configurable option in the skill; if a manager wants visibility, the rep forwards.

What the skill actually does

Two API calls run in parallel: Salesforce SOQL for Task, Event, and OpportunityHistory rows in the window, and Gong /v2/calls filtered by the rep’s email (Gong indexes by email, not Salesforce user ID — translate first or the call list comes back empty). The Salesforce filter explicitly drops Logged Email Tasks with empty Description because those are CRM hygiene noise, not engagement; ten of those without a single reply does not mean the deal is hot.

Each open opportunity then gets a record with stage, amount, time-in-stage, count of meaningful touches, and the qualification framework’s required fields. Each opportunity is bucketed Heating, Cooling, or Stuck against the thresholds in signal-rubric.md. A precedence rule resolves overlaps — Cooling beats Stuck beats Heating — which kills the most common false positive (a deal whose stage moved forward for procedural reasons but where every other signal is dead). Closed Lost transitions are explicitly excluded from Heating; without that rule, a rep closing out dead deals on Friday afternoon would generate a glowing report.

The render step picks the top three Heating, top two Stuck (or Cooling if no Stuck), and produces one suggestion. The suggestion has three guardrails — it must name an account, name a stage, and name a specific blocker. If the rubric cannot produce a suggestion meeting all three, the skill writes “No suggestion this week — pipeline is clean” rather than fabricating a generic “follow up with stale leads” line.

Cost reality

A single weekly run on a rep with twenty open opportunities lands at roughly 6,000 input tokens and 800 output tokens on Sonnet — about $0.05 per run. Scaling math:

1 rep, weekly: $0.20/month
20 reps, weekly: $4/month
100 reps, weekly: $20/month
100 reps, daily: $140/month
200 reps, daily: $280/month — at this point switch to Haiku ($0.04/run, $112/month) or batch the runs into one prompt with multiple rep contexts

The hidden cost is the API quota on Salesforce and Gong, not Claude. Salesforce’s REST API has a per-org daily limit (typically 15k calls for an Enterprise org); each rep run consumes 4-8 calls depending on activity volume. At 200 reps daily that’s 1,600 calls/day on Salesforce — well within budget but worth checking your org’s usage if you already run other automations heavily.

Time cost: 30 minutes initial setup if your CRM field names are clean, an hour if you have to chase down the right custom field API names. Per-week ongoing: zero — it runs scheduled.

What success looks like

A working installation produces output a rep reads in 90 seconds and that changes at least one Monday morning action. Concretely, after four weeks of running:

The rep’s “stuck” deals show up in the report ≥ 1 week before they show up in the manager’s stale-pipeline review. If not, the median time-in-stage thresholds in qualification-framework.md are too generous — tighten them.
The “one suggestion” line produces an action the rep actually takes ≥ 60% of weeks. If lower, the rubric is producing generic suggestions and the rendering guard isn’t tight enough — check that the skill is rejecting suggestions without a named account, stage, and blocker.
The Cooling bucket flags a deal that subsequently goes Closed Lost ≥ 70% of the time. If the precision is much lower, the cooling thresholds are too sensitive (false positives drown the signal).

These are not vanity metrics — they are the signal that the skill is doing the job it was built for. If they don’t move, the skill is generating Friday reading material, not Friday decisions.

Versus the alternatives

vs. CRM-native digests (Salesforce Einstein Activity Capture, Gong’s own weekly summary). These give you raw activity counts and call summaries but don’t synthesize across the two streams or apply your qualification framework. Einstein will tell you “47 emails this week”; this skill tells you “Acme moved to Proposal because the CTO joined and asked pricing.” Different layer of abstraction.

vs. manual rep-written summaries. A rep who writes their own Friday recap will produce better strategy than this skill — they know the deal context. But 80% of reps don’t write the recap, and the ones who do skip it during quarter-end. This skill produces a 90% as-good summary 100% of weeks, which beats a 100% summary 30% of weeks.

vs. Gong’s own weekly summary email. Gong’s summary is call-only; it misses the email and CRM activity that often carries the cooling signal. It also doesn’t apply your qualification framework, so it can’t surface “stuck because no Economic Buyer named.” Useful complement, not a replacement.

vs. status quo (a manager 1:1 every other Friday). Manager 1:1s catch problems two weeks late and at the manager’s bandwidth. This skill catches them in the rep’s hands the same week, which keeps the action where it belongs.

Watch-outs

Privacy posture: rep-facing only. The default recipient is dm and the skill refuses to send to a manager channel. Auto-cc would change the social contract from “weekly self-review” to “weekly snitch report” — and reps will game the input data within a week. Guard: the skill rejects manager channel IDs in the recipient parameter, and the bundle’s SKILL.md documents this as non-configurable.
Gong transcript quality drives signal quality. International calls, bad audio, and short voicemails produce noisy summaries that feed bad bullets. Guard: min_call_duration_seconds = 300 filters voicemails and test calls; the skill also reads Gong’s per-call transcriptionConfidence field and drops anything below 0.6.
Activity definition drift. “Logged Email” with no body and no reply is not engagement; it’s CRM hygiene theater. Ten of those entries does not mean the deal is hot. Guard: the SOQL filter requires non-empty Description on Tasks and explicitly ignores Tasks where Subject matches the team’s auto-logged patterns (/^(Email\: |Logged via )/).
Suggestion fatigue. The “one suggestion for next week” line drifts toward generic (“follow up with stale leads”) when the rubric is loose. Guard: the rendering step rejects any suggestion that does not name an Account, a Stage, and a specific Blocker. If the rubric cannot produce one, the skill writes “No suggestion this week — pipeline is clean” rather than padding.
Stage-changes-as-signal can lie. A rep moving a deal to Closed Lost shows up as a stage change but should not feed Heating. Guard: bucketing rules treat stage rollbacks and Closed Lost transitions explicitly under Cooling, never Heating.
The skill does not replace a deal review. It surfaces signals, not strategy. A Stuck flag tells the rep “Initech is past median time-in-stage with no Economic Buyer”; it does not tell the rep what to do about it beyond the one suggestion. Treat it as triage, not coaching.

Stack

Salesforce — activity, opportunity, and stage-history source of truth
Gong — call transcripts, talk-listen ratios, flagged buying questions
Claude — signal extraction, framework-aware ranking, rendering against the bundle’s tone reference

Edit this page on GitHub

Files in this artifact

Download all (.zip)

---
name: activity-summarizer
description: Summarize one rep's last seven days of Salesforce activity, Gong calls, and email touches into a six-bullet signal report — what is heating up, what is cooling, where the rep is stuck, one suggestion. Designed for Friday self-review, not surveillance.
---

# Activity summarizer

## When to invoke

Use this skill on Friday (or any chosen weekly cadence) for a single rep's pipeline. Inputs are a Salesforce user ID and a seven-day window; output is a Markdown signal report scoped to that rep's open opportunities. The brief is rep-facing first and lands in the rep's DM, not the manager channel.

Do NOT invoke this skill for:
- Cross-team pipeline reviews (use a dashboard, not a Skill — N reps means N invocations and the cost compounds)
- Manager surveillance ("show me what Bob did this week") — privacy posture is broken if the rep didn't run it themselves
- Account-level deep dives (use the `account-research` skill instead)
- Forecast-call prep where you need numeric roll-up (Salesforce reports do this better and cheaper)
- Windows shorter than three days — too few datapoints for the rubric to fire cleanly

## Inputs

- Required: `rep_user_id` — Salesforce user ID (not the email; the API treats them differently)
- Required: `window_days` — integer, defaults to 7. Skill rejects values < 3 or > 28
- Optional: `framework` — one of `meddpicc`, `bant`, `custom`. Defaults to `meddpicc`. If `custom`, the skill loads `references/qualification-framework.md` and uses that as the lens
- Optional: `recipient` — `dm` (default) or `email`. Manager auto-cc is intentionally not an option
- Optional: `min_call_duration_seconds` — defaults to 300 (filters Gong noise; see watch-outs)

## Reference files

The skill loads these from `references/` on every run. Replace template contents with your team's actuals before first production use — the skill works without edits but the output reads generic.

- `references/qualification-framework.md` — the rubric the skill uses to decide "where is the deal stuck." Defaults to a MEDDPICC scaffold; swap in your team's variant
- `references/signal-rubric.md` — the thresholds the skill uses to bucket activity as heating / cooling / stuck. Has knobs for what counts as a "meaningful touch" and what triggers a "stuck" flag
- `references/sample-output.md` — a worked example the skill conditions on for tone, length, and formatting. Edit this when you want to nudge the voice (e.g. blunter, less hedged)

## Method

The four sub-tasks run in order. Steps 1 and 2 fetch in parallel; steps 3 and 4 are strictly sequential because ranking depends on synthesis.

### 1. Pull activity streams

Run two API calls in parallel:

- **Salesforce**: SOQL for `Task` and `Event` records where `OwnerId = rep_user_id` and `ActivityDate` within the window, plus `OpportunityHistory` rows for stage changes on opportunities owned by the rep. Filter Tasks where `Type IN ('Email', 'Call', 'Meeting')` — drop "Logged Call" with empty `Description` (these are usually CRM hygiene noise, not engagement)
- **Gong**: `/v2/calls` filtered by `participants.userId = rep_email` (Gong indexes by email, not Salesforce user ID — translate first), within the window. For each call, pull `summary`, `talkRatio`, `nextSteps`, and `flaggedQuestions` from `/v2/calls/{id}/extensive`. Drop calls where `duration < min_call_duration_seconds` — short calls are usually voicemails or test calls and produce noisy signals

If a stream fails, continue with the other and tag the report header `[Salesforce unavailable]` or `[Gong unavailable]`. Never silently produce a partial report — the rep must know what's missing.

### 2. Join to opportunity context

For each open opportunity owned by the rep, build a record with: stage, amount, close date, last stage change, count of activities in window, count of calls in window, and the qualification framework's required fields (e.g. for MEDDPICC: Metrics, Economic buyer, Decision criteria, etc.). Pull the framework field names from `references/qualification-framework.md` — do not hardcode field names in the skill.

### 3. Bucket per opportunity

For each opportunity, apply the signal rubric (see `references/signal-rubric.md`):

- **Heating**: stage advanced this week OR ≥ 2 multi-threaded touches OR a flagged buying-question on a call
- **Cooling**: no rep-side touch in ≥ 10 days AND last prospect reply > 14 days OR stage rolled back
- **Stuck**: open in current stage > 1.5x the team's median time-in-stage AND framework field gap (e.g. no Economic Buyer named)

A deal can only sit in one bucket. Order of precedence: Cooling > Stuck > Heating. This prevents the "heating but actually broken" false positive that surfaces when stage advanced for procedural reasons but signal is otherwise dead.

### 4. Rank and render

Pick the top three Heating, top two Stuck (or Cooling, if no Stuck), and produce one suggestion. The suggestion must name a specific deal, a specific stage, and a specific blocker — never a generic "follow up with stale leads" line. If the rubric cannot produce a deal-specific suggestion (e.g. all deals are healthy), the skill writes "No suggestion this week — pipeline is clean" rather than padding.

Render to the format below and ship.

## Output format

```markdown
# Week of {YYYY-MM-DD} — {Rep first name}

## Heating
1. **{Account}** — {one-sentence what changed}. Signal: {citation, e.g. "Gong call 2026-04-29: economic buyer joined, asked about pricing tiers"}
2. **{Account}** — ...
3. **{Account}** — ...

## Stuck
1. **{Account}** — {one-sentence what is blocked}. In {stage} for {N} days (team median: {M}). Missing: {framework field, e.g. "no Economic Buyer named"}
2. **{Account}** — ...

## Suggestion for next week
{Single specific action tied to a named deal and a named stage}. e.g. "On Acme, you have a technical evaluator but no Economic Buyer; propose a 30-min exec brief with their CFO."

## Sources
- Salesforce activities: {N} tasks, {M} events, {K} stage changes
- Gong calls: {N} (filtered {dropped} below {threshold}s)
- Window: {start} → {end}
```

## Watch-outs

- **Privacy posture: rep-facing only.** Default `recipient` is `dm` and the skill refuses to send to a manager channel. If a manager wants visibility, the rep forwards. Auto-cc would change the social contract from "weekly self-review" to "weekly snitch report" — and reps would game the input data within a week
- **Gong transcript quality.** International calls and bad audio produce noisy summaries that feed bad signals. Guard: `min_call_duration_seconds = 300` filters voicemails and test calls; the skill also reads Gong's per-call `transcriptionConfidence` field and drops anything below 0.6
- **Activity definition drift.** "Logged Email" with no body and no reply is not engagement; it's CRM hygiene theater. Guard: the SOQL filter requires non-empty `Description` on Tasks and ignores Tasks where `Subject` matches the team's auto-logged patterns (`/^(Email\: |Logged via )/`)
- **Suggestion fatigue.** The "one suggestion" line drifts toward generic ("follow up with stale leads") when the rubric is loose. Guard: the rendering step rejects any suggestion that does not name an Account, a Stage, and a specific Blocker. If the rubric cannot produce one, the skill writes "No suggestion this week" rather than fabricating
- **Token cost compounds with rep count.** A single weekly run is ~6k input + ~800 output tokens (~$0.05 on Sonnet). Twenty reps × four weeks = ~$4/month, fine. Two hundred reps × daily = ~$280/month, no longer cheap; switch to Haiku or batch
- **Stage-changes-as-signal can lie.** A rep moving a deal to "Closed Lost" shows up as a stage change but should not feed Heating. Guard: bucketing rules treat stage rollbacks and Closed-Lost transitions explicitly under Cooling, never Heating

# Qualification framework — TEMPLATE (MEDDPICC default)

> Replace this template's contents with your team's actual qualification
> framework. The activity-summarizer skill reads this file on every run
> to decide which Salesforce fields signal a "stuck" deal. Without your
> real field names, the skill defaults to a MEDDPICC scaffold that may
> not match your CRM schema.

## Framework name

MEDDPICC (replace with `BANT`, `SPICED`, your team's homegrown variant, etc.)

## Required fields

For each letter / criterion, list the Salesforce field that holds it. The skill checks these fields per opportunity; missing values feed the "stuck" bucket via the signal rubric.

| Criterion | Salesforce field | What "filled" looks like |
|---|---|---|
| Metrics | `Opportunity.Metrics__c` | A quantified business outcome the buyer cares about |
| Economic buyer | `Opportunity.Economic_Buyer__c` | Named individual with budget authority — not the champion |
| Decision criteria | `Opportunity.Decision_Criteria__c` | Written list of how the buyer will choose |
| Decision process | `Opportunity.Decision_Process__c` | Sequence of meetings/approvals required to close |
| Paper process | `Opportunity.Paper_Process__c` | Procurement, security review, legal — sequenced |
| Identified pain | `Opportunity.Identified_Pain__c` | The pain in the buyer's words, not the rep's |
| Champion | `Opportunity.Champion__c` | Named individual who sells internally on the rep's behalf |
| Competition | `Opportunity.Competitors__c` | Named competitors in the deal, including "do nothing" |

## Stage-by-stage minimums

Per stage, which fields MUST be filled before the deal is allowed to advance. The skill flags any deal that has advanced past the minimum without the fields.

| Stage | Required fields |
|---|---|
| Discovery | Identified pain, Champion |
| Qualification | + Economic buyer, Metrics |
| Proposal | + Decision criteria, Decision process |
| Negotiation | + Paper process, Competition |
| Closed Won/Lost | (no further requirements) |

## Time-in-stage medians (for "stuck" detection)

Replace these with your team's actuals from a Salesforce report. The skill flags a deal as stuck when time-in-stage exceeds 1.5x the median below AND a required field for that stage is empty.

| Stage | Median days |
|---|---|
| Discovery | 14 |
| Qualification | 21 |
| Proposal | 14 |
| Negotiation | 10 |

## Disqualifiers

Single conditions that drop a deal out of the active pipeline regardless of field completeness. The skill surfaces these prominently in the report.

- No champion identified after 30 days in pipeline
- Economic buyer never met after Proposal stage entered
- Competitor named is one we historically lose to (list here): {Competitor 1}, {Competitor 2}

## Last edited

{YYYY-MM-DD}

# Sample output — TEMPLATE

> Replace the example below with one or two of your team's best
> historical reports (anonymized). The activity-summarizer skill
> conditions on this file for tone, length, and formatting. Edit
> when you want to nudge the voice — blunter, less hedged, shorter
> bullets, etc.

## Tone calibration notes

- Bullets are one sentence. If you need two sentences, the bullet is doing too much.
- Cite the source inline. "Gong call 2026-04-29" beats "according to recent activity."
- The suggestion line names a person if possible: "propose a 30-min exec brief with their CFO" beats "engage the executive sponsor."
- Avoid hedging adverbs: `seems`, `appears`, `potentially`. The skill has the data; either say it or don't include the bullet.

## Example

```markdown
# Week of 2026-04-26 — Sam

## Heating
1. **Acme Robotics** — moved to Proposal after technical evaluator
joined the demo. Signal: Gong call 2026-04-29, CTO asked about
SAML rollout timeline and pricing for 200 seats.
2. **Northwind Health** — champion forwarded the security questionnaire
without prompting. Signal: inbound email 2026-04-30 from
j.lee@northwind.example with attached SIG Lite.
3. **Globex Logistics** — second meeting set with Director of Ops
joining. Signal: Calendar event 2026-05-02, three external
attendees (champion + two new contacts).

## Stuck
1. **Initech Corp** — in Qualification for 38 days (team median: 21).
Missing: Economic Buyer field empty. Champion (Marcus, Ops Lead)
has not been able to surface budget owner.
2. **Stark Industries** — in Negotiation for 22 days (team median: 10).
Missing: Paper Process — procurement timeline never mapped.

## Suggestion for next week
On Initech, ask Marcus directly in Monday's sync: "Who signs off on a
$50k Ops tooling spend this fiscal year?" If he can't name the person,
escalate to a paid pilot path that bypasses procurement.

## Sources
- Salesforce activities: 47 tasks, 12 events, 4 stage changes
- Gong calls: 9 (filtered 3 below 300s)
- Window: 2026-04-26 → 2026-05-02
```

## What a bad sample looks like (for contrast)

The skill should NEVER produce output like this — keep this in the reference file as a negative example so the model conditions away from it:

```markdown
# Weekly Update

## Things That Are Going Well
- Several deals appear to be progressing
- The rep was active across multiple accounts this week
- Engagement seems strong

## Areas of Focus
- Some deals could use attention
- Consider following up with stale leads

## Suggestion
Continue the great work and keep the momentum going!
```

Failure modes shown above: vague accounts ("several"), hedging ("appears", "seems"), generic suggestion ("keep the momentum"), no citations, no specifics. The signal rubric and rendering guards in the skill exist to refuse output like this.

## Last edited

{YYYY-MM-DD}

# Signal rubric — TEMPLATE

> Replace this template's contents with your team's actual thresholds.
> The activity-summarizer skill uses these to bucket each opportunity
> as Heating, Cooling, or Stuck. Defaults below are sane starting
> points; tune after a few weeks of running the skill against your
> historical data.

## What counts as a "meaningful touch"

Not all activities are signal. The skill counts a Task or Event as a meaningful touch only if it meets one of the conditions below. Edit this list to match your CRM hygiene reality.

- Outbound call with a logged disposition AND non-empty `Description`
- Inbound or outbound email where the prospect replied within 7 days
- Meeting (Event type) with at least one external attendee
- Gong call ≥ {min_call_duration_seconds, default 300} seconds with `transcriptionConfidence` ≥ 0.6

Explicitly does NOT count:

- "Logged Email" entries with empty `Description` (auto-logged hygiene)
- Tasks with `Subject` matching `/^(Email\: |Logged via )/`
- Calendar invites without a confirmed external acceptance
- One-way LinkedIn messages without a reply

## Heating thresholds

A deal is Heating if ANY of:

- **Stage advancement**: `OpportunityHistory.StageName` moved forward this window AND the new stage's required framework fields are filled
- **Multi-threading**: ≥ 2 distinct external participants on calls / meetings this window (counts new contacts joining, not the same champion repeated)
- **Buying questions**: a Gong call this window contains a question flagged in Gong's `flaggedQuestions` field tagged as `pricing` / `timeline` / `procurement`
- **Champion proactivity**: champion sent ≥ 1 inbound email this window without rep prompting (detect via `Task.WhoId = champion AND Task.CreatedById = rep`)

## Cooling thresholds

A deal is Cooling if ALL of:

- No rep-side meaningful touch in ≥ 10 days
- Last prospect reply > 14 days ago
- OR `OpportunityHistory.StageName` rolled backward this window
- OR stage transitioned to `Closed Lost` (always Cooling, never Heating)

## Stuck thresholds

A deal is Stuck if BOTH of:

- Time in current stage > 1.5x team median for that stage (see qualification-framework.md for medians)
- At least one required framework field for the current stage is empty

## Bucket precedence

A deal can sit in only one bucket per week. If it qualifies for multiple, the skill applies this precedence (highest wins):

1. Cooling — if cooling, the heating signals are noise; surface the cooling
2. Stuck — if stuck and not cooling, surface the structural problem
3. Heating — only if neither cooling nor stuck

This precedence prevents the "stage advanced for procedural reasons but the deal is actually broken" false positive.

## Suggestion guardrails

The "one suggestion for next week" line at the end of the report MUST:

- Name a specific account (no "follow up with stale leads")
- Name a specific stage (no "move things forward")
- Name a specific blocker pulled from the qualification framework gaps

If the rubric cannot produce a suggestion meeting all three constraints, the skill writes "No suggestion this week — pipeline is clean" rather than fabricating one.

## Last edited

{YYYY-MM-DD}