deal-inspection-coach
Skill14 starsChanged 8 months agoMITView on GitHub
Inspect one live opportunity and produce an evidence-backed manager view of stage validity, deal risk, missing proof, and next actions. Use for a specific deal review, stalled-deal diagnosis, or manager inspection. Use forecast-risk-brief for portfolio forecasting, call-review-coach for seller behavior on one call, and mutual-action-plan-builder for a buyer-shared execution plan.
In this repository38 other files it gives its agents.
- AGENTS.mdAGENTS.md
- account-brief-builderSkill
- battlecard-builderSkill
- call-insights-to-objectionsSkill
- call-review-coachSkill
- case-study-extractorSkill
- certification-program-builderSkill
- content-gap-analysisSkill
- content-governance-systemSkill
- discovery-and-demo-structureSkill
- discovery-rubric-auditorSkill
- enablement-house-styleSkill
- enablement-impact-storySkill
- enablement-metrics-and-instrumentationSkill
- enablement-program-designSkill
- enablement-routerSkill
- executive-briefing-builderSkill
- field-feedback-synthesizerSkill
- forecast-risk-briefSkill
- manager-coaching-cadenceSkill
- mutual-action-plan-builderSkill
- objection-library-builderSkill
- onboarding-program-builderSkill
- onboarding-to-value-playbookSkill
- one-pager-and-slide-outlineSkill
- partner-enablement-packageSkill
- pipeline-stage-definition-and-exit-criteriaSkill
- product-launch-enablementSkill
- proposal-rfp-orchestratorSkill
- qbr-ebr-builderSkill
- quarterly-enablement-plannerSkill
- release-notes-to-seller-updatesSkill
- renewal-and-expansion-enablementSkill
- revenue-enablement-contextSkill
- roleplay-scenario-builderSkill
- talk-track-builderSkill
- value-prop-and-positioningSkill
- win-loss-synthesisSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Ask only for the inputs that change the diagnosis:
- Distinctive: line 27
If a fact is missing, leave it unknown.
- Distinctive: line 31
Read references/deal-inspection-framework.md before rating evidence, stage validity, or risk.
- Distinctive: line 64
Keep recommendations internal unless customer-facing material is requested.
- Distinctive: line 73
No invented CRM facts, amounts, dates, or commitments.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Deal inspection coach
Review one opportunity against what the buyer has confirmed, then identify the action most likely to resolve its next buying decision.
A good inspection tells a manager what the buyer has confirmed, what is still unknown, and the one move that changes the deal. If the user wants a portfolio forecast, use forecast-risk-brief. If they want a buyer-shared plan, use mutual-action-plan-builder.
Buyer proof. "Economic buyer confirmed this is funded this quarter. Security is in their queue with a named owner. Next step is their commercial review on 3 Sep."
Seller activity. "Twelve emails last week. Demo completed. Next step is follow up. Stage is Proposal because the deck went out."
Make buyer confirmation visibly distinct from the seller's interpretation.
Inputs
Ask only for the inputs that change the diagnosis:
- The one opportunity, as-of date, claimed stage, and inspection objective
- The evidence packet: CRM, buyer comms, calls, MAP, proposal, procurement
- The team's stage criteria and qualification method, if they have one
- Whether the output is internal-only
If a fact is missing, leave it unknown. Do not invent CRM fields, amounts, dates, stakeholders, or commitments.
Supporting material
Read references/deal-inspection-framework.md before rating evidence, stage validity, or risk. Read references/source-system-guide.md when evidence comes from CRM, conversation intelligence, or email summaries.
Procedure
- Name the job. One opportunity. One decision: validate stage, recover momentum, test forecast confidence, or choose an intervention. Done when you can say which, and why the others wait.
- Build the evidence ledger. For each material claim: source, source date, buyer-confirmed or internally asserted, and current / stale / missing / conflicted. Done when every claim you will use has a status.
- Test stage validity. Match evidence to the team's exit criteria. If they have none, report buying-path readiness. Do not invent a stage gate. Done when each criterion is met, not met, conflicted, stale, or unknown.
- Walk the buying path. Problem priority, value, stakeholders, criteria, process, alternatives, execution, timing. An unanswered question is not negative evidence. Done when you can name the open buyer decision that matters most.
- Separate risk from gap. A risk is a supported condition that can kill or slip the deal. A gap is a consequential unknown. They need different actions. Skip a numeric score unless the org supplied a model.
- Pick the next moves. Few actions. Each needs an owner, the buyer progress it creates or the unknown it closes, and a verification check. Label dates as proposed unless the buyer confirmed them.
- Prepare the manager's review. The question to ask, the evidence to open, the decision to make, and when to escalate. Recommend stage or CRM changes; do not apply them.
For one recorded call use call-review-coach. For a book of deals use forecast-risk-brief.
What to return
Return a focused answer to the deal question. For a full review, include:
- Inspection decision: objective, as-of date, claimed stage, stage-validity finding, evidence confidence
- Evidence ledger for material claims
- Buying-path review: confirmed progress and open decisions
- Risk register: risk or gap, consequence, urgency, controllability, confidence, reassess trigger
- Priority actions with owner, buyer progress, timing status, verification
- Manager coaching: questions, focus, escalation
- Assumptions, if you had to make any
Keep recommendations internal unless customer-facing material is requested. Share no deal notes or system changes without explicit approval.
Quality bar
- A manager can use this in the next 1:1 without rewriting it.
- Stage support and evidence confidence are separate findings.
- Buyer-confirmed, seller-asserted, inferred, and missing stay labeled.
- Activity volume, an internal task, or a future meeting is not buyer progress.
- Verified risk and missing proof have different actions.
- No invented CRM facts, amounts, dates, or commitments.
- Stage or field changes stay recommendations.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

