Individual skill

deal-qualification-gates

Install evidence-gated qualification on a live pipeline: score the QUALITY of evidence behind every deal (1-5 per qualification dimension), set minimum scores per stage, and enforce qualify-or-kill at each gate. Triggers on 'zombie deals,' 'pipeline is full of junk,' 'is this deal real,' 'qualify or kill,' 'deals stall at proposal,' 'forecast built on hope,' 'reps say every deal is closing,' 'stage criteria,' 'exit criteria,' 'MEDDIC scoring,' 'SPICED scoring,' 'qualification framework rollout,' or any situation where deals advance on rep optimism instead of buyer evidence. Works with SPICED by default and maps to MEDDICC or BANT. BOUNDARY: icp-builder owns ACCOUNT-level fit (is this the right company) and carries a summary of these gates as its pipeline-enforcement step; this skill is the full deal-level operating system (is this deal real). deal-velocity-engineer treats slow deals as a speed problem; this skill treats false deals as a truth problem, and it runs first, because accelerating an unqualified deal just produces a faster loss. Weekly pipeline reviews consume the scores this skill produces; they read the dashboard, this skill builds the engine under it.

skills/rutger-katz/deal-qualification-gates/SKILL.md

Read pinned source

Source commit 5d786aad0c7b2ca59b1abf1f601f9407ca261996

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Instructions only
Last checked: Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 237
Repository last updated: Oct 20, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 9,144 bytes
references/qualification-frameworks.mddoc · 3,679 bytes

Read excerpt


# Deal Qualification Gates: Evidence, Not Enthusiasm

The 2025 Ebsta x Pavilion benchmark put average B2B win rates at 19%. Most of that waste is not lost at the negotiation table; it is manufactured months earlier, when a conversation gets logged as a deal and nobody ever checks whether the evidence behind it hardened. CRM stages measure where a deal is. Almost nobody measures how WELL you know what you claim to know about it.

This skill installs that second axis: an evidence-quality score per qualification dimension, minimum scores per stage, and a standing qualify-or-kill discipline. Gates, not fields. Adding more CRM fields will not fix a forecast; minimum evidence per stage will.

---

## The Evidence-Quality Scale

Score every qualification dimension 1 to 5. The scale grades evidence, never rep enthusiasm:

| Score | Grade | Meaning |
|---|---|---|