deal-qualification-desk
Skill1 starsChanged 26 days agoApache-2.0View on GitHub
Market research, buyer personas, lead generation and qualification, and lead and deal prioritisation, plus the two-lane SE engagement model and its 30-day pilot tracker. Scores deals with MEDDPICC-style fields and fit, routes each to lane 1 (exploratory, self-serve) or lane 2 (named SE, tailored discovery, technical success criteria), and tracks SE hours per qualified opportunity, demo-to-next-stage conversion and time to technical decision. Use when the user asks to research a market or account, build personas, find or qualify leads, prioritise a pipeline, decide where SE time goes, or run the two-lane pilot, or when presales-ai routes here.
In this repository13 other files it gives its agents.
- architecture-decision-recordSkill
- competitive-battle-cardsSkill
- creative-animated-svgSkill
- drawio-creative-diagramsSkill
- excalidraw-creative-diagramsSkill
- find-skillsSkill
- llm-finopsSkill
- markdown-craftSkill
- presales-aiSkill
- presales-meeting-prepSkill
- rfp-response-builderSkill
- solution-design-explorerSkill
- tdr-authorSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Read deal-context.json first if it exists.
- Very specific: line 11
Use web research (and Apollo, Clay or HubSpot when connected and authorised).
- Distinctive: line 14
Every line has a source URL and date.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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 qualification desk
Read deal-context.json first if it exists.
Market and account research
Use web research (and Apollo, Clay or HubSpot when connected and authorised). Output
out/research.md: market size signals, the account's priorities from public sources
(annual report, job posts, press), tech stack hints, trigger events, and named competitors.
Every line has a source URL and date.
Buyer personas
Template: references/persona-card.md. One card per persona: role, goals, pains, what they
measure, objections, words they use, the content that moves them, and discovery questions.
Base them on the user's notes and calls first, research second. Mark guessed fields.
Lead generation
From an ideal customer profile (industry, size, region, tech, trigger), list target accounts with the reason each fits and its source. Never scrape personal contact data. Leave contact lookup to a connected, authorised tool.
Qualification and prioritisation
python3 scripts/score_deals.py deals.csv -c references/scoring.json -o out/scored-deals.csvScores 0 to 100 from MEDDPICC fields (metrics, economic buyer, decision criteria, decision
process, paper process, pain, champion, competition) plus fit. Weights and thresholds live in
references/scoring.json, so the team can tune them. Output adds score, lane, gaps
(the weakest fields, to fix next) and sorts by score times amount.
The two-lane model
| Lane 1: exploratory | Lane 2: qualified and complex | |
| Rule | score below the lane-2 threshold, or no confirmed pain | score at or above threshold and confirmed pain and an economic buyer |
| SE time | none up front | a named SE owner |
| Experience | a short qualification step, then a reusable on-demand product tour or sandbox | tailored discovery, a custom demo, agreed technical success criteria |
| Moves up when | the qualification gaps close |
30-day pilot tracker
python3 scripts/pilot_tracker.py pilot.csv -o out/pilot-tracker.htmlpilot.csv columns: deal_id, lane, start_date, qualified (y/n), se_hours, demo_date,
next_stage_date, tech_decision_date. The page shows three headline numbers per lane: SE
hours per qualified opportunity, demo-to-next-stage conversion, and median days to technical
decision. It also shows a daily trend and a day-30 review panel that suggests coverage
changes (for example, raise the lane-2 threshold if lane-2 conversion is not higher than
lane 1). Template: assets/pilot-tracker.html. Pilot plan text: references/two-lane-pilot.md.
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.