sales-process-guide
Skill1 starsChanged 10 days agoMITView on GitHub
Routes a B2B sales task to the right skill in this set based on where the deal is, from first research to renewal. Use whenever the user describes a sales situation without naming a skill, such as "I have a new lead", "my call is tomorrow", "they went quiet" or "is this deal real", or asks what to do next in a deal.
In this repository7 other files it gives its agents.
- account-research-briefSkill
- call-prep-briefSkill
- cold-outreach-emailSkill
- deal-qualification-checkSkill
- discovery-call-guideSkill
- post-call-follow-upSkill
- re-engagement-emailSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Read the matching skill's SKILL.md and follow it.
- Distinctive: line 31
If the stage has no skill, help directly with the shared principles below and say that no dedicated skill exists yet.
- Distinctive: line 35
Use only facts from the user's notes or cited sources.
- Distinctive: line 36
Ask for one clear next step per message.
- Distinctive: line 37
Keep external messages short and plain, since buyers read on mobile.
- Distinctive: line 38
Don't promise results or quote prices in early messages.
≈ “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
Sales process guide
Sales work goes in a sequence, and each stage has a different job. Picking the skill that matches the stage keeps the output useful: an outreach email is wrong for a deal that needs qualifying, and a recap is wrong for a lead nobody has contacted.
Stage map
| Stage | What the user says | Skill |
| 1. Research | "who is X at Y", "look into this company" | account-research-brief |
| 2. First touch | "write an intro email", "cold email to X" | cold-outreach-email |
| 3. Call prep | "call tomorrow with X", "prep me" | call-prep-brief |
| 4. The call | "how should I run the call", "what do I ask" | discovery-call-guide |
| 5. Recap | "follow-up after my call", "recap email" | post-call-follow-up |
| 6. Qualification | "is this deal real", "why is it stuck" | deal-qualification-check |
| 7. Proposal, negotiation, close | (not in this set yet) | handle directly, see below |
| Any stage | "they stopped replying", "revive this thread" | re-engagement-email |
| 8. Renewal and expansion | (not in this set yet) | handle directly, see below |
How to route
- Identify the stage from what the user describes. If two stages fit, choose the earlier one that hasn't been done.
- Read the matching skill's SKILL.md and follow it.
- Mention in one line which stage this is and what typically comes next, so the user sees the sequence.
- If the stage has no skill, help directly with the shared principles below and say that no dedicated skill exists yet.
Shared principles
These run through every skill in the set. Apply them when working without a dedicated skill:
- Use only facts from the user's notes or cited sources. Invented numbers and references damage the sender's credibility.
- Ask for one clear next step per message.
- Keep external messages short and plain, since buyers read on mobile.
- Don't promise results or quote prices in early messages.
- Mark assumptions and flag what the user should verify before sending anything externally.
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.

