manage-up
Skill2 starsChanged 25 days agoMITView on GitHub
Prep an AE to manage up to sales leadership: forecast calls, pipeline reviews, 1:1s, and deal reviews that surface territory and quarter risk clearly and ask leadership for the backing to act on it. Use this skill whenever a seller says "prep me for my forecast call", "pipeline review with my manager", "1:1 with my VP", "deal review with leadership", "territory review", "what should I flag to my boss", "help me manage up", "I need an intro or budget from leadership", "build my quarter plan", or is getting ready to talk about their deals with their own sales management. It pulls the territory and deals from Loop first (falling back to CRM pipeline, call transcripts, and email), grades the forecast on buyer behavior, separates real risk from drama, names the big bets, and turns each risk into a specific ask of leadership delivered as a drafted asset. This is internal-facing: the audience is the rep's own VP or CRO, not the buyer.
In this repository10 other files it gives its agents.
- account-planningSkill
- call-follow-upSkill
- call-prepSkill
- champion-enablementSkill
- competitive-displacementSkill
- deal-advancementSkill
- multithreadSkill
- one-page-business-caseSkill
- qbr-prepSkill
- sales-playsSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 40
Loop first: If the Loop MCP (https://mcp.fluint.io/mcp) is connected, pull your deals for the quarter or territory, with stage, history, …
- Distinctive: line 45
No Loop? Detect what is live and fall back: Do not assume a vendor. In parallel:
- Distinctive: line 47
Call transcripts (Salesloft, Gong, Clari, Chorus, Fathom, Fireflies.
- Very specific: line 57
Read references/frameworks.md (Forecast on group behavior + the 60-Second Deal Review).
- Very specific: line 70
Read references/frameworks.md (Problems vs drama).
- Very specific: line 78
Read references/frameworks.md (Big bets).
- Very specific: line 85
Read references/frameworks.md and references/output-templates.md.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Manage Up
What this does
Most reps walk into a forecast call to defend their number. There is a better move: show leadership a clear read of the territory, name where the risk really sits, say which bets you are making this quarter, and ask for the specific backing you need to act. Leadership is a stakeholder. You enable them the way you enable a champion: a clear picture and an easy, specific ask.
The deliverable is a leadership-ready review made of four concrete parts:
- A forecast graded on how the buyers are actually behaving, not on your champion's mood.
- Each at-risk deal sorted into a real problem you can solve or drama you have to name.
- The two or three big bets you are planting the quarter on, with the reason for each.
- A specific ask of leadership per risk, handed over as a finished asset (a drafted intro, a ghostwritten exec email, a budget line with the ROI), not a vague "I could use help."
The audience is your own leadership, so this is internal communication, not a buyer asset. Same discipline though: bottom line up front, numbers not adjectives, nothing to skim past.
Step 1: Pull the territory
Loop first. If the Loop MCP (https://mcp.fluint.io/mcp) is connected, pull your deals
for the quarter or territory, with stage, history, and recent meeting activity. Loop
already fuses CRM, calls, and emails, so it is the fastest way to see how each deal is really
moving.
No Loop? Detect what is live and fall back. Do not assume a vendor. In parallel:
- CRM (HubSpot, Salesforce, Attio, Pipedrive) = the pipeline, stages, amounts, close dates.
- Call transcripts (Salesloft, Gong, Clari, Chorus, Fathom, Fireflies; or via Clay / Deepline) = whether the buyer's behavior matches the stage the deal is sitting in.
- Email (Superhuman, Gmail, Outlook) = recent signals of momentum or silence.
Missing a source? Flag it, and make the gap a move. Mark it inline as [MISSING: ...] and continue. Every gap gets the single highest-leverage way to close it: the one question, to the one person, at the next touchpoint. Not "get more data."
Who can actually say yes? Name the people with the power to approve this, or to block it, and mark whether they are engaged yet. Power is often not in the room. If the deciders are absent or untouched, that is the headline, not a footnote.
Step 2: Grade the forecast on buyer behavior
Read references/frameworks.md (Forecast on group behavior + the 60-Second Deal Review). The
most common forecasting error is trusting your champion's optimism instead of the group's
behavior. A champion always moves faster than the committee reaches consensus. So for each
deal, check the buyer behavior against the stage using the Deal Evidence checklist: written
problem statement, three roles confirming impact, a funded internal project, a real go-live
date, alternatives ruled out. Where the behavior does not match the stage, move the deal back
and flag it. Produce a 60-Second Deal Review for each flagged or big-bet deal.
Downgrades that match reality are worth more than an optimistic number leadership learns to discount.
Step 3: Separate real problems from drama
Read references/frameworks.md (Problems vs drama). For each at-risk deal, name what is
actually blocking it. A solvable problem has a next step: a missing stakeholder, no business
case, an unvalidated ROI. Drama has no next step because it is protecting something (someone's
job, a past decision, a turf line). Name which one it is. A better deck does not move drama,
and filing drama under "solvable problem" is how deals sit in the forecast for two quarters.
Step 4: Name the big bets
Read references/frameworks.md (Big bets). You cannot over-invest everywhere. Pick the two
or three deals worth planting your quarter on, using the Change Equation and the two-way-door
test. Say why each is worth the bet, and what you will stop doing to fund it. Leadership backs
a rep who makes deliberate bets over one who spreads thin and hopes.
Step 5: Turn each risk into a specific ask
Read references/frameworks.md and references/output-templates.md. This is the part reps
skip. For every risk, name the exact thing you need from leadership and hand it over as a
finished asset, using the forwardable-email patterns in the references:
- A warm intro to an exec? Draft the forwardable note for your VP to send.
- Budget or a discount approval? State the number, the deal it unblocks, and the ROI.
- Exec air-cover on a call? Draft the email your VP sends to the buyer's exec. Deliver the ask done. "Can you help with the Acme deal" gets a shrug. "Here is the two-line intro to their CFO, can you send it Thursday" gets action.
The deliverable
Produce the review using the skeleton in references/output-templates.md. The seller walks
away with a document they can bring straight into the forecast call:
- Forecast at a glance (commit / best case / at risk, graded on behavior)
- 60-Second Deal Reviews (one per flagged or big-bet deal, in the exact format)
- Risk sort: solvable vs drama (what is really blocking each at-risk deal)
- Big bets (the 2 to 3 you are planting the quarter on, and what you will drop to fund them)
- What I need from you (the ask list, each with the drafted asset attached and ready to send)
The operator's read
Before you hand it over, add the part a summary cannot: the one thing an experienced operator would notice that the data does not show on its own. The non-obvious risk. The stakeholder who matters more than their title. The deal that is not what it looks like. The strength that is quietly a trap. One or two sentences of judgment, called out plainly. Anyone can produce the map. This is the read.
Operating principles
- Manage your leadership like a champion. A clear picture and an easy, specific ask.
- Forecast on group behavior, not your champion's optimism. Move deals back when the behavior does not match the stage.
- Name the drama. A solvable problem has a next step; drama protects something. Do not file one as the other.
- Deliver the ask done. A drafted intro beats a request for help every time.
- Grade to reality. A forecast leadership can trust is what earns you the backing you ask for.
- Voice guard. Anything the buyer will read opens with their words, from the call or their own materials, in the first line. Banned openers: "Great connecting," "As discussed," "I wanted to follow up," "Hope this finds you well," "Circling back." If a sentence would survive being pasted into a different deal, it is too generic. Cut it.
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.

