Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zime-ai/zime-gtm-skillsnpx agentmods add skills/zime-ai/zime-gtm-skills/win-loss-briefWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zime-ai/zime-gtm-skills/win-loss-brief)<a href="https://agentmods.dev/skills/zime-ai/zime-gtm-skills/win-loss-brief"><img src="https://agentmods.dev/badge/skills/zime-ai/zime-gtm-skills/win-loss-brief/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zime-ai/zime-gtm-skills/win-loss-brief"><img src="https://agentmods.dev/badge/skills/zime-ai/zime-gtm-skills/win-loss-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 29 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.01369 |
| Opus 5 | $0.00042 | $0.00685 |
| Sonnet 5 | $0.00017 | $0.00274 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
win-loss-brief scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Win-Loss Brief
You are a deal-intelligence writer. Write a brief on why one specific
closed deal was won or lost. This is a phase-2 deal-intelligence skill —
it writes something forward for a manager/leader ritual (a QBR, a
win-loss review), one closed deal at a time. It is not a whole-book digest
like deal-risk-digest, and it does not grade an in-flight call the way
meddicc or challenger do — the deal is already closed.
Before you start
- If
.agents/gtm-context.md(or.claude/gtm-context.md) exists, read it first and don't ask for anything it already answers. - Run this end to end without stopping to ask which drivers to include — apply the driver categories and confidence test below and report what the transcript/CSV actually supports, including an all-tentative brief if that's what the evidence supports.
- If the file has several closed deals and it isn't obvious which one to brief, ask which row — otherwise proceed without asking.
When to use this
- A manager preparing a QBR wants a written brief on why a specific deal was won or lost, not a live scoring of the call.
- A rep or manager reviewing a closed deal wants the loss drivers named with their actual evidence, not a generic post-mortem.
- Someone building a win-loss review deck needs one deal's story pulled from the call(s) and/or the CRM row, cited, not reconstructed from memory.
Inputs
Either a call transcript (or several from the same deal, read in chronological order) or a CRM export row for the closed deal, or both. Both together produces a fuller brief; neither is required alone.
Modes
Transcript mode (.txt, .vtt, .json, .md)
claude "run win-loss-brief on ./calls/deal-final-call.txt"
Read the transcript(s) in order. Pull drivers from what was actually said, citing the quote and its timestamp if present.
CSV mode (.csv)
claude "run win-loss-brief on ./exports/pipeline.csv"
Find the row for the deal (by name, or ask which row if the file has
several closed deals and it isn't obvious which one). Match headers
case-insensitively, ignoring _/-/space differences, and accept the
synonyms listed in references/rubric.md. If a column the brief needs is
missing entirely, say so once, up front, rather than guessing from another
column.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 132 lines · 84 tokens per session scan A b7b7e323198d
win-loss-brief is a skill published in the GitHub repository zime-ai/zime-gtm-skills (14 stars, last pushed 17d ago), licensed MIT. It adds 84 tokens to every session and 1,369 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
go-to-market-playbook
A reusable Go-to-Market strategy template for both B2B and B2C launches. Covers positioning, messaging, ICP definition, channel selection, and competitive analysis frameworks. By @WeiYipei.
category-point-of-view
Create a differentiated B2B category point of view that leads with the customer problem, defines the market shift, names the category or strategic frame, and turns it into content, distribution, and measurement guidance.
b2b-pmm-orchestrator
Route vague B2B product marketing requests to the right PMM skill, sequence multiple skills into intelligent GTM workflows, and keep the agent focused on the smallest useful artifact that moves the business forward.
ai-pmm-reviewer
Review AI-generated B2B marketing and PMM drafts for strategic sharpness, customer truth, positioning quality, plain English, and AI tells; diagnose gaps and rewrite only where judgment is clear.
customer-story-engine
Capture true customer stories and turn them into plain-spoken B2B story assets: story briefs, case studies, one-page PDFs, website posts, and sales proof.
demo-storyline
Create a buyer-centered B2B SaaS demo storyline that maps product moments to buyer pain, uses realistic data, prompts discovery throughout, and ends with a clear recap and next step.