Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add boshi-xixixi/TraeSkill --skill gtm-ai-gtmgit clone --depth 1 https://github.com/boshi-xixixi/TraeSkillWrote 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/boshi-xixixi/traeskill/gtm-ai-gtm)<a href="https://agentmods.dev/skills/boshi-xixixi/traeskill/gtm-ai-gtm"><img src="https://agentmods.dev/badge/skills/boshi-xixixi/traeskill/gtm-ai-gtm/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/boshi-xixixi/traeskill/gtm-ai-gtm"><img src="https://agentmods.dev/badge/skills/boshi-xixixi/traeskill/gtm-ai-gtm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 474 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.
- low Excessive Agency · line 373 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00056 | $0.04865 |
| Opus 5 | $0.00028 | $0.02433 |
| Sonnet 5 | $0.00011 | $0.00973 |
| Haiku 4.5 | $0.00006 | $0.00487 |
Grade A, and why
gtm-ai-gtm 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 7d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- gtm-ai-gtm — 100% identical, 0 lines differ
- ai-gtm — 97% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 570 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Product GTM
Go-to-market strategy for AI products. These aren't generic AI principles — they're patterns from selling autonomous AI agents into enterprises where "autonomous" scared buyers and "teammate" converted them.
When to Use
Triggers:
- "How do we position this AI product?"
- "Buyers say they're worried about AI breaking production"
- "Should we call it autonomous or copilot?"
- "How do we price AI when usage varies 10x by customer?"
- "Enterprise security passed but ops rejected us — why?"
Context:
- AI agent platforms (coding, support, ops)
- LLM-based applications
- Autonomous tools that do things (not just suggest)
- AI infrastructure
- Anything where the AI makes decisions
Core Frameworks
1. The Real Enterprise AI Objection (It's Not What You Think)
What I Learned Selling Autonomous AI Agents:
Three months in, enterprise security reviews were passing fast. Good sign, right? Then the pattern emerged: security approved, but operations rejected us.
The objection wasn't "will the AI break production?" — they assumed it would break production eventually. The real question was:
"Who's responsible when the agent does something wrong?"
Not "do we trust the agent?" — "do we trust our team to handle this?"
Why This Matters:
Autonomous agents create a new operational burden. You're not selling AI capability, you're selling organizational readiness. When your agent halts production at 2am, who gets paged? Who fixes it? Who explains it to the VP?
Framework: The Accountability Cascade
Before deploying AI agents, enterprises need clear answers:
- L1 Response: Who monitors the agent? (24/7 ops team, or dev team on-call?)
- L2 Escalation: When agent action fails, who debugs? (Agent team, or product team?)
- L3 Ownership: When something breaks badly, who owns customer communication?
If you can't answer all three, they won't buy. Doesn't matter how good your AI is.
How This Changes Your Sales Process:
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.
- 7d ago First seen · 570 lines · 56 tokens per session scan A eddccd76f450
gtm-ai-gtm is a skill published in the GitHub repository boshi-xixixi/TraeSkill (263 stars, last pushed 4mo ago), licensed MIT. It adds 56 tokens to every session and 4,865 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
temprouter
Call tempRouter — a payable, end-to-end-encrypted LLM inference endpoint on MPP (Tempo). Pay per inference in pathUSD stablecoin AFTER your agent verifies (Intel DCAP) that the prompt runs inside a real Phala Intel TDX enclave that can't read it. Use when a prompt holds secrets/PII (API keys sk-…, private keys 0x……
llm-patterns
AI-first application patterns, LLM testing, prompt management.
prompt-engineering
Master the art and science of crafting effective prompts for large language models. Covers foundational patterns, advanced techniques like chain-of-thought and role prompting, structured output formats, and practical strategies for iterative refinement.
qianwen-text
Generate text, have conversations, write code, reason, and call functions with Qwen models. TRIGGER when: user asks to chat with Qwen, generate text, write code with Qwen, use Qwen function calling, or explicitly invokes this skill by name (e.g. use qianwen-text). DO NOT TRIGGER when: general coding questions without…
prompt-engineering
Use when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt blocks, or the inline cases you run while tuning. NOT the agent loop, tools, or retrieval (that is building-agents), NOT a standing CI eval…
loom-prompt-engineering
Designs and optimizes prompts for large language models including system prompts, agent signals, and few-shot examples.