Agent Skill Library, kit
The GTM AI OS: who to go after and what to say
Eleven skills that run account work as a loop: KNOW why you win and what each account needs, DECIDE which accounts to act on, ACT with evidence-based messages checked by a separate evaluator, LEARN from what changed each week.
Who it is for
Sales, business development, marketing, and RevOps leaders who want AI-assisted account research and outreach with a human approval step before anything is sent. The files include the complete method and instructions.
The download holds all 11 SKILL.md files plus templates and setup notes (28 files).
Safari note: Safari on Mac can unzip downloads automatically. To keep the kit zipped, open Safari, go to Settings, General, and turn off "Open 'safe' files after downloading". Chrome, Edge and Firefox keep the zip as it is.
Install this package
- Run the command below in your terminal. It downloads and extracts the package, then copies its skill folders into Claude Code's skills directory. Existing skill folders with the same names may be replaced.
- Keep the extracted
gtm-ai-osfolder. Read its setup notes for any additional scripts, templates, or workspace steps before running the skills. For another assistant, follow its own skill installation instructions using the downloaded folders. - Start with the package's first step and check the output before using it.
curl -fL "https://www.therevenueaireport.com/agent-skills/kits/gtm-ai-os/download.zip" -o "gtm-ai-os.zip" && unzip -o "gtm-ai-os.zip" && find "gtm-ai-os" -name SKILL.md -print | while IFS= read -r file; do dir="$(dirname "$file")"; target="$HOME/.claude/skills/$(basename "$dir")"; mkdir -p "$target" && cp -R "$dir/." "$target/"; doneCore, install first
Creates the shared workspace, the router that sends each request to the right skill, a status check, and a report on whether the system is learning.
Os Install
Creates or repairs the shared workspace that every SCALE and GTM AI OS plugin depends on, detects an existing workspace and installed skills, and runs quick (3 questions) or advanced (12 questions) onboarding.
Gtm Chief of Staff
Router for the shared workspace. Sends any request to the right SCALE or GTM AI OS skill, checks prerequisites and the fence, and answers status questions.
Os Status
Reports what is done, what is next, and what is stale in the user's GTM AI OS workspace.
Os Graph Report
Reports harness health and learning over time from the workspace's own signals log and evolve records: evaluator pass rate, override rate, signal freshness, records with doubt filled, proposals approved, plus week-one baseline versus now.
Know
Learn why deals are won and lost, then build an evidence record for each account.
Os win Loss Extract
Extracts why deals were won, lost, disqualified, or churned over 18 to 24 months in the buyer's own words, writes an evidence-based ICP, and proposes buying signals only after comparing their frequency in wins versus losses.
Os Account Context
Builds the Account Context record for one account: expected value, verified pain with source, recent changes, confidence-tagged signals, hypothesis, why-we-might-be-wrong, owner, and next action.
Decide
Score accounts and put each one in exactly one bucket: act, research, monitor, or deprioritize.
Act
Draft outreach from evidence, grade it with a separate evaluator, and log every touch.
Os Message Architecture
Writes outreach for one account from its Account Context using the path its evidence allows (confirmed pain, signal-only question, or research task), mapped to three decision roles, with every proof point drawn from the proof register.
Os Message Evaluator
Separate pre-send check that grades a drafted message against the account record, the readiness policy, the proof register, and the fence, and returns pass or a failure code.
Os act Loop
Runs the KNOW → DECIDE → ACT sequence on one Action Priority account: refresh the record, re-score, draft by path, evaluate, enforce the fence, and log every touch.
Learn
Review the week and propose changes. A person approves each one.
How to start
- 1. Claude desktop (Cowork): install the core skills first, then Know, Decide, Act, Learn.
- 2. First run: say "Set up my workspace", then "Run win loss".
- 3. ChatGPT, Codex, Grok, or other tools: see README-OTHER-TOOLS.md in the download. Run the message evaluator yourself on every draft.
- Nothing is sent without your say. A fence file sets what the system may do on its own, what needs approval, and what it must never do.
- The core skills are shared with the SCALE kit. Install them once for both.
Built by Jonathan Kvarfordt. Standalone bundle v0.2.