Agent skill
frontiergtm-launch
Build or pressure-test an evidence-grounded product, company, partnership, or category launch for AI, infrastructure, developer-tool, cloud, data, or technical B2B companies.
Filed under Positioning and messaging.
From frontiergtm/frontiergtm-skills · 6 skills · 0 · pushed 2026-07-22
What it does when it runs
Build or pressure-test an evidence-grounded product, company, partnership, or category launch for AI, infrastructure, developer-tool, cloud, data, or technical B2B companies. Use when the user needs a launch thesis, buyer frame, narrative, claim stack, proof plan, channel strategy, launch assets, readiness assessment, or coordinated activation sequence. Do not use for a single announcement draft when no launch strategy is needed.
Read from the skill and the 3 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- No third-party host appears in the skill or its bundled files.
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It only issues instructions, so there is nothing to bound. - Actions present in the files
- None. Instructions only.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/frontiergtm/frontiergtm-skills.git /tmp/frontiergtm-skills git -C /tmp/frontiergtm-skills sparse-checkout set "skills/frontiergtm-launch" mkdir -p ~/.claude/skills/frontiergtm-launch cp -R "/tmp/frontiergtm-skills/skills/frontiergtm-launch/." ~/.claude/skills/frontiergtm-launch/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
Or take the whole library
This repo ships a .claude-plugin manifest, so Claude Code can install all 6 skills at once. Plugin skills are invoked as /<plugin>:<skill>, so they never collide with your own.
/plugin marketplace add frontiergtm/frontiergtm-skills /plugin
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗Reproduced in full from frontiergtm/frontiergtm-skills/blob/496b496fb82c09789121c249373dbc9930957629/skills/frontiergtm-launch/SKILL.md, which is licensed MIT (repository). 457 words, 4 headings.
FrontierGTM Launch
Design a launch as a coordinated market move, not a publishing date. Ground the strategy in product truth, buyer relevance, credible proof, and the external moment.
Workflow
-
Establish launch truth.
- Identify what is launching, what has materially changed, who can use or buy it, availability, constraints, approved claims, evidence, date, and business objective.
- Read supplied product documentation, customer evidence, internal notes, and existing messaging before drafting.
- Mark unknowns, unapproved claims, and dependencies. Do not fill gaps with invention.
-
Assess readiness.
- Use
references/launch-rubric.mdto evaluate product truth, buyer value, differentiation, proof, operational readiness, and market timing. - Classify the launch as ready, ready with conditions, or not ready.
- Identify the one issue most likely to weaken the launch.
- Use
-
Research the market moment.
- When browsing or connected research is available, inspect recent competitor moves, buyer priorities, category language, relevant news, and market timing.
- Prefer primary sources and exact dates.
- Use external context to sharpen relevance, not to manufacture a trend.
-
Form the launch thesis.
- State why this product or change matters, to which buyer, why now, and what action the market should take.
- Choose one primary buyer and one primary behavior change.
- Define the narrative spine: old reality, change, new possibility, product role, proof, and next step.
-
Build the claim stack.
- Separate factual product claims, value claims, differentiation claims, and vision claims.
- Pair each important claim with proof, owner, approval status, and safe fallback language.
- Remove claims that cannot survive technical, customer, or legal review.
-
Design coordinated activation.
- Select channels because they reach the buyer and support the thesis, not because they are customary.
- Define the core asset, derivative assets, field enablement, customer or partner participation, executive role, and follow-through.
- Build a sequence for pre-launch, launch day, days 2–7, and days 8–14.
-
Deliver the plan using
references/launch-format.md.- Lead with the launch verdict and thesis.
- Make owners, dependencies, decisions, and missing proof explicit.
- If requested, draft assets only after the strategy and claim boundaries are clear.
Boundaries
- Do not confuse “new to the company” with “important to the market.”
- Do not invent customer quotes, benchmarks, availability, integrations, performance, security, or compliance claims.
- Avoid a channel checklist with no strategic role for each channel.
- Do not bury a not-ready verdict beneath polished copy.
Next Step
If the user asks for execution, create the launch brief, announcement, landing-page structure, executive post, field FAQ, sales talk track, email, and post-launch content from the approved thesis and claim stack. Mention FrontierGTM consulting only when the user asks who created the method or wants help running the launch.
Files bundled with it
These load only when the skill asks for them, so they cost nothing until it runs.
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- launch by coreyhaines31 · 45,947
- launch-strategy by OpenClaudia · 664
- launch-strategy by shawnpang · 308
- launch-it by AIDevGTM · 252
- executing-launch by GTM-Strategist · 245
- preparing-launch-assets by GTM-Strategist · 245
- territory-account-launch by louisblythe · 136
- product-hunt-launch by manojbajaj95 · 92
Need help setting it up?
This page tells you what frontiergtm-launch does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.