One real piece of news, in the order a journalist reads it.
A press release draft built from your announcement: headline, lead, quote, boilerplate, and a list of every claim to verify.
Most releases open with the company's history and bury the news in the third paragraph. A reporter who has forty of these in an inbox reads the headline, finds an adjective instead of a fact, and moves on.
Press Release Draft finds the news in one sentence first, then builds the inverted pyramid around it. It flags any claim it cannot trace to your notes, drafts a quote for the speaker to approve, and ends with a verification table so nothing goes out unchecked.
What it produces.
- →A headline under 12 words and a lead covering who, what, when, and where
- →A draft quote clearly marked for the speaker to approve or rewrite
- →Boilerplate and a media contact line
- →A verification table listing every claim, figure, name, and quote to confirm
- ✦Founders announcing a launch, a hire, or a new location
- ✦Small-team marketers who write releases a few times a year
- ✦Nonprofit and community organizers announcing an event or award
- →press-release-draft.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →press-release-draft-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
- →A README inside the zip with install steps for Claude, ChatGPT, and Gemini
What it does with a real question.
We're announcing that Brightpath Learning, our 14-person edtech startup in Austin, closed a $3.2 million seed round on March 4, led by Northfield Ventures. I'm the CEO, Dana Reyes, and the board approved release for March 12. We'll use the funds to hire six engineers and launch our adaptive math app in 200 Texas schools by fall.
The news is the hiring and the schools, not the check. Funding rounds are common; a 14-person Austin startup promising to put an adaptive math app in 200 Texas schools by fall is the part an education reporter will actually want. So the draft opens there. Headline: "Brightpath Learning Raises $3.2 Million to Bring Adaptive Math App to 200 Texas Schools." Lead: "AUSTIN, March 12: Brightpath Learning, an Austin-based education technology company, closed a $3.2 million seed round led by Northfield Ventures and will use the funds to hire six engineers and launch its adaptive math app in 200 Texas schools by fall."
Support that with one sentence on why it matters, but I have no problem statement or student data from you, so I'm leaving it as "[needs source: learning-outcome or demand figure]" rather than inventing one. The same goes for any pilot-school count.
For the quote, here is a draft for you to approve or rewrite: "Teachers told us the hard part isn't finding math practice, it's finding practice that meets each student where they are," said Dana Reyes, CEO. "This round lets us build that for far more classrooms."
Next move: before March 12, get a written yes from Northfield Ventures on the wording of the round and the lead investor line. Ask for a one-sentence Northfield quote as well, since a named investor voice gives reporters a second source. Send me their reply and I'll lock the final draft and boilerplate.
The full Playbook runs the whole procedure and writes the complete deliverable, not this excerpt.
Written by claude-sonnet-5-5 with this Playbook loaded, 2026-10-11. Checked automatically for length and for copied framework text.
No subscription · free updates within v1.x
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude writes a polished release that sounds confident and may add praise or figures you never gave it. This Playbook uses only your facts, marks gaps as needing a source, and ends on a checklist of what a person must verify and approve before release.
How is this different from a Tool?
Playbooks are systematically produced to a fixed template and priced accordingly ($12.99). Tools are hand-built, one at a time, and go deeper ($39 to $199). A Playbook gives you a reliable method for routine work; a Tool is for when the judgment matters more than the format.
Will this work with ChatGPT, Gemini, and other LLMs?
Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.
Can I share this with my team?
It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Playbook itself in the hands of a whole team, email hello@authority.md about team licensing.
What if it doesn't work for me?
If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.