Skip to content
Writing & Comms · Playbook

Say who the talk is for and what they will do differently.

A conference talk abstract, reviewer note, and speaker line built from your idea and the facts you supply.

IncludedNative Claude Skill + plain .md for ChatGPT, Gemini & every LLM
100 Playbooks in the catalogDelivered as Claude Skill + plain .mdReviewed Oct 22, 2026Instruction-only · verifiable

Most abstracts describe a topic and hope the reviewer fills in the value. Organizers scoring a long stack cannot tell who should attend or what the audience takes home, so the abstract blends into the rest.

Talk Abstract starts with the change: who the audience is and what they can do after. It tests three titles, drafts the abstract to the event's word limit, writes the private reviewer note with a timed outline, and checks that the promise fits the session length.

What you get

What it produces.

  • →Three title options with a recommendation
  • →An abstract with problem, approach, three takeaways, and who it is for
  • →A private reviewer note with a three-part outline
  • →A one-sentence speaker line from your supplied facts
Who it's for
  • ✦Practitioners submitting to a conference call for proposals
  • ✦Consultants who speak at meetups and webinars for lead generation
  • ✦Anyone whose abstract keeps getting declined without explanation
What's included
  • →talk-abstract.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →talk-abstract-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
Delivery
Emailed within 60 seconds of payment
Compatibility
Claude, ChatGPT, Gemini, any LLM
License
One-time purchase, yours to keep
Sample output

What it does with a real question.

The brief

I'm a platform engineer at a mid-size logistics firm, and I want to submit a 30-minute talk to DevOpsDays Chicago, due March 14. It's about how we cut our CI build times from 42 minutes to 9 by splitting a monorepo test suite. The audience is mid-level engineers and team leads who own pipelines.

Lead with the change, not the number. Your 42-to-9 result is the hook, but a number alone tells a reviewer what happened to you, not what the audience can do. Mid-level engineers and team leads who own pipelines will ask one thing: can I do this to mine? So frame the promise as an action. After this talk, pipeline owners will be able to split a slow monorepo test suite into parallel groups and cut build time without losing coverage.

I'd title it "Why Your CI Takes 42 Minutes (and How We Got to 9)." It states the tension plainly and puts the metric where reviewers will see it.

For the abstract, open with the pain every pipeline owner knows: developers context-switching while they wait on a build. Then name the one method at the center, how you decided where to cut the suite, and give three takeaways: how to measure which tests are slow, how to group them without flaky ordering, and how to prove the split did not hide failures. End by saying who it is for: teams with a single large test suite and a build over 20 minutes. Say who it is not for, such as small repos that already finish quickly.

The reviewer note should outline three timed parts of ten minutes each: the diagnosis, the split, and the results and pitfalls. Include one real failure you hit, because organizers trust a speaker who shows what went wrong.

Next move: draft the 150-word version tonight and send it to a teammate before March 14.

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.

One-time purchase
$12.99
Yours to keep
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

Questions

Before you buy.

How is this different from just asking Claude directly?

Asked cold, Claude writes an enthusiastic abstract with a broad promise and a catchy title. This Playbook anchors it in a named audience and a specific takeaway, fits the event's constraints, and cuts promises the talk cannot deliver in the time given.

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.

More Writing & Comms Playbooks

Other Playbooks.