press-release-faq

press-release-faq is a skill for Claude Code, Codex from ohong/agent-skills. It costs 132 tokens per session (1,629 once invoked), scanned A, original, MIT.

A product-planning document made of a short launch announcement and answers to likely questions, written before the product exists. It uses Amazon’s Working Backwards method to test an idea against the existing codebase.

In plain words
What is it for?
Use it to pressure-test a product or feature idea and produce a grounded press release and FAQ.
Why use it?
It exposes unclear customers, problems, and differences before you spend time building.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Use it to pressure-test a product or feature idea and produce a grounded press release and FAQ.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ohong/agent-skills/press-release-faq
Install

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.

Any agent
npx skills add ohong/agent-skills --skill press-release-faq
Clone the repo
git clone --depth 1 https://github.com/ohong/agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for press-release-faq

README.md
[![agentmods](https://agentmods.dev/badge/skills/ohong/agent-skills/press-release-faq/github.svg)](https://agentmods.dev/skills/ohong/agent-skills/press-release-faq)
Your own site
<a href="https://agentmods.dev/skills/ohong/agent-skills/press-release-faq"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/press-release-faq/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.

agentmods 80×15 button for press-release-faq

Your own site · 80×15
<a href="https://agentmods.dev/skills/ohong/agent-skills/press-release-faq"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/press-release-faq.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,629 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00132 $0.01629
Opus 5 $0.00066 $0.00814
Sonnet 5 $0.00026 $0.00326
Haiku 4.5 $0.00013 $0.00163

Measured 9d ago against content hash 5b8bffa8ea54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

press-release-faq 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 9d 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.

press-release-faq/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Press Release / FAQ (Working Backwards)

Write the press release and FAQ before the product exists — Amazon's Working Backwards method (Bryar & Carr). The PR/FAQ is a truth-seeking document, not a sales pitch. Its job is to force clarity on who the customer is, what problem is being solved, and why this solution is meaningfully better than what exists today. Most PR/FAQs should reveal weaknesses; that is the point.

Run fully autonomously. Make every judgment call yourself (customer segment, launch date, pricing, differentiation). Do not ask the user questions.

Scope

  • Default: the entire product/project described by the repo.
  • If the user names a feature or change: write the PR/FAQ for that feature only, treating the existing product as the status quo customers use today.

Step 1 — Gather context from the codebase

Read the written documentation first; it carries the intent. Priority order:

  1. README.md (root, then subdirectories)
  2. Specs, PRDs, design docs, RFCs — search for *.md in docs/, specs/, design/, rfcs/, and the repo root (e.g. SPEC.md, PRD.md, VISION.md, ROADMAP.md, CLAUDE.md)
  3. package.json / pyproject.toml / Cargo.toml etc. — name, description, dependencies (reveals capabilities)
  4. Top-level code structure — routes, commands, models, UI pages — to infer what the product actually does and doesn't do

Extract: what the product is, who it seems to be for, what problem it addresses, what exists today vs. what is planned, and any stated positioning or pricing. Where docs are silent, infer from code; where code is silent, make a reasonable decision and commit to it.

Step 2 — Work backwards from the customer

Before writing, answer these for yourself (they shape every sentence):

  • Who exactly is the customer? A specific segment, never "everyone." If the docs say "developers," decide which developers.
  • What is their most important problem? From the customer's point of view, not the builder's. Not all problems are equal — pick the one with the largest willingness to pay.
  • What do they use today? There is always a current solution. Name it.
  • On which dimension is this better, cheaper, or faster? If the answer is "none," the PR/FAQ should say so honestly in the FAQ — do not paper over a copycat.
  • What behavior change are we asking for? Customers must switch from something.

Read the full file on GitHub · 95 lines

Changes

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.

  1. 9d ago First seen · 95 lines · 132 tokens per session scan A 5b8bffa8ea54

Subscribe to this mod's changes

press-release-faq is a skill published in the GitHub repository ohong/agent-skills (3 stars, last pushed 9d ago), licensed MIT. It adds 132 tokens to every session and 1,629 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens