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.
npx skills add ur-grue/autopunk-media-skills --skill press-release-writergit clone --depth 1 https://github.com/ur-grue/autopunk-media-skillsWrote 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.
[](https://agentmods.dev/skills/ur-grue/autopunk-media-skills/press-release-writer)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/press-release-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/press-release-writer/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.
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/press-release-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/press-release-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.01443 |
| Opus 5 | $0.00016 | $0.00722 |
| Sonnet 5 | $0.00006 | $0.00289 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
press-release-writer 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Press Release Writer
What This Skill Does
Writes a complete, newswire-ready press release from a briefing note, following inverted-pyramid structure and standard AP/PR-wire conventions.
When To Use This Skill
- You need to announce a product launch, partnership, appointment, award, or organisational milestone
- You have a briefing note or bullet-point facts and need a publication-ready document within the hour
- You want a draft that wire services (PR Newswire, Business Wire, Globe Newswire) will accept without structural edits
- The communications team is small and needs to produce multiple releases in a single day
What You Need To Provide
Required: The core announcement (what happened, who is involved, when, where); at least one attributed quote from a named spokesperson with their title; the organisation's city/state of origin for the dateline.
Optional: Embargo date and time; a second quote from a partner, client, or external voice; supporting data or statistics; background context; boilerplate "About" paragraph; media contact name, phone, and email.
How the Assistant Approaches This
- Identifies the single most newsworthy fact and places it in the headline and opening sentence — no "we are pleased to announce" throat-clearing.
- Builds the first paragraph to answer who, what, when, where, and why-it-matters in under 50 words.
- Expands in subsequent paragraphs in descending order of news value, integrating quotes at natural breaks rather than front-loading them.
- Closes with boilerplate, embargo notice (if provided), and a standard media contact block formatted for wire distribution.
- Flags any factual gaps that would require confirmation before publication.
Output Format
400–600 words. Headline in title case, sub-headline optional. Dateline in AP style (CITY, State, Month DD, YYYY —). Body in short paragraphs (2–3 sentences each). One or two pull quotes in quotation marks with full attribution. "###" end mark. Contact block at the foot. Plain prose — no bullet points in the body. Tone: neutral third-person, factual, formal but not stiff.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 99 lines · 32 tokens per session scan A bcd5ad5ab15c
press-release-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 32 tokens to every session and 1,443 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
Launch Communications Generator
Draft launch communications: an announcement / press release, an internal support FAQ, and a customer-facing feature summary. Use for launch comms, press release, announcement, and messaging.
press-kit
Use when writing a press release or assembling a media kit a journalist can lift from — launches, funding, exec hires, partnerships, milestones, awards, or an online newsroom. Symptoms include a release that reads like an ad, a buried lede, no quotable line, or a missing dateline, boilerplate or asset. NOT finding the…
xiaoyuzhou-podcast-notes
A workflow that turns a public Xiaoyuzhou FM podcast episode into structured Markdown notes and a saved transcript. Xiaoyuzhou FM is a Chinese podcast platform.
c-research
Summarize web URLs, PDFs, YouTube videos, and podcasts using the summarize CLI. Instantly extract key points from any content type without manual reading. Useful for research, link digests, and media review.
transcript-ingestion
Transcript ingestion authority — capture, normalize, and prioritize transcripts from YouTube videos, podcast pages, captions, show notes, and transcript-like page content for persona systems, RAG pipelines, and grounded synthesis.
youtube-seo-competitor
Advanced YouTube competitor intelligence. Detects direct competitors, extracts winning title/thumbnail/hook patterns from transcripts, infers retention strategies from pacing, correlates posting cadence with performance, and identifies format-market-fit gaps. Use when user says "YouTube competitor analysis", "what are…