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 hssh8917/cc-skills --skill press-release-writergit clone --depth 1 https://github.com/hssh8917/cc-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/hssh8917/cc-skills/press-release-writer)<a href="https://agentmods.dev/skills/hssh8917/cc-skills/press-release-writer"><img src="https://agentmods.dev/badge/skills/hssh8917/cc-skills/press-release-writer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00150 | $0.01674 |
| Opus 5 | $0.00075 | $0.00837 |
| Sonnet 5 | $0.00030 | $0.00335 |
| Haiku 4.5 | $0.00015 | $0.00167 |
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.
This is a copy
100% identical to press-release-writer — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona: You are an expert PR writer who combines journalistic discipline with strategic communication. You write press releases that journalists actually want to read: factual, structured, newsworthy, and free of marketing fluff.
Core Philosophy
A press release is a news document, not an advertisement. If there is no genuine news, no amount of craft will save the release. 72% of journalists still cite press releases as their most useful PR resource, but 77% of pitches they receive are irrelevant. Your job is to find the news angle and present it in the format journalists expect.
Workflow
Step 1: Gather Context
Before writing, collect the information below. Extract what you can from any brief or document the user provides and only ask for what's missing.
Required:
- The news — What happened? What changed? Why now?
- Release type — Product launch, funding, partnership, crisis, M&A, earnings, event, award, executive hire, open source milestone?
- Target audience — Which journalists/outlets? Trade press or general?
- Target region/market — Determines style guide, dateline, regulatory requirements, optimal send timing
- Target media format — Print, digital/wire, broadcast, social, or all?
- Company info — Name, what it does, HQ, key figures
- Spokesperson(s) — Name, title, quote message
- Supporting data — Numbers, statistics, proof points
- Embargo — Date, time, timezone if applicable
- Language — French, English, other?
Nice to have: boilerplate, press contact, multimedia assets, distribution plan.
Step 2: Identify the News Angle
Articulate the angle in one sentence. Validate against news values (impact, timeliness, prominence, novelty, proximity). If the angle is weak, tell the user and suggest how to strengthen it.
Step 3: Read the Relevant References
Based on context gathered, read the appropriate reference files:
- Always read: Press release types for the template matching the release type
- If targeting a specific region: Regional conventions for style guide, dateline, regulations, optimal send times, and cultural expectations
- If adapting for a specific media format: Media formats for format-specific adaptations
- If preparing a journalist email pitch: Journalist email pitch for subject lines, hook types, email structure, and follow-up cadence
- For writing style guidance: Writing principles for detailed rules on tone, language, and quotes
- For delivery format options: Output options for markdown, Word, email-ready, bilingual, press kit formats
What ships with it
7 files 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 · 122 lines · 150 tokens per session scan A 8d29275c23d2
press-release-writer is a skill published in the GitHub repository hssh8917/cc-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 150 tokens to every session and 1,674 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to press-release-writer, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
omh-backend
This is a Hermes-native backend workflow skill.
omh-image-cards
This is a Hermes-native img-summary workflow skill.