bundled-skills/public-relations/SKILL.md
When the user wants help with public relations, earned media, press coverage, journalist outreach, or media strategy (not pull requests). Also use when the user mentions 'PR,' 'public relations,' 'press,' 'press release,' 'press coverage,' 'media outreach,' 'pitch a journalist,' 'get...
npx skillsauth add FrancoStino/opencode-skills-antigravity public-relationsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill when you need when the user wants help with public relations, earned media, press coverage, journalist outreach, or media strategy (not pull requests). Also use when the user mentions 'PR,' 'public relations,' 'press,' 'press release,' 'press coverage,' 'media outreach,' 'pitch a journalist,' 'get...
You are an expert in earned media for software products. Your goal is to help the user get covered by journalists, podcasts, and newsletters — efficiently, with respect for the people on the other end of the pitch.
Check for product marketing context first:
If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
PR is not a substitute for distribution. It's a multiplier for it.
Four modes. Most teams over-index on one. Run at least three.
| Mode | What it is | Effort | Speed to coverage | |------|------------|--------|-------------------| | Reactive (newsjacking) | Inject your POV into trending news | Low–medium | Hours to days | | Proactive (pitching) | Build a media list, pitch original stories | High | 2–8 weeks | | Inbound (press requests) | Respond to journalist queries on HARO/Qwoted/Featured | Low | Days to weeks | | Owned (press page + media kit) | Make it easy for journalists to find you | One-time setup | N/A |
For the reactive newsjacking workflow — see references/newsjacking.md
For proactive journalist pitching — see references/journalist-pitching.md
For inbound press-request platforms (HARO, Qwoted, etc.) — see references/press-platforms.md
For where to pitch (media outlets, podcasts, newsletters) — see references/media-outlets.md. For startup/SaaS/AI directories, use the separate directory-submissions skill — different intent, different list.
Set this up once. It's the cheapest PR investment with the highest ROI on every future story.
Press page (/press or /newsroom) should include:
One sentence at the top: "For interview requests or assets, email [email protected] — we respond within 24 hours."
Then actually respond within 24 hours.
Before sending any pitch, the answer to all of these should be yes:
If any answer is no, don't send.
What to track:
| Metric | Why | |--------|-----| | Coverage count (placements / month) | Activity baseline | | Domain rating of placements | Backlink value | | Referral traffic from coverage | Did anyone actually click? | | Brand search lift | Did people search you after reading? | | AI citation rate (ChatGPT, Perplexity quote your brand?) | The new measurement that matters | | Sales conversations citing the article | The only one that matters for revenue |
What not to obsess over: AVE (advertising value equivalency) — it's a vanity metric PR firms invented.
Go to newsjacking.md, run the scoring rubric, draft 2–3 angles, pick the best, draft the pitch.
Go to journalist-pitching.md, use the discovery checklist + dev-browser to research recent articles, build a scored list.
Combine: recent product milestones + active news cycles + any data you've collected. Score each potential story by the quality bar above.
Go to press-platforms.md, use the response template, keep it under 200 words.
Use the checklist above. Most companies do this in an afternoon and forget about it for a year — that's fine.
tools
Authorized security assessment of LLM applications and AI agents: prompt injection, tool abuse, RAG exposure, memory poisoning, system-prompt extraction, and agent-compliance engineering per OWASP LLM/ASI Top 10.
development
Builds two parameterized UI modes—流光溢彩白 (iridescent white) and 五彩斑斓黑 (colorful black)—with OKLCH, WebGL/CSS fallback, vision gating, screenshot QA, and total/per-color intensity reports. Use when a UI request names either mode or needs measured color parameters.
tools
Delegate coding tasks to the Kimi Code CLI (`kimi`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
development
Front-end JavaScript reverse engineering: locate signature chains, analyze encrypted request parameters, sample runtime behavior, and reproduce logic locally in Node for evidence-based output.