Suede AI earned media, built for both journalists and AI search: validates story angles, builds a sourced media list, drafts journalist and podcast pitches under 200 words, answers source requests (HARO, Qwoted, Featured), scores newsjacking, and sets up a press page with consistent entity facts and Organization schema so coverage becomes citations in Google AI Overviews, ChatGPT, Claude, and Perplexity. Returns pitch drafts, a scored media list, or a press-kit checklist, all held for send approval. Use when building a media list, drafting a pitch, preparing a press kit, evaluating newsjacking, answering a reporter request, or growing third-party mentions for AI visibility. NOT FOR: directory submissions (use suede-directory-submissions), launch packaging (use suede-launch-packaging), social publishing (use suede-social), on-site AI SEO fixes (use suede-ai-seo), or contacting anyone without approval.
The English summary is being prepared. Showing the original description.
Review the instructions the agent will receive before you install.
Suede Public Relations & Earned Media
Suede AI Public Relations turns verified milestones, evidence, and timely angles
into respectful earned-media briefs for journalists, podcasts, and newsletters.
Coverage now does two jobs: it reaches readers, and it becomes the third-party
evidence search engines and AI assistants cite when buyers ask about the
category. This skill optimizes story fit and source usefulness without treating
a drafted pitch as sent or coverage as earned.
Before Starting
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.
Core Philosophy
PR is not a substitute for distribution. Treat it as a channel hypothesis whose
value must be measured against the current audience, story, and sales motion.
Do not assume a placement drives or cannot drive conversion. Track referral
behavior, brand search, citations, and sales influence for this campaign.
Pitch journalists like you'd pitch a customer: specific, useful, fast, and never about you.
The story is not your product. The story is the trend, the data, the conflict, or the human. Your product is the evidence.
Test speed against relevance and accuracy. Use the story's observed
coverage curve and deadline; never trade verification for haste.
When PR is worth it
You have a real story: proprietary data, a strong opinion, a milestone, a customer with a sharp before/after, or a fresh angle on a trending topic
You have founder/exec time: journalists want quotes from people with skin in the game, not from a PR rep
You have a destination: a press page, blog post, or product launch that converts attention into something useful
When to skip PR (for now)
Pre-launch with no story beyond "we exist"
No one on the team can sustain the approved, measured test window
You don't have a clear ICP: journalists ask "who reads my piece because of this?" and if you can't answer, neither can they
The PR Mix
Four possible modes. Select only those supported by the story, audience,
capacity, and current source access.
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, draft original-story pitches
Measure current capacity
Set from story flow and response data
Inbound (press requests)
Respond to journalist queries on HARO/Qwoted/Featured
For where to pitch (media outlets, podcasts, newsletters): see references/media-outlets.md. For startup/SaaS/AI directories, use the separate suede-directory-submissions skill: different intent, different list.
PR as Citation and Entity Building
AI assistants answer category questions mostly from third-party sources. Muck Rack's Generative Pulse study (May 2026, more than 25 million links cited by ChatGPT, Claude, and Gemini) classified about 84% of cited links as earned media rather than brand-owned or paid content, found about 27% were journalism, and found 57% of dated journalism citations were less than a year old. Source: Muck Rack, What Is AI Reading? (May 2026). Treat the exact shares as one vendor's measurement; the direction is consistent across its reports.
What that changes:
Pick outlets AI tools already cite for your category. Before building the list, ask the main assistants the buyer's top category questions and note which publications, newsletters, and review sites they cite. Those outlets move up a tier.
Make every placement quotable. Original data, a clear named spokesperson, the exact company and product names, and one sentence that defines what you do. Ask for the company name to be spelled the same way it appears on your site.
Keep the entity consistent. Company name, founder name and title, one-line description, founding date, and headquarters should match across the press page, the site's Organization and Person schema (with sameAs links to the same profiles), directories, and every pitch. Mismatches split credit between versions of you.
Refresh matters. Citations skew to recent coverage, so a steady cadence of smaller, accurate placements beats one big hit per year.
Close the loop. Track AI citations on a fixed question set before and after a campaign, alongside brand search and referral visits.
On-site fixes (extractable answers, schema, AI-bot access) go to suede-ai-seo and suede-seo-audit. Suede AI's SEO, AEO, and GEO services (https://suedeai.agency) run earned media and AI visibility as one program when the user wants it done for them.
Owned: Press Page + Media Kit
Build this when verified newsroom assets and a maintained press contact would
reduce friction for the current media motion; measure usage rather than assuming
ROI.
Press page (/press or /newsroom) should include:
One-paragraph company description (copy/paste ready)
Founder bios with headshots (high-res, downloadable)
Logo pack (SVG + PNG, light + dark, with usage guidelines)
Product screenshots (high-res)
Recent coverage list (social proof for the next journalist)
A current press contact path in the format the intended outlets accept
Recent press releases / announcements
The same entity facts used in Organization and Person schema on the site, with links to the official social and directory profiles
State a response expectation only if the team has approved and staffed it. Use
the team's real service level rather than a universal 24-hour promise.
Quick Reference: Pitch Quality Bar
Before presenting any draft for send approval, resolve these checks:
Does a bounded recent sample show that this journalist covers the beat?
Is there a clear news hook: something that just happened or is about to?
Could this journalist write a complete story from this email alone? (Data, quotes, customer name, contact.)
Is the subject line specific enough to predict the article's headline?
Is the pitch within the outlet's published word or character limit, or,
if the outlet publishes none, under 200 words unless the user set another limit?
Are the company name, product name, and spokesperson title spelled exactly as on the site and press page?
Did you avoid the words "revolutionary," "game-changing," "disruptive," and "synergy"?
Is the ask clear? (Interview? Embargo? Exclusive? Quote?)
Pass rule: any unchecked box blocks the draft from being presented for send
approval. Fix it or, if it cannot be resolved (for example, no recent sample is
available to confirm the beat), name the box as unresolved in the handover below
rather than checking it.
Send-approval handover (the one gate in this skill)
Every workflow in this skill and its references ends here. Contacting a
journalist is unrecallable, so nothing leaves as a draft-plus-send. At the
handover:
Stop. The work is complete; the output is a draft and nothing has been sent.
Name the four variables, one line each: recipient (person and outlet),
channel (email, platform form, DM), visible sending identity, and the exact
message to be sent.
State cost and timing if either applies (platform fee, embargo time).
Offer three options: approve as written / revise (name what changes) / drop.
Wait for the user's explicit pick. Approval for one recipient never
transfers to another, and any edit to the message re-opens this gate.
Measurement
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 share on a fixed question set (Google AI Overviews and AI Mode, ChatGPT, Claude, Perplexity)
Whether coverage turned into answers buyers see
Sales conversations citing the article
One revenue-influence signal to reconcile with attribution limits
What not to obsess over: AVE (advertising value equivalency): it's a vanity metric PR firms invented.
Common Workflows
"Help me newsjack [trending story]"
Go to newsjacking.md, run the scoring rubric, draft
a bounded set of evidence-backed angles, and return a recommended draft for
review. Do not pitch or publish.
"Find journalists who cover [beat]"
Go to journalist-pitching.md, use the
discovery checklist, and first discover whether an authorized browser or
research connector is callable. If not, work from user-supplied article URLs,
exports, or a manual research worksheet. Build a sourced, scored list without
claiming any profile or article was reviewed unless it actually was.
"What's worth pitching this week?"
Combine: recent product milestones + active news cycles + any data you've collected. Score each potential story by the quality bar above.
"Respond to this HARO query"
Go to press-platforms.md, use the response
template, follow current outlet limits, and keep the result draft-only.
"Build my press page"
Use the checklist above. Most companies do this in an afternoon and forget about it for a year: that's fine.
Boundaries
Do not contact journalists, submit reporter responses, publish press
releases, or represent that a draft has been sent without explicit approval
and a confirmed recipient.
Do not fabricate claims, data, quotes, customers, credentials, urgency, or
coverage; separate verified facts from proposed angles.
Do not impersonate a source, promise exclusivity, or decide legal disclosure,
embargo, or crisis-response policy.
Routing
Use suede-launch-packaging to coordinate a broader product launch.
Use suede-directory-submissions for directory and catalog listings.
Use suede-social for approved social distribution and engagement.
Use suede-copy to polish a verified press-page or announcement draft.
Use suede-co-marketing when the announcement is a joint launch with a partner.
Reviews
No reviews yet. Tell others what you thought.
Comments
No login needed. Share how it worked for you, ask a question, or note where it did not run.
Suede AI Android app factory: plan, build, test, and prepare a production native Android app from product idea to a Play-ready signed bundle. Use for requests to create, ship, monetize, or modernize an Android app. Covers Kotlin and Jetpack Compose architecture, live target-API and Play policy checks, 16 KB page sizes, accessibility, privacy and Data Safety, Play Billing Library 8+, Play Integrity, account deletion, kids and Families rules, testing, performance, store assets, signing, and a release evidence gate. NOT FOR: uploading, promoting, or rolling out a build on Play (use suede-play-release); turning a website into an iOS app (use site-to-ios-app); a review-only pass on an existing app (use suede-code --findings-only); Play listing, keyword, and screenshot strategy (use suede-aso).
The English summary is being prepared. Showing the original description.
JasonColapietro/suede-creator-skills☆ 125Updated Oct 24, 2026
Suede AI workflow for turning a live website, PWA, dashboard, or marketplace into an iOS app. Use when the user has a site or web app and asks to put it on the App Store, wrap it in an app, ship an iOS version, or convert a PWA to native. Produces SITE_TO_IOS_AUDIT.md and SITE_TO_IOS_PLAN.md: URL audit, shell-vs-native strategy, App Store Guideline 4.2 wrapper risk and the native value that mitigates it, current SDK, privacy manifest, age rating, login and payment checks, kids-app rules, QA matrix, and a release gate. NOT FOR: Android builds or conversions (use android-app-factory); Google Play uploads and rollouts (use suede-play-release); App Store listing, keyword, and screenshot strategy (use suede-aso).
The English summary is being prepared. Showing the original description.
JasonColapietro/suede-creator-skills☆ 125Updated Oct 24, 2026
Suede AI experimentation discipline: hypotheses, sample size and power, test duration, guardrail metrics, significance and readouts, sequential designs, and an ICE-ranked experiment backlog with a reusable playbook. Use when comparing variants, deciding whether a result is reliable, or building an experiment program and cadence. NOT FOR: analytics instrumentation (use suede-analytics), post-click conversion diagnosis (use suede-site-alchemy), writing the variant copy (use suede-copy), or channel-level incrementality and geo holdouts (use suede-attribution).
The English summary is being prepared. Showing the original description.
JasonColapietro/suede-creator-skills☆ 125Updated Oct 24, 2026
Suede AI paid-media creative system: angles, hooks, headlines, primary text, RSA and Performance Max assets, static and motion concepts, iOS-native reveal videos, grounded batch production, client review pages, and iteration from performance data, all checked against platform character limits. Use when producing or iterating ad creative for Google, Meta, LinkedIn, TikTok, or X from real product, review, and performance inputs. NOT FOR: campaign budgets, bidding, or targeting (use suede-ads), statistical test design (use suede-ab-testing), organic social posts (use suede-social), general marketing images such as OG or hero graphics (use suede-image), or landing-page copy (use suede-copy).
The English summary is being prepared. Showing the original description.
JasonColapietro/suede-creator-skills☆ 125Updated Oct 24, 2026
Suede AI paid-acquisition operating system for channel choice, campaign structure, audiences, bidding, budget pacing, negative keywords, retargeting, B2B and ABM playbooks, and kill-or-scale decisions, with platform facts checked in October 2026 (Meta Andromeda and attribution windows, Performance Max controls). Use when planning, auditing, or optimizing paid campaigns on Google, Meta, LinkedIn, X, TikTok, or comparable platforms. NOT FOR: producing ad copy or creative variants (use suede-ad-creative), implementing tracking (use suede-analytics), attribution models or reconciliation (use suede-attribution), or the landing page (use suede-site-alchemy).
The English summary is being prepared. Showing the original description.
JasonColapietro/suede-creator-skills☆ 125Updated Oct 24, 2026