product-communications
Skill2 starsChanged 29 days agoMITView on GitHub
When the user wants a product announcement, media or analyst briefing, executive thought leadership, reactive messaging, or a PR narrative. For launch sequencing, see launch-strategy; for final copy, see marketing-copy.
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- account-based-marketingSkill
- acquisition-conversionSkill
- ad-creativeSkill
- analytics-trackingSkill
- aso-auditSkill
- buyer-resourcesSkill
- cold-emailSkill
- community-marketingSkill
- competitor-alternativesSkill
- competitor-profilingSkill
- content-strategySkill
- customer-marketingSkill
- customer-researchSkill
- email-sequenceSkill
- eventsSkill
- go-to-market-strategySkill
- icp-and-buyer-personasSkill
- launch-readiness-checkSkill
- launch-strategySkill
- localization-claimsSkill
- market-entry-briefSkill
- market-entry-orchestrationSkill
- marketing-copySkill
- marketing-experimentationSkill
- market-intelligenceSkill
- messaging-consistency-auditSkill
- messaging-frameworkSkill
- objection-intelligenceSkill
- output-quality-checkSkill
- paid-adsSkill
- partner-marketingSkill
- positioning-strategySkill
- pricing-strategySkill
- product-activationSkill
- product-marketing-contextSkill
- referral-programSkill
- revopsSkill
- sales-enablementSkill
- search-discoverabilitySkill
- social-contentSkill
- ssot-context-loopSkill
- upgrade-conversionSkill
- website-buyer-journeySkill
- win-loss-intelligenceSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Before planning, read ../_shared/evidence-gaps.md for evidence labels, Inputs and assumptions, and ranked evidence gaps.
- Very specific: line 22
Read ../_shared/creative-brief.md when briefing announcement visuals or explainer narrative.
- Very specific: line 59
Never manufacture customer/executive/analyst quotes, statistics, adoption, media coverage or interest, endorsements, or leadership claims.
- Very specific: line 61
Keep draft claims sourced and approved.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Product Communications
Develop PMM narrative and orchestration for product-related communications. This is not a generic PR agency toolkit. It does not promise coverage, media interest, or analyst endorsement, and it does not own final marketing-copy.
Before planning, read ../_shared/evidence-gaps.md for evidence labels,
Inputs and assumptions, and ranked evidence gaps.
Product communications boundary
Own product narrative, newsworthiness, spokesperson briefs and product-related media/analyst coordination.
Company, partnership, research or executive material is in scope only when it supports a product/category story. Funding, corporate affairs, investor relations and crises route to the corporate communications owner.
Consume approved go-to-market-strategy; final assets remain with execution owners.
Read ../_shared/creative-brief.md when briefing announcement visuals or explainer narrative.
Workflow
Distinguish buyer/user intelligence from journalist, analyst or other recipient needs when choosing narrative and outreach.
- Define communication objective and audience: product/company/partnership/ funding/research announcement, executive thought leadership, media or analyst briefing, or reactive FAQ.
- Identify the actual news or audience-relevant idea. If the announcement has no material change or useful audience reason, say so and recommend a more suitable channel or no announcement.
- Load relevant canonical positioning, product truth, claims, and proof using
../_shared/ssot-consumption.md. Record version/files and unresolved gaps. - Develop narrative, message hierarchy, approved proof, spokesperson, support assets, distribution/outreach direction, owners and approvals, and measures.
- Mark proposed quotes exactly
DRAFT / REQUIRES APPROVALuntil approved by the named speaker. Do not simulate external interest or endorsement. - Route final copy to
marketing-copy; coordinate product launches withlaunch-strategy, partnerships withpartner-marketing, and asset review withmessaging-consistency-audit.
Required output
Inputs and assumptions; objective and audience; newsworthiness assessment;
canonical inputs; announcement narrative and hierarchy; proof/claims register;
spokesperson and quote status; supporting assets; distribution direction;
measurement; approvals, risks, and ranked evidence gaps. Possible formats are
an announcement brief, press release structure, media pitch direction,
spokesperson points, FAQ, briefing document, or launch narrative. Output
quality: output-quality-check can check these requirements, sourcing,
approval states, news rationale, and prohibited inventions.
Safety and boundaries
- Never manufacture customer/executive/analyst quotes, statistics, adoption, media coverage or interest, endorsements, or leadership claims.
- Keep draft claims sourced and approved. External messages are market-facing:
use
messaging-consistency-auditfor vertical SSOT and horizontal asset validation. Output quality and messaging alignment have separate statuses. - Route potential canonical changes through
ssot-context-loop; never edit canon. For launch readiness, uselaunch-readiness-checkafter the launch assets and approvals are ready. - This skill provides narrative and orchestration.
marketing-copyowns final press release, pitch, FAQ, and announcement copy where requested.
Related skills
launch-strategy, launch-readiness-check, partner-marketing, marketing-copy,
messaging-consistency-audit, ssot-context-loop, output-quality-check.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

