Skip to content

Fresh entity pages

New and Recently Updated Skills

Verified Agent Skills sorted by source update date. This is where newly published SKILL.md files should surface first.

Snapshot 2026-09-023908 verified skills
#3323

Campaign Plan

Generate a complete multi-channel campaign plan document — SMART objectives, audience segments with targeting criteria, channel mix with rationale, a budget allocation table with reach/cost estimates, a phased timeline from pre-launch to wrap-up, a KPI framework, and a risk register. Plans only; it does not launch or modify campaigns. Triggers on \"/digital-marketing-pro:campaign-plan\", \"plan a campaign for our product launch\", \"build the Q3 campaign plan\", \"what channels and budget for lead gen\", \"draft a campaign timeline with KPIs\". Reads the brand profile, guidelines, and agency SOPs, and reuses the /digital-marketing-pro:campaign-orchestrator reference docs for planning frameworks instead of re-deriving them.

CommunicationClaude Code
#3324

Campaign Status

Unified status dashboard for every tracked campaign across connected platforms — produces a summary table with health indicators, live spend and performance metrics, a 7-day execution history, pending approvals with age, KPI variance classification (on track / at risk / behind), flagged issues, and next scheduled actions. Reports only; it changes nothing on any platform. Triggers on \"/digital-marketing-pro:campaign-status\", \"what campaigns are running right now\", \"any failed executions or stuck approvals\", \"status of the Q1-Launch campaign\", \"which campaigns are behind target\". Reads the brand's campaign registry, execution log, and approval queue via campaign-tracker.py, execution-tracker.py, and approval-manager.py, plus live metrics from connected platform MCPs.

CommunicationClaude Code
#3325

Case Study Plan

Build a complete case-study creation blueprint — a Challenge-Solution-Results narrative framework, 15-20 client interview questions plus 10 internal-team questions, a data-visualization plan, format specifications (PDF, web page, slide deck, video script outline, social snippets, sales one-pager), a distribution strategy, a permission/approval checklist, and a draft executive summary. Plans the case study; it does not produce the finished designed asset. Triggers on \"/digital-marketing-pro:case-study-plan\", \"turn this client win into a case study\", \"what should we ask the client in the interview\", \"plan a success story for sales enablement\", \"case study formats and distribution plan\". Reads the brand profile, guidelines, custom templates, and agency SOPs.

CommunicationClaude Code
#3326

Check

Run the unified pre-publish quality gate on marketing content — wraps scripts/eval-runner.py to score hallucination risk, claim substantiation (with --evidence), brand-voice fit (with --brand), structure (with --schema), content quality, and readability, plus a C2PA provenance check for AI assets in EU-targeted campaigns; returns a composite score with a PASS / WARN / BLOCKED decision and per-issue fix suggestions. Reports only — it never edits the content. Triggers on \"/digital-marketing-pro:check\", \"is this safe to publish\", \"run a hallucination check on this draft\", \"validate this copy against the brand voice\", \"pre-publish quality gate\". Resolves the active brand profile automatically; pairs with /digital-marketing-pro:c2pa-metadata to fix missing manifests.

CommunicationClaude Code
#3327

Churn Risk

Score customer segments for churn risk from behavioral signals — email engagement decline, purchase recency, usage drops, support sentiment — producing a 0-100 risk scorecard with four tiers, per-tier intervention playbooks (actions, timing windows, channels, messaging), LTV-at-risk totals, and retention-ROI prioritization. Assesses and recommends; it does not send outreach or launch campaigns. Triggers on \"/digital-marketing-pro:churn-risk\", \"which customers are about to churn\", \"score our segments for churn risk\", \"email engagement is dropping, who is at risk\", \"build a retention intervention plan\". Pulls behavioral data from a connected CRM MCP (Salesforce or HubSpot) or user-provided exports, runs scripts/churn-predictor.py, and reads the brand profile for lifecycle context.

CommunicationClaude Code
#3328

Client Onboarding

Generate a complete onboarding package for a new marketing client — kickoff meeting agenda, 20-30 question discovery questionnaire, stakeholder map with RACI matrix, platform-by-platform access checklist, 30-60-90 day milestone plan, communication cadence, escalation protocol, welcome email template, internal team brief, risk register, and a day-by-day first-week action plan. Triggers on \"/digital-marketing-pro:client-onboarding\", \"we just signed a new client\", \"build a kickoff agenda and discovery questionnaire\", \"30-60-90 day plan for the new account\", \"what access do we need from the client\". Reads the brand profile, guidelines, custom templates, and agency SOPs so the package matches house process.

CommunicationClaude Code
#3329

Client Proposal

Draft a professional agency proposal or pitch document for a prospective client — executive summary, situation analysis, scope of services with a deliverables matrix, KPI targets with baselines and stretch goals, 2-3 pricing options, team bio structure, case-study placeholders, terms outline, and next steps, written from the agency's perspective. Triggers on \"/digital-marketing-pro:client-proposal\", \"write a proposal for this prospect\", \"scope of work for a 6-month retainer\", \"respond to this RFP\", \"pitch deck outline with pricing tiers\". Loads the agency's own brand profile (not the client's), plus custom templates and agency SOPs; industry benchmarks inform the KPI and pricing sections.

CommunicationClaude Code
#3330

Client Report

Generate a white-labeled client report in agency voice — weekly pulse, monthly review, or QBR — with a KPI scorecard vs targets and comparison period, channel breakdowns, top wins with attribution, root-cause analysis of misses, 3-5 strategic recommendations, and budget efficiency. Requires explicit approval before any external send; only then can it deliver via connected Slack, email, or Google Sheets MCPs and log the delivery. Triggers on \"/digital-marketing-pro:client-report\", \"prepare the monthly report for the client\", \"build the QBR for this account\", \"send the weekly performance pulse\", \"white-labeled performance report\". Reads the brand profile and pulls data via campaign-tracker.py, execution-tracker.py, and connected platform MCPs; formats via report-generator.py.

CommunicationClaude Code
#3331

Client Validation Document

Produce the Part 5 Client Validation Document — the one true stop of the 12-Part engagement where unbiased v1 findings from Parts 2-4 are compiled into 12-25 evidence-cited finding blocks, each awaiting an ACCEPT / REJECT / EDIT / DEFER client decision, plus a paired JSON response template. Recorded responses feed the Part 6 Decision Matrix (engagement-state.py) to determine v2 re-runs. Triggers on \"/digital-marketing-pro:client-validation-document\", \"prepare v1 findings for client review\", \"run part 5 client validation\", \"the one true stop\", \"record the client's validation responses\". Requires Parts 3-4 marked completed in _engagement.json; reads the eight v1 core documents; pairs with /digital-marketing-pro:engagement-workflow and /digital-marketing-pro:four-core-documents.

CommunicationClaude Code
#3332

Competitor Alerts

Configure a tiered competitor alert system — per-competitor trigger thresholds across content, pricing, ads, social, ranking, and SERP changes, with critical/warning/info urgency routing, digest batching, and alert-fatigue guardrails — then send test alerts to verify Slack or email delivery. Triggers on \"/digital-marketing-pro:competitor-alerts\", \"alert me when a competitor changes pricing\", \"set up competitor alerts\", \"too many competitor notifications\", \"tell me when competitors launch new ads\". Requires baselines from /digital-marketing-pro:competitor-monitor and persists config via competitor-tracker.py; reads the brand profile for competitive context.

CommunicationClaude Code
#3333

Competitor Monitor

Set up ongoing competitor monitoring — captures per-competitor baselines across content, pricing, ads, social, SEO, and SERP features, saves them via competitor-tracker.py, configures per-dimension scan schedules and alert rules, and produces an initial competitive intelligence brief with threat rankings. Triggers on \"/digital-marketing-pro:competitor-monitor\", \"track our competitors over time\", \"watch competitor pricing pages\", \"set up competitor tracking\", \"detect when competitors change their site\". Baselines power /digital-marketing-pro:competitor-alerts and share-of-voice trends. Reads the brand profile for competitive landscape context.

CommunicationClaude Code
#3334

Competitor Pages

Build competitor comparison and alternatives pages — X-vs-Y head-to-heads, alternatives-to-X lists, category roundups, and feature-matrix pages — delivering a 1,500+ word page template, comparison table, JSON-LD schema via schema-generator.py, keyword and title-tag targeting, an internal-linking plan, and fairness/accuracy guardrails. Triggers on \"/digital-marketing-pro:competitor-pages\", \"create a vs page\", \"build an alternatives page\", \"comparison page for our product\", \"best tools roundup for our category\". Produces page content and markup, not a live publish. Reads the brand profile and guidelines, especially restrictions on competitor mentions.

CommunicationClaude Code
#3335

Connect

Guide the connection of a known MCP integration to the plugin — looks up the connector registry via connector-status.py, checks current status, and returns transport-specific setup steps (OAuth for HTTP connectors, env-var credentials plus the exact .mcp.json block for npx connectors), verification steps, and the skills each connector unlocks. Triggers on \"/digital-marketing-pro:connect\", \"connect Google Ads\", \"hook up Slack to the plugin\", \"set up the HubSpot integration\", \"how do I add Mailchimp\". Guidance and status checks only — the user adds credentials themselves; unknown or custom servers route to /digital-marketing-pro:add-integration.

CommunicationClaude Code
#3336

Content Brief

Create a production-ready content brief a writer can execute without extra context — keyword map (primary, secondary, related questions), H2/H3 outline with key points and word-count targets, brand voice guidance, on-page SEO checklist, visual/media spec with AI-generation and C2PA provenance notes, and success metrics. Triggers on \"/digital-marketing-pro:content-brief\", \"write a brief for this topic\", \"brief a blog post on X\", \"what should this article cover\", \"outline and SEO requirements for a pillar page\". Preferred upstream of /digital-marketing-pro:content-engine. Reads the brand profile, guidelines, and compliance rules.

CommunicationClaude Code
#3337

Content Calendar

Generate a structured content calendar for a month, quarter, or custom range — topics mapped to platforms and publish dates, content-pillar and funnel-stage tags, repurposing chains from each core piece, SEO keyword targets, and owner assignments when team capacity is given. Triggers on \"/digital-marketing-pro:content-calendar\", \"plan next month's content\", \"build a quarterly editorial calendar\", \"what should we publish in March\", \"map our content pillars to a schedule\". Planning output only — it does not schedule or publish posts. Reads the brand profile, guidelines, and compliance rules for pillars and voice.

CommunicationClaude Code
#3338

Content Decay Scan

Scan the content library for decay — declining traffic, falling keyword positions, stale content, broken links, lost AI citations — scoring each URL 0-100 via creative-fatigue-predictor.py and ranking refreshes by recoverable revenue, with actionable refresh briefs and traffic-recovery estimates for top-priority tiers. Triggers on \"/digital-marketing-pro:content-decay-scan\", \"which content is losing traffic\", \"find stale content to refresh\", \"our blog traffic keeps dropping\", \"prioritize content refreshes\". Pulls performance data from Google Analytics/Search Console MCPs or exported CSVs; cross-reference causes with /digital-marketing-pro:seo-drift. Reads the brand profile for content strategy context.

CommunicationClaude Code
#3339

Content Engine

Draft marketing content in brand voice — blog posts, ad copy, email sequences, social posts, landing pages, and brand-voice guides — through a gated pipeline (research, outline, draft, fact-check, humanize, voice check, SEO checklist) with numbered working files and a five-gate quality scorecard before copy is publish-ready. Triggers on \"/digital-marketing-pro:content-engine\", \"write a blog post about X\", \"draft ad copy for this campaign\", \"create an email sequence\", \"landing page copy for our product\". Takes /digital-marketing-pro:content-brief as preferred upstream; hands off to /digital-marketing-pro:publish-blog, /digital-marketing-pro:content-repurpose, and /digital-marketing-pro:check. Reads the brand profile, guidelines, platform specs, and compliance rules.

CommunicationClaude Code
#3340

Content Repurpose

Turn one piece of content into a multi-channel repurposing plan — a derivative matrix targeting 10+ formats, full platform-adapted drafts, a publishing calendar, UTM-tagged links, and per-piece brand-voice scores; every derivative must pass the standalone test (own hook, own payoff) and the cut list records what failed it. Triggers on \"/digital-marketing-pro:content-repurpose\", \"repurpose this blog post\", \"turn this webinar into social posts\", \"get more mileage out of this article\", \"atomize this whitepaper\". Produces drafts and a schedule, not published posts. Reads the brand profile, channel style overrides, and platform specs.

CommunicationClaude Code
#3341

Context Engine

Load and manage the shared marketing context other skills build on — the active brand profile (voice, audiences, competitors, goals), industry benchmark profiles, geographic and industry compliance rules, platform specs, and scoring rubrics — plus brand switching and campaign-data persistence under ~/.claude-marketing/. Triggers on \"/digital-marketing-pro:context-engine\", \"switch to brand X\", \"what are the benchmarks for my industry\", \"which compliance rules apply to us\", \"load my brand context\". Pairs with /digital-marketing-pro:brand-setup to create profiles and /digital-marketing-pro:switch-brand to change them; its reference files are read by nearly every sibling skill.

CommunicationClaude Code
#3342

Continuous Improvement Loop

Run Part 12 of the engagement methodology — the continuous improvement loop that aggregates quarterly-review, customer-feedback, competitive, and operating signals into a Quarterly Product & Offering Improvement Brief for business leadership, plus fast 1-3 page ad-hoc briefs when a significant signal lands mid-quarter. Triggers on \"/digital-marketing-pro:continuous-improvement-loop\", \"run part 12\", \"produce the quarterly improvement brief\", \"aggregate this quarter's signals\", \"we need a fast read on this competitor move\". Flags v2.x update-back triggers but never auto-executes them. Reads monthly reports, signals.jsonl, /digital-marketing-pro:competitor-monitor outputs, and the Living Project Instruction File.

CommunicationClaude Code
#3343

Counter Narrative

Build a counter-narrative playbook responding to a competitor's positioning move — rebrand, category claim, aggressive campaign, price change, or partnership. Analyzes the move and its impact, selects a counter approach (direct counter, reframe, category counter, social proof, or zeitgeist) via narrative-mapper.py, and delivers a multi-channel response plan with content angles, ad concepts, PR angles, messaging guidelines, an urgency-calibrated timeline, and tracking metrics. Triggers on \"/digital-marketing-pro:counter-narrative\", \"competitor just rebranded, how do we respond\", \"they are claiming a new category\", \"respond to their attack campaign\", \"counter a competitor price cut\". Plans the response — it does not launch campaigns. Reads the brand profile and messaging guardrails.

CommunicationClaude Code
#3344

Cowork Setup

One-shot setup that wires Digital Marketing Pro for team use in Anthropic Cowork — verifies the sandbox via plugin-metadata.py, checks a Google Drive MCP is connected, creates the canonical Drive folder skeleton (_brands/, _runs/, _plans/), and writes the routing config via drive-sync-state.py so brand profiles, plans, and run checkpoints persist across sessions. Triggers on \"/digital-marketing-pro:cowork-setup\", \"set up DMP for my team in Cowork\", \"brand profiles aren't persisting between sessions\", \"route outputs to our shared Drive\", \"first-time Cowork install\". Run once per team; in local Claude Code it only offers optional Drive mirroring. Pairs with /digital-marketing-pro:brand-setup next and /digital-marketing-pro:doctor to verify routing.

CommunicationClaude Code
#3345

Creative Health

Assess ad creative fatigue across active campaigns — scores each creative 0-100 via creative-fatigue-predictor.py (CTR, CPM, and engagement vs baseline, frequency saturation, time running), predicts days until fatigue, and delivers refresh briefs, A/B test plans, and a priority list ranked by estimated spend waste. Triggers on \"/digital-marketing-pro:creative-health\", \"are our ads fatiguing\", \"CTR is dropping on our ads\", \"when should we refresh creatives\", \"which ads are wasting spend\". Needs per-creative performance data (exported or from connected ad platform MCPs). Analysis and recommendations only — it does not pause or launch ads. Reads the brand profile and visual-identity restrictions for refresh constraints.

CommunicationClaude Code
#3346

Creative Testing Framework

Design a structured ad creative testing playbook — prioritized variable matrix, isolated test grid, script-computed sample sizes and minimum budgets per variant, holdout control design, iteration cadence, and winner selection criteria. Plans the testing program; it does not launch or edit live ads. Triggers on \"/digital-marketing-pro:creative-testing-framework\", \"design an A/B test for our ads\", \"our ad creatives fatigue too fast\", \"build a creative testing roadmap\", \"how many conversions per variant do we need\". Reads the brand profile and guidelines, and pairs with /digital-marketing-pro:c2pa-metadata for AI-generated variants headed to EU placements.

CommunicationClaude Code
#3347

Credential Switch

Switch the active credential profile to a different client brand, validating each configured platform's API keys, env vars, and token expiry before anything runs — preventing cross-client data leaks and misrouted ad spend. Outputs a per-platform validation report plus a logged switch confirmation with audit trail. Triggers on \"/digital-marketing-pro:credential-switch\", \"switch to the other client's account\", \"activate Acme's API keys\", \"are the right credentials active\", \"change which brand we're working on\". Reads brand and credential profiles under ~/.claude-marketing/ and pairs with /digital-marketing-pro:client-onboarding when a profile is missing.

CommunicationClaude Code
#3348

Crisis Response

Assess a PR crisis and deliver a structured response plan — severity classification (Level 1-3), a ready-to-publish holding statement, tailored messaging per stakeholder group, an hour-by-hour communication timeline, and a trust-rebuilding roadmap. Drafts and plans only; it publishes nothing. Triggers on \"/digital-marketing-pro:crisis-response\", \"we're getting slammed on social media\", \"draft a holding statement fast\", \"a negative story just broke about us\", \"how do we respond to this backlash\". Reads the brand profile, voice settings, guidelines, and market compliance rules before drafting any statement.

CommunicationClaude Code
#3349

Crm Sync

Sync marketing data to and from Salesforce, HubSpot, Zoho, or Pipedrive — contacts, deals, and campaign links with field mapping, deduplication, consent checks, batched execution behind a mandatory approval gate, and a rollback manifest. Produces a full sync report with per-record outcomes. Triggers on \"/digital-marketing-pro:crm-sync\", \"push these contacts into HubSpot\", \"sync deals to Salesforce\", \"our CRM and marketing lists don't match\", \"set up a recurring CRM sync\". Reads the brand profile and compliance rules; for scored lead imports use /digital-marketing-pro:lead-import instead.

CommunicationClaude Code
#3350

Ad Creative

Generate 3-5 ad copy variations per platform — headlines, descriptions, and CTAs formatted to Google, Meta, LinkedIn, TikTok, X, and Pinterest specs — each scored 1-10 with policy-compliance flags, A/B testing groupings, and a message-match check against the landing page. Triggers on \"/digital-marketing-pro:ad-creative\", \"write ad copy for Meta\", \"give me RSA headline variations\", \"we need LinkedIn ad copy\", \"draft TikTok ad creative\". Reads the brand profile, guidelines, and compliance rules; routes video ad scripts to /digital-marketing-pro:video-script and gates AI-generated visuals for EU campaigns through /digital-marketing-pro:c2pa-metadata and /digital-marketing-pro:check.

CommunicationClaude Code
#3351

Cohort Analysis

Segment customers into cohorts — by acquisition period, channel, first behavior, or revenue tier — and produce a color-coded retention matrix, overlaid retention curves, LTV-by-cohort comparisons with LTV:CAC where cost data exists, best/worst cohort rankings with hypothesized drivers, stabilization-point analysis, and intervention recommendations for underperformers. Analyzes and recommends; it launches nothing. Triggers on \"/digital-marketing-pro:cohort-analysis\", \"are newer customers retaining better than older ones\", \"which channel produces the highest-LTV customers\", \"build a retention matrix\", \"when does our churn stabilize\". Pulls customer data from connected CRM and analytics MCPs, reads the brand profile for business-model context, and saves the summary as a campaign-tracker.py insight for trend tracking.

CommunicationClaude Code
#3352

Competitor Analysis

Run a multi-dimensional competitive teardown of 2-5 competitors — content strategy, SEO, paid ads, social, AI answer-engine visibility, and pricing/positioning — producing a competitor overview matrix, per-competitor SWOT, gap analysis, and strategic recommendations prioritized by opportunity size. Triggers on \"/digital-marketing-pro:competitor-analysis\", \"analyze our competitors\", \"how do we stack up against X\", \"competitive landscape report\", \"what are competitors doing that we aren't\". Point-in-time analysis, not ongoing tracking — pair with /digital-marketing-pro:competitor-monitor for that. Reads the brand profile, guidelines, and compliance rules.

CommunicationClaude Code
#3353

Cro

Audit landing pages, forms, pricing pages, and checkout flows for conversion killers, and design statistically sound A/B tests — ICE-prioritized recommendations, hypothesis templates, and script-computed sample sizes and significance checks. Advises and plans; it does not edit your site or run the tests. Triggers on \"/digital-marketing-pro:cro\", \"audit this landing page\", \"why is our conversion rate so low\", \"how long should this A/B test run\", \"reduce cart abandonment\". Reads the brand profile, industry benchmarks, and campaign history before making recommendations.

CommunicationClaude Code
#3740

Autofix

Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly

CodingClaude Code
#3741

Code Review

AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security).

DevOpsClaude Code
#3881

Analyzing Products

Normalizes a product into generation-ready facts — from an e-commerce URL (a clean description plus curated product images) or from a photo alone (category, how it's used, its moving/opening parts, and key visual details). Use when a product URL or photo needs turning into inputs for image/video generation, or when another skill needs product facts before generating.

MediaClaude Code
#3882

Generating Ad Videos

Makes a product ad video — a product showcase with no one on screen, or a story or lifestyle commercial where a presenter or actor plays a role in the brand's spot, with or without a voiceover. Use when the user wants a product ad, commercial, TV ad, brand film, or product-hero video. Not for a creator or customer sharing their own take on a product, like a review, unboxing, try-on or testimonial — that is generating-ugc-videos; not for a video with no product being sold — that is generating-videos.

MediaClaude Code
#3883

Generating Ai Actors

Generates one photorealistic person as a single image — an AI actor, influencer, presenter or model. The image is reusable, so passing it into any later generation brings the same face, hair and build back and one person can hold across a whole set of images or videos. Use when the user wants an AI actor, or when something needs a person and no photo of one was supplied.

MediaClaude Code
#3884

Generating Audio

ALWAYS read this skill before generating spoken audio or calling audio_generate — a voiceover, narration, an ad read, a character line, or any script read aloud. Turns a script into speech — picks the model and voice, prepares the text for reading, and splits a long script into clips. Use whenever the user asks for text-to-speech, a voiceover, narration, or to have something read or spoken aloud.

CommunicationClaude Code
#3885

Generating Cartoon Videos

Generates a cartoon video for a product — a drawn, animated, anime, illustrated or painted spot that holds one art style and the same characters across every cut. A cartoon character presents, uses or sells the product, and the product itself is either kept exactly as photographed or drawn into the style. Use when the user wants a cartoon, animated, anime, illustrated or hand-drawn video, an animated ad, explainer or mascot spot, or any video whose look is drawn rather than filmed. Not for a photorealistic ad or a live actor or for animating a supplied photo.

MediaClaude Code
#3886

Generating Image Ads

Turns a product photo or URL into a static image ad — one image, or a set. Reads the real product first and holds it identical across every frame and ratio. Triggers: "image ad", "make an ad", "static ad", "promo graphic", "offer graphic", "sale creative", "social ad", "banner ad", "ad creative", "before/after ad", "testimonial ad". Not for generating product photography.

MediaClaude Code
#3887

Generating Images

ALWAYS read this skill before generating or editing any image, or calling image_generate — text-to-image or image-to-image, simple or complex. Turns a text brief, optionally guided by reference images (a character, a style to follow, an existing photo to edit), into a still image. Analyzes intent, routes to the best model, and structures the prompt. Use whenever the user asks to generate, create, make, design, or edit an image — except commercial photography of a product being sold, which belongs to generating-product-photos.

CommunicationClaude Code
#3888

Generating Product Photos

ALWAYS read this skill before generating a product photography — before writing any prompt or calling image_generate. Turns a product photo or URL into commercial photography - packshots, lifestyle and campaign frames, on-model, macro detail, flat lays, seasonal staging, infographics, concepts and floating shots. Reads the real product first and holds it identical across every frame. Triggers: "product photo", "packshot", "shoot my product", "studio shot", "lifestyle shot", "hero image", "on a model", "flat lay", "product infographic", "floating product".

CommunicationClaude Code
#3889

Generating Storyboards

Generates the storyboard sheets for a video — one image per clip, panels in a row, each panel one action. Divides each clip into panels itself, then builds the sheets one at a time, each taking the previous one as a reference, so the person and product stay consistent except where the story deliberately changes them. Use when a video's clip lengths and story are settled and it needs sheets before anything is animated. Not for a still image on its own — that should be made using generating-images.

MediaClaude Code
#3890

Generating Ugc Videos

Generates a UGC video — a creator or customer, on camera as themselves, sharing their own authentic take on a product. Use when the user wants a UGC video, creator video, influencer ad or endorsement, tiktok-style review, unboxing, try-on, OOTD, fit check, haul, tutorial, talking head, or creator testimonial. Not for a produced advertisement in the brand's voice, where a presenter or actor plays a role in the brand's spot — that is generating-ad-videos; not for a video with no person in it, or a person with no product to show.

MediaClaude Code
#3891

Generating Videos

ALWAYS read this skill before generating or animating any video, or calling video_generate — text-to-video, image-to-video, a start→end transition, or a reference / motion / audio-guided clip. Generates a video from a brief — one clip, or several clips joined into a single file at any length. Use when the user wants to make or generate a video, animate a photo, bring an image to life, produce b-roll, film a described scene, or move from one held frame to another. This skill should also be used when the video takes its motion or style from an existing video, or has to run to an existing audio track.

CommunicationClaude Code
#3892

Writing Ad Copy

Writes the words of an ad — the headline, primary text, description and call to action that go into the ad platform's own fields, shaped to the channel it runs on. Handles one channel or several, returning copy sized to each platform's limits. Nothing is generated here — text only. Use when the user wants ad copy, ad text, headlines, primary text, a description or captions written for a paid ad.

CommunicationClaude Code
#3893

Writing Video Prompts

Writes the motion prompt for a video clip — what moves, how the camera behaves, the physics and the audio, in the shape the chosen model wants. Works from a brief alone, from a start frame, from a source video, or from a storyboard sheet where each panel becomes a cut. Handles one clip or a whole set, returning one prompt per clip. Nothing is generated here. Use when a clip's model, duration and content are settled and it needs the prompt written.

MediaClaude Code
#3894

Writing Video Scripts

Writes what is said in a video — the words a person speaks on camera, or a voiceover heard over the picture. Fits the writing to the time available, so lines are never rushed to fit or padded to fill. A video longer than a single clip gets its script split into one piece per clip, each sized to that clip's seconds. Outputs the words as text only — nothing is recorded or voiced here. Use when the user wants a script, dialogue, or a voiceover written for a video.

MediaClaude Code
#3908

Creating Dsh Plugins

Use when building, extending, or fixing tools/plugins for DeepSeek Harness (dsh) — writing a dsh plugin entry module, registering a tool with defineTool, authoring parameters/output JSON Schemas, the dsh bundle manifest, or cordis.patch.yml, or when a plugin fails to load, a tool is missing from the agent, or tool calls error at runtime.

CommunicationDeepSeek Harness