Trendende Agent Skills

Official GSAP skill for React, covering useGSAP hook, refs, gsap.context(), and cleanup for animations in React or Next.js.

Look up conventions, patterns, and concrete implementations from your own GitHub repositories checked out locally under ~/projects/referenzen/.

Create or update a product marketing context document capturing positioning, audience, and product info for other marketing skills to reference.

Make durable artifacts portable by replacing incidental stack, vendor, model, CLI, path, quota, or harness nouns with the mechanism they mean, while keeping provenance, runbooks, and tool-subject claims concrete.

Official GSAP skill for gsap.utils — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pipe, and more.

Check a specific piece of affiliate or influencer content (caption, video script, transcript, screenshot, or live URL) against disclosure regulations and return a pass/fail compliance review with placement, wording, and per-format fixes.

Add, fix, or optimize schema markup and structured data on your site to enhance Google search results.

Audit an affiliate or partner commission payout run for accuracy before money is disbursed - per-line rate and tier recomputation, double-counted conversions, clawback and validation windows, period cutoff, currency, rounding, and tax-form status, delivered as an audit report with severities and recommended holds.

Design the commission and payout structure of a commission-based affiliate program: rate model (revenue share, flat CPA, hybrid), rate level derived from unit economics, payout tiers, recurring duration and caps, attribution/cookie window, validation, clawback, and payment terms.

Use this skill to handle PDF files, including reading, extracting, merging, splitting, rotating, watermarking, creating, form filling, encrypting/decrypting, image extraction, and OCR on scanned PDFs.

A skill for creating, editing, and analyzing .pptx and .potx presentation files.

Carve guardrail-adjacent items out of scope with safe alternatives before risk-adjacent work starts, then run the safe remainder at full strength in a fresh subagent that only ever sees the carved prompt.

Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA.

Define the metric set and layout for an affiliate performance dashboard, delivered as a dashboard specification document - metric definitions with explicit formulas, views per audience, refresh and review cadence, and alert thresholds for top affiliates, conversion by source, and program ROI.

Use when deduplicating bounded collections.

Rewrite a finished commit's message into a clean, handoff-ready form so git log alone tells the story.

Build the detection rule set an affiliate program manager uses to flag fraudulent affiliate activity, plus the investigation and escalation path behind it - cookie stuffing, fake lead and form-fill fraud, self-referral rings, traffic-quality baselines, commission holds and clawbacks, and separating real fraud from legitimate low-incrementality coupon or cashback partners.

Draft the terms and conditions an affiliate accepts when joining a commission-based program - the affiliate program agreement, with the canonical clause set, prohibited-tactics clauses and enforcement ladder, commission validation, clawback and termination mechanics, and jurisdiction overlays (FTC endorsement rules, EU P2B, UK ASA/CAP, GDPR roles).

Use when instructions mix outcomes with recipes.

Rank named candidate strategic alliances and technology partnerships by expected value, effort, and risk, to decide where partner-team capacity goes - must-pass screens, a weighted alliance scorecard with sensitivity analysis, co-innovation and platform-dependency risk checks, a ranked shortlist, and a go/no-go recommendation memo.

Turn a finished, failed, or disappointing work cycle into portable lessons, anti-patterns, quality gates, and next-cycle vocabulary.

Use when a claim depends on an agent taking a real action.

Design the onboarding sequence that carries a newly approved affiliate from approval to first tracked conversion - touch plan (timing, channel, one action per touch), asset kit, time-boxed activation nudge, and never-activated follow-up branch.

Use when packaging source input for a standing goal.

Restart a project or artifact from v0 while preserving only proven lessons, contracts, gates, vocabulary, real-surface tests, and negative corpus.

Draft the outreach copy and sequence plan used to recruit new affiliates into a commission-based affiliate program - prospect qualification and tiering, pitch angle, first-touch recruitment email, follow-up sequence with a breakup touch, channel mix, and outreach tracking.

Use when replying.

Open a paperthin iteration's casebook before re0-loop's first turn, seeding it with real content the moment the folder exists so it is never empty.

Provides foundational Firebase CLI setup, login, project creation and switching, and app config file downloads.

Use when simplifying a skill without losing behavior.

Audits Firebase security rules for vulnerabilities, privilege escalation, role bypasses, and more, providing a score and recommendations.

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing.

Use when a vague idea, stray thought, remembered fragment, or uncertain direction needs to become a concrete outcome, tested design, decision record, artifact, or executable handoff.

Sequence the training, content, and certification a B2B partner program needs to make partners self-sufficient sellers - the partner enablement roadmap, not the training content itself.

re0-loop runs repeated build -> QA -> re0-memo -> re0-work cycles while preserving learning and letting code die, for long agentic projects.

Use when one exact callable tool and a user-authored behavior configuration must become a tool-specific Agent Skill, or when that behavior must be integrated into one exact existing Agent Skill.

Decide which partner categories to add next to a partner ecosystem and in what sequence - a staged partner-category expansion roadmap with readiness gates, capacity limits, and kill criteria.

Walk a pending change through this repo's shipping and releasing checklist end to end, then tag and publish once confirmed.

Use when a request prescribes a method, tool, metric, or artifact that may not reach the result the user described, or when doing the request as written would leave that result unproved: "A/B test the signup button color" for a conversion problem, "add a cache" for a slow page, "the focused tests passed, announce the release".

Design or redesign the tier structure inside an existing B2B partner program - qualification criteria, benefit bundles, tier count, promotion and demotion rules, review cadence for registered/silver/gold-style ladders, and migration of the current partner base.

Sets up, manages, queries, and configures Cloud Firestore databases (Standard/Enterprise edition), including data modeling, security rules, indexes, and SDK integrations.

Use when rewriting rules without meaning loss.

Refactor selected code while preserving behavior, then verify.

Discover what customers truly think, feel, say, and struggle with by analyzing existing assets, mining online communities, and running interviews and surveys.

Use when a workflow, recipe, or capability needs to be packaged as an agent skill, or when an existing skill needs scaffolding, validation, linting, or evals.

Draft a Next.js and shadcn v0.dev prompt from the current file and wait for OPEN, EDIT, or CANCEL.

Model the unit economics of one partner relationship - partner P&L, margin modeling, cost-to-serve, referral-fee and lifetime-value split, channel partner ROI, partner CAC vs direct CAC, ramp and payback - to decide whether to sign, scale, renegotiate, or exit that partner.

Use when the user asks to enhance, improve, refine, rewrite, strengthen, or validate a prompt, or says "make this prompt better".