affiliatemcp

Use this skill to render affiliate-mcp's branded, screenshot-ready social cards (1080x1080) for the weekly launch and other marketing, from the repo design system. It produces card assets for review; the numbers on a card must be real anonymised data or clearly a demo, never invented client data presented as real. Trigger on: "make the weekly card", "render the earnings card", "build a social card", "design the launch artifact".

Use this skill to run affiliate-mcp's day-to-day company operations on a schedule in prepare-and-approve mode: gather everything waiting for the operator's approval (across GitHub, Buffer, and Gmail), collect new inbound feedback and headline metrics, and assemble one daily brief. It prepares drafts and surfaces decisions; it never sends, posts, or merges anything itself. Trigger on: "run the daily company brief", "what needs my approval today", "run company ops", "prepare today's operations brief", "daily ops run".

Use this skill to triage inbound customer and user feedback for affiliate-mcp in prepare-and-approve mode: read new and updated GitHub issues and the support inbox, draft grounded replies from the repo's own docs, propose triage labels, and escalate anything ambiguous, tense, or money-related to the operator. It drafts replies and proposes labels; it never posts a public comment or sends an email itself. Trigger on: "triage the support queue", "draft replies to new issues", "any new user feedback?", "handle customer service", "what did users report today?".

Use this skill to prepare affiliate-mcp's find-users marketing in prepare-and-approve mode: the weekly branded LinkedIn card and post, directory and registry listing submissions, and free lead-magnet content. It applies the voice and ship-checks and queues everything as Buffer drafts; it never publishes or queues a live post. Trigger on: "prepare this week's launch post", "draft the marketing", "queue the weekly card", "prepare directory listings", "run the marketing loop".

Use this skill to prepare onboarding and lifecycle email for new and dormant hosted sign-ups in prepare-and-approve mode: a guided first-value message for a fresh sign-up, an activation nudge for someone who connected but has not run a report, and a re-engagement draft for a dormant account. It prepares Gmail drafts only; it never sends. Distinct from the agency `client-onboarding` skill, which records a client's advisory strategy. Trigger on: "prepare onboarding emails", "draft activation nudges", "welcome new sign-ups", "re-engage dormant hosted users", "run the onboarding loop".

Use this skill when an agency operator wants the Monday weekly note produced for every client in the book in one pass, each in the client's own recorded voice and escalation thresholds, rather than one brand at a time. This is the premium batch extension of the free `programme-performance-report` skill's weekly-client-note output profile, not a replacement for it. Trigger on: "Give me this week's client notes for the whole book", "Run the Monday reports for every client", "Batch the weekly notes for all clients", "Send-ready weekly notes for the book".

Use this skill when an agency operator wants more than this week's headline across the book: a multi-period trend per client, each client benchmarked against the book's own average, and which single publisher shows up across multiple clients so a concentration risk in one partner is visible book-wide. This is the premium extension of the free `agency-portfolio-rollup` skill, not a replacement for it. Trigger on: "How has the whole book trended over the last few months?", "Which clients are underperforming the book average?", "Is any one publisher overexposed across our clients?", "Give me a benchmarked view of the book, not just this week".

Use this skill when an agency operator needs a presentation-ready Quarterly Business Review for a client brand: an executive-summary narrative, a multi-quarter trend (not just this quarter vs last), and a check of whether last quarter's recommended actions actually happened. This is the premium extension of the free `programme-performance-report` skill's QBR output profile, not a replacement for it. Trigger on: "Build the full QBR deck for Acme", "Prepare Acme's QBR with a trend and last quarter's action follow-up", "Get me presentation-ready for the Acme quarterly review", "Did we deliver on what we said last QBR for Acme?".

Use this skill when a publisher wants a multi-period earnings trend across their configured networks, how concentrated their earnings are in one or two programmes, and how long money typically takes to move from converted to approved to paid so they can forecast the next payout. This is the premium extension of the free `affiliate-earnings-report` skill, not a replacement for it. Trigger on: "Show my earnings trend over the last six months", "How concentrated is my income in one programme?", "How long does [network] usually take to pay me?", "Forecast when my pending commissions will land".

Use this skill when a publisher wants to understand why their own commissions are being reversed or declined across configured networks: which programmes and reasons account for the losses, whether the rate is worsening, and a factual evidence pack they can raise with a network's publisher support. No free skill covers this on the publisher side today. Trigger on: "Why are my commissions being reversed?", "Investigate my declines this quarter", "Build me a case to raise with [network] about reversals", "Which programme is costing me the most in reversed commission?".

Use this skill when a publisher wants a running, escalating chase across every configured network: aging tiers instead of a single email, a reconciliation check between the summary total and the transaction-level detail, and an escalation letter for a chase that already went unanswered. This is the premium extension of the free `chase-unpaid-commissions` skill, not a replacement for it. Trigger on: "Escalate the chase on my unpaid commissions", "I sent a chase two weeks ago and heard nothing, escalate it", "Reconcile my unpaid summary against the actual transactions", "Give me an aging breakdown of what's unpaid across networks".

Use this skill when the user asks how much they have earned across their configured affiliate networks, or wants a consolidated period summary. Trigger on: "show my affiliate earnings", "what did I earn last month?", "earnings report", "how much have I made?".

Use this skill when the user wants to verify that the affiliate links on their site, in a draft, or in a sitemap are still pointing at active programmes. Trigger on: "audit my affiliate links", "check my links still work", "find broken affiliate links", "verify my links track properly".

Use this skill when a publisher wants to chase commissions that a network has validated (approved) but not yet paid, typically those sitting unpaid past a payment-term threshold such as 90 days. The skill pulls the matching transactions, groups them, and drafts a chase email with the unpaid sales attached. Trigger on: "chase my unpaid commissions", "which approved sales haven't been paid?", "draft a chase email for unpaid payments", "I've been validated but not paid in 90 days".

Use this skill when an agency operator asks for a performance report for a single brand across one or more advertiser-side affiliate networks: per-publisher rollup, status split, and period-over-period delta. This is also the one reporting workflow behind the cadence deliverables an account manager ships: the daily snapshot, the weekly client note, the month-close report, and the quarterly business review (QBR). Match the output profile to the cadence the user asks for. Trigger on: "How is Acme performing this quarter?", "Show me the programme report for [brand]", "[brand] performance last month", "Which publishers are driving Acme's revenue?", "Acme's weekly report", "How did Acme do this week?", "Acme's month-end report", "Prepare Acme's QBR", "Build the Q2 review for [brand]".

Premium pack. A deep cross-brand, cross-network portfolio analysis for an agency: revenue concentration, partner overlap across brands, reversal outliers, and the brands most exposed to a single partner or network. Goes beyond the free headline rollup. Trigger on: "deep dive the whole portfolio", "where is our agency revenue concentrated", "which brands are over-reliant on one partner".

Premium pack. Use this to prepare a full quarterly business review for a brand across its affiliate networks: quarter-over-quarter performance, top and declining partners, reversal and pending exposure, and a narrative with recommended actions. Trigger on: "prep the QBR for Acme", "quarterly business review for this brand", "build the Q3 review deck notes".

Premium pack. Benchmark one brand's affiliate programme against the other brands you manage in the same vertical: commission competitiveness, partner mix, reversal rate, and AOV, with a gap list the account manager can act on. Trigger on: "benchmark Acme against its vertical", "how does this brand compare to peers we manage", "is our commission competitive for this category".

Use this skill when an agency operator wants a single headline view of revenue across every brand and every network in their book — the agency's home dashboard. Trigger on: "How is the whole book doing this week?", "Show me revenue across all clients", "Portfolio summary", "Which brands are trending down this month?".

Use this skill to spot week-over-week anomalies across an agency's portfolio of brands and networks — revenue drops, reversal spikes, dead links, publishers that fell out of the top 10. Designed to run on a schedule via Claude's own scheduling so the agency learns about problems before clients do. Trigger on: "Are there any problems with the affiliate programmes this week?", "Anomaly check", "Anything weird in the affiliate data?".

Use this skill when a publisher or agency wants to actually apply to a batch of Awin brand programmes they have not yet joined. The joinable set is read from the Awin API; applying is a click Awin exposes no API for, so it is carried out in the operator's own authenticated Awin session through Claude-in-Chrome. For every programme the skill surfaces the advertiser's terms for review, lets the operator drop rows, and submits only after one explicit batch confirmation that stands as informed acceptance of the terms shown. Trigger on: "apply to these Awin brands", "join these Awin programmes for me", "submit my Awin applications", "apply to my Awin shortlist", "join [brand] on Awin".

Use this skill when a publisher or agency wants to find brands on Awin they have not yet joined and decide which ones to apply to next, ranked by fit. Discovery only: it reads the joinable programmes from the Awin API and produces a prioritised shortlist with reasons. It does not apply to anything. Trigger on: "Which brands should I apply to on Awin?", "Find new programmes to join", "Build my Awin application shortlist", "What programmes can I still join?", "Prioritise brands to apply for".

Steward affiliate-mcp implementation, documentation, and pull-request delivery end to end. Use when asked to implement or plan a repo change, advance work from an issue or user outcome, manage multiple PRs, repair or refresh branches, monitor CI, address review findings, prepare merges, or accelerate delivery while keeping product and architecture decisions with the appropriate human.

Prepare, open, update, or request review for an affiliate-mcp pull request. Use when asked to create a PR, make a PR review-ready, update a PR body, request maintainer review, or check whether a branch is ready for review.

Review an affiliate-mcp pull request for correctness, architecture, tests, product and customer-journey clarity, documentation, and merge readiness. Use when asked to review, re-review, supervise, or unblock a PR.

Use this skill when an agency operator wants the list of partner applications waiting on a decision for a brand: who has applied to the programme and is sitting in the pending queue. The output is a read-only queue; the approve or decline happens in the network dashboard. How the queue is read depends on the network. Some advertiser networks expose application status through the API. Awin does not: its advertiser API returns only joined publishers with no application status, so Awin's pending queue is read from the operator's own authenticated Awin session (new UI, app.awin.com) through Claude-in-Chrome, read-only. Awin Classic (ui.awin.com) accounts have no equivalent and are detected and stopped. Trigger on: "Which partner applications are pending on Acme?", "Acme's application queue", "Who's waiting for approval on [brand]?", "Show me pending partners for Acme".

Use this skill when an agency operator wants the partner roster for a brand split by relationship status, plus the active partners who have gone quiet so they can be chased or reactivated. The output is a read-only worklist; the outreach itself happens outside this skill. How a partner's relationship status is read depends on the network. Some advertiser networks report it through the API. Awin does not: its advertiser API returns only already-joined publishers with no relationship-status field, so every Awin row maps to unknown and neither the roster split nor the dormant worklist can be derived from the API. Awin's roster and per-partner relationship status are read from the operator's own authenticated Awin session (new UI, app.awin.com) through Claude-in-Chrome, read-only. Awin Classic (ui.awin.com) accounts have no equivalent and are detected and stopped. Trigger on: "Who's gone quiet on Acme?", "Acme's partner roster health", "Which partners have gone dormant on [brand]?", "Build a reactivation list for

Use this skill when an agency operator wants to work through a brand's pending Awin publisher applications and approve or decline them in one assisted batch. The pending queue is read from the Awin API; the approve or decline click is carried out in the operator's own authenticated Awin session through Claude-in-Chrome, because Awin exposes no public approve/decline endpoint. Decisions follow the brand's recorded strategy only, and the whole batch runs against a single explicit human confirmation. Trigger on: "approve pending Awin publishers for Acme", "work through Acme's Awin application queue", "auto-approve Awin applicants for [brand]", "clear the Awin pending publishers for Acme".

Use this skill when an agency operator wants to draft outreach to partners for a brand: a re-engagement message to a partner who has gone quiet, or a recruitment sequence to a prospective partner. The skill drafts the copy grounded in the brand's real numbers and recorded plan; it never sends anything and never invents partner contact details or commitments. Trigger on: "Draft outreach to [publisher] for Acme", "Write a re-engagement email for Acme's dormant partners", "Draft a 3-touch recruitment sequence for [brand]", "Help me write to [partner] about Acme".

Use this skill for a one-off diagnostic across every available data operation for a brand, typically at account handover or kick-off: is the connection healthy, what can we actually read, is data flowing, and where are the gaps. It is the "audit the account before we start" pass, not a recurring report. Trigger on: "Audit Acme's programme", "Health-check the Acme account", "Run a full check on [brand]", "We just won Acme, what can we see?", "Is the Acme connection working end to end?".

Use this skill when an operator wants to record, review, or change a client's affiliate strategy and KPI targets so reports can be judged against the client's own plan. Capture is conversational: the operator pastes an existing brief, deck, or email, or just describes the client in their own words, and this skill drafts the strategy and KPI files, reads them back in plain English, and saves them only after the operator confirms. Thereafter it edits them through chat. Trigger on: "set up a strategy for Acme", "record Acme's KPIs", "onboard a new client", "what are we aiming for with Acme?", "raise Acme's Q3 revenue target to 400k", "Acme prefers premium partners, no coupon sites", "save this client brief".

Use this skill when the user is trying to set up a specific affiliate network and needs help finding credentials, navigating the dashboard, or understanding the setup steps. Trigger on: "help me set up Awin", "how do I get a CJ API token", "setup help", "I'm stuck on Impact setup".

Use this skill when an agency operator wants to understand why a brand's commissions are being declined: the reversed transactions over a period, grouped by reason and by publisher, with the value at stake and how the reversal rate is trending. Trigger on: "Why are Acme's commissions being declined?", "Acme's reversals this month", "What's getting rejected on [brand]?", "Show me the decline report for [brand]".

Use this skill when an agency operator wants a deep dive on one publisher for a brand, usually as prep for a partner call: that publisher's clicks, conversions, EPC, average order value, commission, status split, and trend over time, with talking points for the conversation. Trigger on: "Review CashbackCo for Acme", "Prep me for the call with [publisher]", "How is [publisher] performing on [brand]?", "Pull a publisher review for [partner]".

Use this skill when the user wants to contribute to the affiliate-mcp project — adding a new affiliate network adapter, fixing a broken network adapter, adding a new Claude Code skill, or improving the documentation. Trigger on: "add [network] to affiliate-mcp", "contribute a network", "fix the [network] adapter", "the [network] adapter is broken", "add a skill to affiliate-mcp", "improve the docs for [network]".

Use this skill when the user wants a health check of their configured affiliate networks — auth, reachability, supported operations. Trigger on: "is my affiliate setup working", "check my affiliate networks", "are all my networks responding", "network health".