skills-agents-co
OrganizationClaude Code plugin marketplace and skill library. Install: /plugin marketplace add Anlo-Ventures/skills-and-agents-library
Categories
Indexed Skills (49)
discovery-call-prep
Turns a stated hypothesis and what you know about a person into a discovery-call question guide where every question asks about something that already happened. Grounded in two books, not paraphrased from either, The Mom Test's rule that a real interview asks about past behavior, never a hypothetical, and Transformed's four product risks (value, usability, feasibility, business viability), which decide what each question is actually testing. Tags every question with the risk it tests, names any hypothesis an interview cannot answer, and ends with an ask that costs the person something real. Use whenever the user says "prep me for a discovery call", "write a discovery guide", "build interview questions for this hypothesis", "/discovery-call-prep", or pastes a hypothesis plus notes on who they're about to talk to.
discovery-to-prd
Reads a set of discovery call transcripts and writes a PRD draft where every problem statement names the call it came from and quotes the line behind it. Tags findings with one of four product risks from Transformed (value, usability, feasibility, business viability), marks a template section unsupported rather than inventing a plausible sentence when no transcript covers it, and never states a product or market figure the transcripts don't contain. Use whenever the user says "turn these calls into a PRD", "write a PRD from these transcripts", "synthesize these discovery calls", "/discovery-to-prd", or pastes a set of discovery call transcripts and asks for a PRD draft.
drip-api
Research Drip's premium financial newsletters and podcasts by searching topics, browsing sources, resolving named publications, newsletters, authors, podcast shows, Substack URLs, and direct article links, listing recent posts, presenting purchasable article options, fetching paid article summaries, and synthesizing or comparing selected paid articles. Also supports fetching structured stock picks for a given UTC day when users ask for stock recommendations, ticker-level long/short ideas, or analyst calls. Use for questions about finance commentary, analyst views, market themes, company or sector writeups, podcast/newsletter source discovery, stock picks, and paid Drip content. Paid post and stock-picks routes are gated by x402/MPP micropayments.
data-set-analysis
Reads an attached data file and a stated data type, then writes a four-part report, summary of key content, patterns and trends, insights grouped by priority, and recommendations, with the metrics it focuses on shifting to match the data type. Every insight names why it's high, medium, or low priority, and every recommendation names the insight it follows from. Use whenever the user attaches a data file and asks for analysis, insights, or a summary, or says "analyze this data", "analyze the attached file", "what patterns are in this", "give me insights on this data set", or "/data-set-analysis".
sales-email-template-generator
Writes one personalized sales outreach email, 200 words or fewer, from a stated prospect type, their current solution, and your product or features. Names a plausible pain point, a specific feature that addresses it, a clear value proposition, and closes with a soft demo invitation instead of a hard close. Use whenever the user says "write a sales email", "draft an outreach email", "sales email for [prospect type]", "cold email template", "/sales-email-template-generator", or names a type of prospect and what they currently use and asks for an email to send them.
backlog-prioritization-strategy
Reads a backlog and a written strategy document, and returns the backlog ranked against that strategy, with each ranked item citing the exact strategy passage that justifies its position. Items the strategy document doesn't cover get flagged as unscored rather than ranked or given an invented framework score. Use whenever the user says "rank this backlog against our strategy", "prioritize this backlog", "which of these should we build first", "/backlog-prioritization-strategy", or pastes a backlog alongside a strategy doc and asks what to build first.
ads-copilot
Chat with your ad-platform and analytics data and get specific, ranked optimization recommendations. Discovers whatever sources are reachable in the session (connected MCP servers for Google Ads, Meta, TikTok, LinkedIn, GA4, Stripe, or CSV exports the user pastes/uploads), answers plain-language questions about ad performance first, then surfaces 3 to 5 ranked moves with expected effect and the assumption behind each one. Use this skill whenever the user says "ads copilot", "how are my ads doing", "review my ad spend", "what should I do about my Meta ads", "optimize my ads", "audit my ads", or "why isn't growth working" (even without the word "ads"). This is a veneer layer, not an attribution platform — it never builds tracking pixels, identity resolution, or multi-touch attribution, and it treats platform-reported conversions as self-reported.
board-deck
Turns a period's financials into the finance section of a board deck. It takes a P&L export, plus optional prior-period and plan figures, and drafts structured text: headline metrics, period-over-period movement, the narrative behind each move, and an always-present list of what it could not figure out from the input. Hand it a past board deck and it matches that deck's format, swapping in this period's numbers and commentary. It never invents a figure and never guesses at a cause it cannot trace back to the input. Text only, no slides, charts, or images.
financial-pulse
Analyzes bank transaction data to produce a categorized 30-day spending breakdown and surfaces 3 specific things to look into based on 60-day trends. This skill is the analysis engine — it does NOT connect to any bank directly. It expects transaction data to be available in the session via a bank connector agent (e.g., Grasshopper MCP, Mercury MCP) or pasted/uploaded by the user. Use this skill whenever the user says "financial pulse", "check my spending", "money check-in", "where's my money going", "spending review", "run the pulse", "how am I doing financially", "spending trends", "what should I look into", "money audit", or any variation implying they want an actionable view of their financial health. Also use when transaction data is already in context (CSV upload, bank MCP connected) and the user asks for analysis. Always use this skill for spending analysis — do not freehand financial breakdowns without it.
ghost-seo-agent
Autonomously audits, fixes, and re-submits Ghost posts for Google indexing. Works for any Ghost publisher. Uses browser access to log into Google Search Console, pull non-indexed URLs, diagnose each page, apply fixes via Ghost MCP, and request re-crawl — all without manually exporting CSVs or clicking through Search Console. Also detects Ghost-specific structural issues (tag/author archives, paginated pages, sitemaps, AMP duplicates, HTTPS config, members-only content, sparse tags, non-WebP images) and content quality problems (thin posts, isolated posts with no internal links). Includes a migration audit mode for publishers moving from Substack or WordPress. Use this skill whenever a Ghost publisher says "run SEO audit", "fix indexing issues", "check what's not indexed", "why aren't my posts showing up in Google", "fix Ghost SEO", or any similar phrase about search visibility, indexing, or organic traffic on a Ghost site. Always use this skill for Ghost SEO work — do not attempt to diagnose or fix indexing i
investor-update
Drafts a founder's periodic update to investors and LPs for review, then hands it back to the founder to send. This skill is the drafting engine, it does NOT connect to any source or send anything. It pulls the period's raw material from whatever is reachable in the session (a Slack MCP on the founder's updates, metrics, and team channels; a Gmail/Google Workspace MCP for customer-win, hire, partnership, and fundraise threads; an analytics or billing MCP like Stripe or Amplitude for numbers) or from material the founder pastes, and produces a complete email draft in the Elad Gil long or short format. Built for founders sending monthly or quarterly updates to investors and LPs. Use whenever the founder says "draft my investor update", "investor update", "write my monthly update to investors", "LP update", "write my investor email", "monthly investor email", "update to our investors", or "/investor-update".
office-tells
Mandatory anti-AI quality gate for every PowerPoint (.pptx), Word (.docx), and Excel (.xlsx) file Claude creates or edits. Strips the visual, structural, and metadata tells that mark a document as machine-generated: pipe separators, em dashes, accent lines under slide titles, beige/default-blue/default-grey color choices, zebra table banding, excessive conditional formatting, Sheet1 names, library-default file metadata, hardcoded totals, and boilerplate section names. Use this skill BEFORE writing any code or content whenever the user asks to build, create, generate, make, write, edit, update, or produce a deck, slides, presentation, slideshow, pitch deck, PowerPoint, Word doc, document, report, memo, letter, brief, one-pager, template, spreadsheet, Excel file, workbook, financial model, tracker, budget, dashboard, or any .pptx/.docx/.xlsx file. Triggers even when the user does NOT mention "human," "natural," or "anti-AI" wording, the file type alone is the trigger. This is a behavioral overlay on the pptx, d
qbo-bank-reconciliation
Matches bank transactions against the QuickBooks Online register and the petty cash log for a stated period, so cash gets reconciled first in the close instead of last. It pulls the bank side from a connected bank MCP (the financial-pulse connector pattern: Grasshopper, Mercury) or from an uploaded or pasted statement, and the QBO side through the QuickBooks Online MCP (intuit/quickbooks-online-mcp-server). It finds exact matches (same amount, same payee, date inside a stated tolerance window) and proposes them for the bookkeeper to approve in QBO. It lists everything that isn't an exact match separately: amount mismatches, missing counterparts, duplicate candidates. It writes nothing to QBO or to the bank. It's read-only by design. Use it whenever the user says "reconcile the bank", "run bank rec", "match the bank feed", "petty cash reconciliation", "close the books on cash", "what doesn't match in the bank register", "bank and petty cash close", "QBO bank reconciliation", or anything else that means they wa
qbo-closing-package
Tracks where a QuickBooks Online period close stands, and (once every checklist step is clean) pulls the final P&L, balance sheet, cash flow, and a set KPI list for the controller handoff. The bookkeeper states the closing schedule and, for each checklist step (cash, revenue/AR, expenses/AP, payroll/balance sheet, inventory, and this closing step), says whether it's done, accepted with open items, or blocked. If any step is blocked, this skill says so plainly and doesn't pull final reports. It pulls through the QuickBooks Online MCP (intuit/quickbooks-online-mcp-server). It writes nothing to QBO and never sets or changes the closing date. It's read-only by design. Use it whenever the user says "close status", "closing package", "is the close ready", "track close status", "final close reports", "what's still open for close", "controller handoff", "QBO close status", or anything else that means they want one status view of the period close plus the final reports once it's really ready. Always use this skill for
qbo-expenses-ap
Cross-checks what you owe against the receipts and invoices that back it up in QuickBooks Online. It pulls vendor bills, bill payments, and an AP aging report for a stated period through the QuickBooks Online MCP (intuit/quickbooks-online-mcp-server), matches each recorded payable against a list of expense receipts and supplier invoices you paste or upload for the same period, and flags both sides of the gap: every payable with no matching document, and every document with no matching payable. It writes nothing to QBO. It's read-only by design. Use it whenever the user says "reconcile expenses and AP", "run the AP reconciliation", "close the books on payables", "what do we still owe", "AP aging", "match bills to receipts", "expenses and AP for the period", "QBO expense reconciliation", or anything else that means they want every dollar spent to trace back to a receipt or invoice before close. Always use this skill for QBO expenses and AP close work. Don't freehand a reconciliation without it.
qbo-inventory-reconciliation
Checks a physical inventory count against what QuickBooks Online thinks is on the shelf. It takes a per-item quantity list that the bookkeeper pastes or uploads, pulls QBO's inventory asset records for the same period through the QuickBooks Online MCP (intuit/quickbooks-online-mcp-server), and reports the variance item by item instead of as one lump number. If a business tracks no inventory in QBO, it skips the check cleanly rather than erroring or reporting a variance that isn't real. It writes nothing to QBO. It's read-only by design. Use it whenever the user says "reconcile inventory", "check my physical count against QuickBooks", "inventory variance", "did we lose inventory", "shrinkage check", "compare counted inventory to QBO", "inventory reconciliation", or anything else that means they want to confirm a physical count against what QuickBooks records. Always use this skill for QBO inventory reconciliation work. Don't freehand a variance comparison without it.
qbo-payroll-balance-sheet
Checks payroll expense against QuickBooks Online income, and lists what changed period over period on loans, accrued expenses, deferred revenue, and equipment or fixed assets, the balance sheet side of the close that gets skipped first under deadline pressure. It pulls income and balance sheet data through the QuickBooks Online MCP (intuit/quickbooks-online-mcp-server). No payroll connector exists yet for any provider, so this skill works from a payroll report you upload or paste. It writes nothing to QBO or to any payroll provider. It's read-only. Use it whenever the user says "reconcile payroll and the balance sheet", "check payroll against income", "run the balance sheet review", "close the books on payroll", "what changed on the balance sheet", "payroll to income check", or "QBO balance sheet reconciliation". Always use this skill for the QBO payroll and balance sheet close. Don't freehand it.
qbo-revenue-ar
Shows you what a period actually earned and who still owes you money in QuickBooks Online. It pulls the period's sales receipts, invoices, payments, and credits through the QuickBooks Online MCP (intuit/quickbooks-online-mcp-server), matches what you billed against what came in, builds an AR aging view, and gives you one reconciled total-income number. It never writes to QBO. It's read-only by design. Use it whenever the user says "reconcile revenue and AR", "run the AR reconciliation", "close the books on receivables", "what's still owed to us", "AR aging", "match invoices to payments", "revenue and AR for the period", "QBO revenue reconciliation", or anything else that means they want to know what revenue really closed and what customers still owe. Always use this skill for QBO revenue and AR close work. Don't freehand a reconciliation without it.
learn-quiz
Turns Claude into a teacher whose job is to make sure you DEEPLY understand the work before the session ends, instead of rubber-stamping a diff you never read. Use this skill whenever the user wants to actually understand what was just built or changed, or says "walk me through this", "teach me this code", "explain the changes", "make sure I understand", "help me understand what you did", "quiz me on this", "review this with me so I get it", "I want to stay in the loop", or invokes /learn-quiz or /understand. Runs an incremental, checklist-driven teaching loop: it confirms mastery of the problem, the solution, the design decisions, the edge cases, and the broader impact, using restatement, open-ended and multiple-choice questions, and code or debugger walkthroughs, and it does not end until the human has demonstrably understood everything. Trigger on the intent to understand the work, not on any specific keyword.
ap-invoice-processing
Watch an inbox for vendor invoices, extract the key fields, dedupe against the AP log, log them, forward to the AP system, and file the email. Use for daily accounts-payable intake when you want to automate the clerical part and keep a human in the loop before anything gets paid.
buy-side-diligence
Runs systematic buy-side due diligence on a private company acquisition target. Deconstructs financials into normalized earnings, stress-tests the seller's narrative, cross-references documents to surface inconsistencies, quantifies red flags into valuation adjustments, and produces an investment-committee-ready output package. Built for corporate development teams, PE associates, search fund operators, and M&A advisors running buy-side diligence. Use whenever the user says "run diligence", "due diligence", "DD this", "QoE this", "build a red flag matrix", "normalize this EBITDA", "diligence package", "/diligence", or points at a data room, CIM, or financial package and asks what's wrong with it.
card-receipt-forwarding
Forward recurring corporate-card receipts (e.g. Divvy, Ramp, Expensify) to the card/AP system and keep those vendors out of invoice processing to avoid double-counting. Use for known recurring card vendors only; flag anything off-list for review.
ceo-todo
Maintains one canonical markdown file as a CEO's single source of truth for everything they're on the hook for, and runs the Getting Things Done loop over it — capture, clarify, organize, reflect, engage. Turns pasted emails, meeting notes, and asks into clarified next-actions with an owner and a priority, tracks status with a fixed vocabulary ([OPEN]/[DONE]/[STALE]/[WAITING]), ages open items to [STALE] after 7 days, flags [WAITING] items past their reply-by date, archives done work without ever deleting it, and never auto-closes an item the CEO added by hand. Every mutating run is snapshot-backed and gated by a bundled deterministic validator so a commitment is never lost, corrupted, or silently changed. Use this skill whenever the user says "run my to-do", "update my todo doc", "what am I on the hook for", "GTD", "getting things done", "capture this", "triage my inbox into my todos", "weekly review", "single source of truth", "CEO to-do", "/ceo-todo", or points at a markdown to-do file and asks to keep it
equity-reconciliation-carta
Live equity reconciliation powered by the Carta MCP server. Pulls cap-table data directly from Carta, compares it against your HRIS export, and surfaces termination-date mismatches, active grants for terminated employees, lapsed exercise windows, and missing source documents. Use periodically and before any capital raise or audit.
equity-reconciliation
Reconcile equity records against the HRIS to catch termination-date mismatches and active grants for terminated employees. Use periodically and before any capital raise or audit.
expense-access-audit
Generate the onboarding or offboarding checklist for the expense/card tool, and audit it against the HRIS to catch terminated people with active cards or missing approvers. Use on a new hire, a termination, or a periodic access review.
expense-policy-check
Review expense reports against policy, flag violations and missing receipts, and draft the monthly missing-receipt chase. Use on an expense report or export, or at month-end. Every flag cites the policy rule it breaks; ambiguous items are flagged to confirm, never auto-approved or auto-rejected. The chase is a draft a person sends.
financial-model-qa
Scan a financial model for formula errors and logic defects, and check scenario outputs after input changes. Cites the exact sheet and cell for every issue and never edits the model. Use before sharing or relying on a model.
gl-to-report
Turn a raw accounting/GL export into a clean reporting template (flash report) and draft variance commentary against prior actuals and budget. Use for the monthly close and the recurring flash report.
invoice-generation
Draft a customer invoice from billing inputs -- customer, line items, terms -- with every amount cited to an input and nothing invented. Use to generate the invoice you send to a customer for work done or goods delivered, not to process invoices you receive.
llm-visibility-agent
Reads a brand's weekly AI Visibility report from the Amplitude or PostHog AI Visibility MCP, diagnoses where competitors show up in LLM answers but the brand does not, and recommends specific posts to close the gaps. Use whenever the user says "check AI visibility", "how is my brand showing up in LLMs", "run the LLM visibility report", "what AI prompts is my brand missing from", "AI search visibility brief", "am I showing up in AI search", "LLM visibility audit", "what should I write to rank in ChatGPT", "why is my brand not in AI answers", or "/llm-visibility". Pure read and synthesize layer on top of the existing weekly AI Visibility runs. Does not crawl LLMs, does not scrape, does not call models directly. Turns the measurement data into editorial action.
local-lead-prospector
Assembles an outreach list of local businesses for an SDR from an industry + region pair. Returns a CSV with name, category, address, phone, website, rating, review count, and a Google Maps source URL, plus a markdown summary. Listing data only. No decision-maker names, no personal emails, no LinkedIn scraping. Google Places API (New) is the preferred path and requires GOOGLE_MAPS_API_KEY. A Playwright + Chromium scrape of public Google Maps results exists as an opt-in fallback, gated behind an explicit confirmation, because scraping Google Maps is against Google's Terms of Service. Use this skill when an SDR asks to "find me dentists in Austin", "build a lead list for HVAC companies in Denver", "I need contacts for law firms in Chicago", "give me a prospecting list", or "who should I cold-call in this market". Do NOT trigger on single-consumer lookups like "find me a good dentist near me", "what is the best taco place in Austin", or "where should I take a client to dinner in SoHo". Those are one-shot recomme
meeting-memo
Turn a meeting transcript into the team's standardized notes format (commentary, observations, action items with owners and dates) and carry forward unresolved items from the last meeting. Use after any recurring meeting. Writes against your frozen template, flags missing owners, invents no decisions.
resume-tailor
Tailors your resume and cover letter to a specific job description with ATS keyword scoring, parser-safe formatting, and submission-ready PDF output.
meeting-scribe
Turn a meeting transcript into structured meeting memory — a dated meeting note, one appended mention line per entity the transcript names (person, organization, or meeting you already track), and a recap email drafted for review but never sent. Matches names against your own entity files first; an unmatched name becomes a proposed new entity instead of a guess, and an ambiguous name lists every candidate and writes nothing. Inspired by USV's Meeting Scribe agent (https://blog.usv.com/meet-the-agents), rebuilt generic for any team that keeps a folder of who and what it tracks. Use whenever the user says "run meeting scribe", "turn this transcript into meeting memory", "log this meeting against my contacts", "who did we mention on this call", "draft a recap from this transcript", "/meeting-scribe", or points at a transcript plus a folder of people/company files.
calendar-agent
Read a calendar export and turn it into a dated prep brief per upcoming meeting — matching every attendee and company against the same tracked entity files meeting-scribe writes to, so you walk into each meeting already knowing what's been said about the people and companies on it. Matches names against your own entity files first; an unmatched name is reported unmatched, an ambiguous name lists every candidate, and no entity or mention file is ever created or edited. Inspired by USV's Calendar Agent (https://blog.usv.com/meet-the-agents), rebuilt generic for any team that keeps a folder of who and what it tracks. Use whenever the user says "run calendar agent", "prep me for my meetings", "brief me on today's calendar", "who am I meeting with", "check my calendar against my contacts", "/calendar-agent", or points at a calendar export plus a folder of people/company files.
news-monitor
Find current news about the people and companies you track, filtered against your own entity files rather than a generic feed, and write a dated digest of what matters — or a plain "nothing found" line when there's nothing. Reads the same tracked entity folder meeting-scribe writes to and calendar-agent reads. Searches live, scoped to a fixed list of source publications (default TechCrunch, The Information, Ars Technica), or reads a news export you hand it directly. Never writes a mention line, never creates an entity, only writes to its own digests/ folder. Use whenever the user says "run news monitor", "what's new on my tracked companies", "check the news on my contacts", "any news on X", "news check", "/news-monitor", or hands over a saved search export, RSS/Atom export, or forwarded newsletter to filter against their tracked list.
email-sequence
When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle emails." For in-app onboarding, see onboarding-cro.
lead-research-assistant
Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
librarian
Read the meeting notes and mention history already sitting in your tracked entity folder, find the ideas that keep recurring across more than one meeting, and draft a short post for each one, grounded in quotes from the meetings it came from. Reads the same entity folder meeting-scribe writes to and calendar-agent and news-monitor read. Never re-matches names, never writes to people/organizations/meetings, never publishes anything — every draft is a local markdown file the user reviews and posts themselves. Inspired by USV's Librarian agent, rebuilt generic for any team that keeps a folder of who and what it tracks. Use whenever the user says "run librarian", "find recurring themes in my meetings", "what keeps coming up", "draft some posts from my meeting notes", "distill my meetings into content ideas", "/librarian", or points at an entity folder and asks what ideas are worth writing up.
competitor-intel
Researches competitors in real-time — positioning, pricing, recent moves, strengths, and gaps
code-reviewer
Reviews code for bugs, security issues, performance problems, and style — with specific, actionable feedback
document-creator
Turns a short brief into a complete, professionally structured document: reports, proposals, executive memos, project briefs, and status updates, ready to send.
github-pr-summarizer
Reads a GitHub pull request and generates a clear summary of what changed, why, and what reviewers should focus on
research-brief
Turns any topic into a structured research brief: background, key players, what's contested, and a short reading list. Get up to speed fast before a meeting.
email-drafter
Drafts professional emails from a quick brief — the right tone, length, and structure every time
meeting-notes-distiller
Turns raw meeting notes or transcripts into clean summaries with decisions, action items, and owners
meeting-scheduler
Finds the best meeting time across calendars, drafts the invite, and sends it — all in one flow
gws-gmail
Read, search, draft, and manage Gmail email
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.