23 agents · Tech & development
Give it your experimental results and get back a conference-format paper draft, covering experiment design, ablations, related work, and references. ## What it does - **Conference-format drafts:** results shaped into a paper in the expected structure - **Experiment & ablation sections:** methodology and ablations written from your data - **Related work:** prior art positioned around your contribution - **References:** citations formatted to the venue ## Where it fits - **A grad student writing up:** "Draft the methods and ablations from these results." Sections ready to edit. - **A researcher prepping a submission:** "Structure this into a conference paper." A formatted draft to refine. - **A team racing a deadline:** "Write the related-work section around these citations." A positioned draft to tighten. ## How it works 1. **Give it your results:** data, settings, and the contribution. 2. **It drafts the paper:** structure, ablations, related work, and references. 3. **You get a draft back:** conference-format sections to edit and submit. Built for graduate students and researchers. Every draft is yours to verify, edit, and stand behind.
Describe a system, a relationship, or a dataset, and get back a clean architecture diagram, flowchart, or ER diagram as SVG or PNG, ready to drop into docs or slides. ## What it does - **Architecture diagrams:** services, data stores, and the connections between them laid out clearly - **Flowcharts & process maps:** a described workflow turned into a readable top-down or left-to-right flow - **ER diagrams:** a schema or table description rendered as entities, keys, and relationships - **Export:** every diagram as SVG or PNG, ready for docs, wikis, or slides ## Where it fits - **An engineer writing a design doc:** "Diagram the request path from the gateway through to the database." A clean architecture figure to paste into the RFC. - **A product manager mapping a flow:** "Turn this onboarding sequence into a flowchart." A shareable diagram for the spec. - **A backend dev documenting a schema:** "Draw the ER diagram for these five tables." Entities and relationships ready for the wiki. ## How it works 1. **Describe it in words:** a system, a process, or a set of tables. 2. **It picks the diagram type:** architecture, flowchart, or ER, with a clean layout. 3. **You get a file back:** SVG or PNG to drop straight into docs or a deck. Built for engineers and product managers visualizing system design. Every diagram is a draft you can refine and re-export.
Give it a topic or an outline and get back a polished HTML slide deck you can present straight from the browser. ## What it does - **Topic to deck:** a subject or outline expanded into a structured, presentable slide set - **Clean front-end design:** typography, spacing, and layout handled, no template wrestling - **Browser-native:** present directly from the browser, no export step - **Editable:** plain HTML you can tweak slide by slide ## Where it fits - **A developer prepping a tech talk:** "Build a 12-slide deck on our API design." A presentable deck to refine before the talk. - **A founder pitching:** "Turn this outline into slides." A clean deck ready for the room. - **A teacher building a lesson:** "Make slides explaining recursion with examples." A structured set to present from the browser. ## How it works 1. **Give it a topic or outline:** a subject or a bullet list. 2. **It builds the deck:** structured slides with consistent design. 3. **You get HTML back:** present from the browser or edit slide by slide. Built for tech talks and product demos. Every deck is a draft you can reorder and restyle.
Give it a website or piece of content and get back an AEO/GEO report that helps your pages surface inside AI search engines like ChatGPT and Perplexity. ## What it does - **AEO/GEO audit:** your content evaluated for AI-engine citation readiness - **Optimization report:** specific edits to make the page more likely to be cited - **AI search check:** likelihood of appearing in ChatGPT, Perplexity, and AI Overviews - **Actionable output:** a prioritized list of changes, not just a score ## Where it fits - **A content lead chasing AI citations:** "Audit this guide for GEO readiness." A report on gaps plus what to change. - **A marketer optimizing key pages:** "How do we show up in AI answers for this topic?" An edit list to act on. - **An SEO adapting to AI:** "Score our top pages for AI search." A coverage report with fixes. ## How it works 1. **Give it a URL or content:** a page, article, or site section. 2. **It runs the audit:** AEO/GEO checks against how AI search engines read and cite content. 3. **You get a report back:** visibility findings plus specific edits to apply. Built for content and SEO teams optimizing for AI search. Every report is a set of recommendations for you to review and apply.
Describe a technical relationship and get back a production-grade diagram as SVG or PNG, in your pick of 7 styles including UML. ## What it does - **Technical diagrams:** components, flows, and relationships rendered at publication quality - **UML support:** class, sequence, and component diagrams from a plain description - **7 visual styles:** pick the look that fits your paper, doc, or deck - **Export:** clean SVG or PNG, sized for figures and slides ## Where it fits - **A researcher preparing a figure:** "Draw the model architecture as a UML component diagram." A paper-ready figure in your chosen style. - **An architect documenting a system:** "Show the service interactions as a sequence diagram." A clean SVG for the design doc. - **A writer polishing a deck:** "Render this flow in a minimal style." A diagram that matches the slide template. ## How it works 1. **Describe the relationship:** components, a sequence, or a class structure. 2. **Pick a style:** one of 7, including UML conventions. 3. **You get a file back:** SVG or PNG, ready for the paper or deck. Built for technical documentation and paper figures. Every diagram is a draft you can restyle and re-export.
Give it your research direction and existing materials and get back first drafts of each paper section, formatted with citations. ## What it does - **Section drafts:** intro, methods, results, and discussion drafted from your materials - **Citation formatting:** references handled in the expected style - **Academic structure:** the conventional shape of a paper applied - **Material-grounded:** built from the notes and sources you provide ## Where it fits - **A grad student facing a blank page:** "Draft the introduction from my notes." A section to edit instead of start. - **A researcher organizing:** "Turn these results into a methods and results section." Structured drafts to refine. - **A writer formatting:** "Format these references and weave them in." Clean citations in place. ## How it works 1. **Give it your direction and materials:** the topic plus notes and sources. 2. **It drafts section by section:** structured academic prose with citations. 3. **You get drafts back:** sections to verify, edit, and assemble. Built for graduate students and researchers. Every draft is yours to fact-check, edit, and stand behind.
Point it at a code repository and get back an interactive online course with exercises. ## What it does - **Repo to curriculum:** a codebase turned into a structured learning path - **Interactive pages:** lessons you click through, not a static README - **Hands-on exercises:** tasks tied to the actual code - **Teaching-ready:** output you can publish or assign ## Where it fits - **An open-source maintainer:** "Turn our repo into an onboarding course." A guided path for new contributors. - **An instructor building material:** "Make a course from this example project." Lessons with exercises. - **A team onboarding engineers:** "Teach our codebase interactively." A walkthrough new hires can do. ## How it works 1. **Point it at a repo:** the codebase to teach. 2. **It builds the course:** lessons and exercises mapped to the code. 3. **You get a course back:** interactive pages to publish or assign. Built for open-source teaching and technical training. Generated material is a draft to review before you teach from it.
Your deal team in a box: 10 specialist analysts for investment banking, equity research, private equity, and fund operations. Hand it a deal, a company, or a portfolio, and get back pitch books, models, research notes, and fund reports as analyst-grade drafts, ready for your review. ## What it does - **Pitch books:** comps, precedents, and an LBO assembled into a branded 15 to 20 slide pitch deck (.pptx), client-ready - **Market & sector research:** sector overview, competitive landscape, peer comps, and a shortlist of ideas in a structured HTML or Word brief - **Earnings analysis:** an earnings call plus the latest filings turned into a model update and a desk-ready research-note draft - **Financial modeling:** DCF, LBO, 3-statement, and comps models as working Excel files with live formulas, not hardcoded numbers - **Meeting prep:** a one-page briefing pack on the company, the people, and the open questions before every client meeting - **Fund valuation review:** GP packages reconciled into a valuation template and an LP-ready reporting pack - **GL reconciliation:** accounting breaks found, root cause traced, each item routed for sign-off - **Month-end close:** accruals, roll-forwards, and variance commentary, close-ready - **KYC screening:** onboarding docs parsed, the rules engine run, and compliance gaps flagged with an audit trail ## Where it fits - **A banker prepping a pitch:** "Build comps and an LBO for [target], then drop them into our pitch template." A branded deck in hours, not days. - **An equity research analyst on earnings day:** "Read [company]'s Q3 call and 10-Q, update the model, and draft the note." Model and note ready to edit before the desk opens. - **A PE associate at quarter-end:** "Reconcile these GP statements into our valuation template and prep the LP report." A valuation review plus an LP-ready package. - **A fund accountant at month-end:** "Run the GL reconciliation and write up the variances." Breaks flagged with root cause and commentary. ## How it works 1. **Point it at your inputs:** filings, earnings calls, GP packages, onboarding docs, or just a company name. 2. **It routes to the right agent:** each task maps to a specialist that knows the workflow, the templates, and the checks. 3. **You get a draft back:** Excel models, branded decks, research notes, or reconciliations, structured for a human to review and sign off. Slash commands: `/comps` `/dcf` `/earnings` `/ic-memo` Built for investment banks, equity research desks, PE/VC funds, and wealth-management teams. Every output is an analyst draft for human review. No transactions executed, no ledger posts.
Give it a system, a code diff, or a data table, and get back a shareable HTML page that explains the concept visually. ## What it does - **Visual explainers:** a concept turned into an annotated HTML page with diagrams and callouts - **Diff visualization:** a code change rendered as a clear before/after a non-author can follow - **Data storytelling:** a table or dataset turned into charts and a guided narrative - **Shareable output:** self-contained HTML, client- and doc-ready ## Where it fits - **An engineer briefing stakeholders:** "Explain how our caching layer works for a non-technical audience." A visual page anyone can follow. - **A reviewer walking through a change:** "Visualize this refactor diff for the team." A clear before/after to share in the PR. - **An analyst presenting findings:** "Turn this results table into an explainer." Charts plus narrative on one page. ## How it works 1. **Hand it the material:** a system, a diff, or a data table. 2. **It builds the visual:** diagrams, annotations, or charts with a guided explanation. 3. **You get an HTML page back:** share it as is or refine the layout. Slash commands: `/generate-visual-plan` `/generate-web-diagram` `/generate-slides` `/fact-check` Built for technical docs and client briefings. Every page is a draft you can edit and reshare.
Give it documents or a dataset and get back structured knowledge work: brand and voice guidelines, account plans, and periodic briefs, from a collection of knowledge-work plugins. ## What it does - **Document synthesis:** documents and datasets distilled into structured summaries - **Brand & voice:** guidelines discovered and enforced across your content - **Account plans:** research pulled into a structured plan - **Periodic briefs:** weekly briefs and channel digests assembled for you ## Where it fits - **A consultant onboarding a client:** "Discover their brand voice from these materials." A guideline doc to work from. - **A sales team prepping:** "Generate an account plan for this prospect." A structured plan in one pass. - **A team staying aligned:** "Send me a weekly brief on this channel." A recurring digest. ## How it works 1. **Give it inputs:** documents, a dataset, or a target. 2. **It runs the right plugin:** synthesis, guidelines, planning, or briefing. 3. **You get a structured output back:** a doc ready to review and use. Slash commands: `/discover-brand` `/enforce-voice` `/generate-account-plan` `/weekly-brief` `/channel-digest` Built for consulting, research, and knowledge-intensive teams. Every output is a draft for you to review.
Give it a topic and get back a polished, magazine-style HTML slide deck with horizontal page turns. ## What it does - **Magazine layout:** editorial typography and composition, not stock slide templates - **Horizontal page-turns:** a deck that reads like flipping through a magazine - **Topic to deck:** a subject expanded into a designed set - **Share-ready:** self-contained HTML you can present or send ## Where it fits - **A creator publishing an explainer:** "Turn this topic into a magazine-style deck." A designed set ready to share. - **A knowledge worker presenting:** "Make this report feel editorial." A polished page-turn deck. - **A founder telling a story:** "Lay out our vision as a flip-through." A share-ready narrative. ## How it works 1. **Give it a topic:** a subject or an outline. 2. **It designs the deck:** magazine layout with page-turn flow. 3. **You get HTML back:** present it or send the link. Built for content creators and knowledge sharing. Every deck is a draft you can restyle and re-share.
Give it a target company or contact and get back a prospect profile, BANT score, LinkedIn outreach message, and email sequence — for B2B sales teams. ## What it does - **Prospect profiles:** company overview, decision-makers, and buying signals surfaced - **BANT scoring:** budget, authority, need, and timeline evaluated for each target - **LinkedIn messages:** personalised outreach copy ready to send - **Email sequences:** multi-step follow-up sequences tailored to the prospect ## Where it fits - **An AE prepping for an outbound push:** "Research these 10 accounts and score them." Profiles and BANT scores to prioritise the list. - **An SDR writing outreach:** "Write a LinkedIn message and email sequence for this contact." Personalised copy to send. - **A sales lead building a target list:** "Who are the decision-makers at this company?" A profile with names, roles, and entry points. ## How it works 1. **Give it a target:** a company name, URL, or contact. 2. **It researches and scores:** prospect profile built, BANT evaluated, outreach drafted. 3. **You get a sales package back:** profile, score, and copy ready to use. Built for B2B sales teams. Every output is a draft for you to review before sending.
Give it a research direction and get back a literature review, paper draft, and formatted references, covering the full path from survey to submission. ## What it does - **Literature review:** the field surveyed and summarized - **Paper drafting:** sections written toward a submission - **Reference formatting:** citations checked and formatted to the venue - **End-to-end:** the path from survey to submission in one workflow ## Where it fits - **A researcher starting out:** "Survey the literature on this topic." A review to ground the project. - **A student writing up:** "Draft the paper and format the references." Sections plus clean citations. - **A team near a deadline:** "Check our citations and tighten the draft." A submission-ready pass. ## How it works 1. **Give it a direction:** the research topic. 2. **It runs the workflow:** review, drafting, and references. 3. **You get outputs back:** a literature review and a formatted draft to refine. Slash commands: `/ars-full` `/ars-citation-check` `/ars-abstract` `/ars-format-convert` Built for the full research-to-submission workflow. Every draft is yours to verify and stand behind.
Describe your goal and get back a precise prompt tuned for the AI tool you are using, with no extra token overhead. ## What it does - **Goal to prompt:** a plain description turned into a structured, effective prompt - **Tool-specific tuning:** phrasing adapted to the model or tool you name - **Lean output:** no padding, so you pay no extra token cost - **Reusable:** prompts you can save and adapt ## Where it fits - **A power user refining a workflow:** "Write a prompt that extracts action items from meeting notes." A tuned prompt ready to reuse. - **A PM standardizing prompts:** "Turn this task into a reliable prompt for our tool." A consistent template for the team. - **A builder debugging output:** "My prompt rambles, tighten it." A leaner version that holds the intent. ## How it works 1. **Describe your goal:** what you want the AI to do. 2. **It engineers the prompt:** structured and tuned for your tool. 3. **You get a prompt back:** ready to paste, save, or adapt. Built for AI power users and product managers. Every prompt is a starting point you can test and refine.
Upload a CSV or Excel file, describe what you want to learn, and get back an insights report with charts, narrative, and business recommendations. No code required. ## What it does - **Insight reports:** your data turned into findings, not just tables - **Charts:** the right visualizations chosen for what you asked - **Plain-language narrative:** what the numbers mean, in words - **Recommendations:** concrete business next steps ## Where it fits - **A founder reading sales data:** "What's driving the dip in Q3?" Charts plus a plain-language read. - **A marketer on campaign numbers:** "Which channels actually converted?" A ranked answer with visuals. - **An ops lead on a spreadsheet:** "Find the outliers in this data." Flagged anomalies and what to do. ## How it works 1. **Upload your file:** a CSV or Excel sheet. 2. **Describe the question:** what you want to learn. 3. **You get a report back:** charts, narrative, and recommendations, no code written. Built for anyone who needs analysis without writing code. Every report is a draft for you to sanity-check against your numbers.
Point it at a pull request and get back an advisory, severity-tagged code review report that helps the author ship a change that improves the overall health of the codebase. ## What it does - **Severity-tagged findings:** issues ranked by impact so reviewers focus on what matters - **Advisory reports:** recommendations the author acts on, not automated rewrites - **Human- and AI-authored code:** works on PRs from both, with awareness of common AI-generated patterns - **Code health framing:** every finding tied to overall system quality, not just the changed lines ## Where it fits - **An engineer reviewing a PR:** "Review this change for quality and correctness." A prioritized report to work through. - **A team gating AI-generated code:** "Flag the issues in this Copilot-generated PR." Severity-ranked findings before merge. - **A lead coaching a junior:** "Give feedback on this PR for the author to learn from." An advisory report that teaches. ## How it works 1. **Point it at a PR:** the diff, the code, or the repository. 2. **It runs the review:** correctness, code health, and advisory-style findings. 3. **You get a severity-tagged report back:** ranked findings for the author to review and address. Built for engineering teams reviewing PRs. Every finding is advisory — the author owns the changes.
Describe a Google Cloud, Firebase, or Android need and get back code and configuration that follows Google's official standards. ## What it does - **Standards-compliant code:** GCP code written to Google's documented best practices - **Firebase configs:** setup and rules aligned with official guidance - **Android guidance:** code and configuration following platform conventions - **Best-practice defaults:** the recommended way, not just a way that works ## Where it fits - **A developer on GCP:** "Set up a Cloud Run service the recommended way." Code and config to official standards. - **A mobile dev on Firebase:** "Configure Auth and Firestore rules correctly." A compliant setup to drop in. - **An Android engineer:** "Scaffold this feature following platform best practices." Conventional, reviewable code. ## How it works 1. **Describe the need:** a GCP, Firebase, or Android task. 2. **It applies the standards:** Google's official best practices. 3. **You get code and config back:** ready to review and integrate. Built for GCP developers. Every output follows documented best practices and is a draft for you to review before shipping.
Bring a finance question or dataset and get back analysis reports, quant strategy backtests, and financial models, from a free, open-source skill collection. ## What it does - **Analysis reports:** a finance question worked into a structured write-up - **Quant backtests:** a strategy tested against historical data - **Financial models:** valuation and projection models built from your inputs - **Open source:** a free, inspectable skill collection ## Where it fits - **An analyst sizing an idea:** "Backtest this momentum strategy on these tickers." Performance stats plus a write-up. - **A quant prototyping:** "Build a DCF from these assumptions." A working model to stress-test. - **A researcher exploring data:** "Analyze this dataset for signal." A structured findings report. ## How it works 1. **Bring a question or data:** a strategy, a dataset, or assumptions. 2. **It runs the analysis:** backtest, model, or report as needed. 3. **You get output back:** results and a write-up to review. Built for analysts and quant researchers. Outputs are drafts for human review, not investment advice.
Hand it your React code and get back a quality report: performance traps, anti-patterns, and likely bugs, each with a fix you can apply. ## What it does - **Performance diagnosis:** unnecessary re-renders, unstable references, and expensive work in render, traced to the component and line - **Anti-pattern flags:** effect misuse, derived-state-in-state, prop drilling, and key misuse, called out with why they bite - **Bug-risk review:** stale closures, missing dependencies, and races in async effects surfaced before they ship - **Fix suggestions:** every finding paired with a concrete code change, not just a warning - **Rule-based checks:** a configurable rule set (`inspect`, `why`, `rules`) you can run in CI or on demand ## Where it fits - **A front-end engineer in code review:** "Review this PR's components for re-render traps and stale effects." A prioritized report with line-level fixes before you approve. - **A lead onboarding a codebase:** "Audit src/ for React anti-patterns and rank by impact." A triaged list to work through. - **An engineer chasing a slow page:** "Why does this list re-render on every keystroke?" The offending reference traced, with the memo or split that fixes it. ## How it works 1. **Point it at your code:** a file, a component, a PR diff, or a directory. 2. **It runs the diagnosis:** rules and analysis flag performance traps, anti-patterns, and bug risks. 3. **You get a report back:** findings ranked by impact, each with an explanation and a suggested fix to review and apply. Built for front-end engineers and teams running React code review. Every finding is a suggestion for you to review; no code changes without your approval.
Describe the interface you want and get back a high-fidelity HTML prototype you can open straight in the browser, animations included, built on 20 design principles. ## What it does - **Clickable prototypes:** a described screen or flow rendered as a working HTML page you can open in the browser - **High-fidelity UI:** layout, spacing, and type tuned against 20 built-in design principles, not a rough wireframe - **Animations:** transitions and micro-interactions included, so the prototype feels real - **Demo-ready output:** pages clean enough to drop into a pitch or a design review ## Where it fits - **A designer pitching a concept:** "Prototype the dashboard with a sidebar and three summary cards." A high-fidelity page to click through in the review. - **A founder prepping a demo:** "Mock up the signup flow end to end." A browser-ready prototype for the investor call. - **A PM validating an idea:** "Show me two layouts for this settings screen." Two polished options to compare. ## How it works 1. **Describe the interface:** a screen, a flow, or a full page. 2. **It applies the design system:** layout and interaction built on the 20 principles. 3. **You get HTML back:** open it in the browser, click through, and refine. Built for designers and product demos. Every prototype is a starting point for you to iterate on.
Bring a finance question and get back quant strategy backtests, financial models, and market research reports. ## What it does - **Quant backtests:** a strategy tested against historical data with performance stats - **Financial models:** valuation and projection models from your inputs - **Market research:** a sector or question worked into a research report - **Analyst-grade:** outputs structured for review, not black boxes ## Where it fits - **A quant prototyping:** "Backtest this mean-reversion idea." Stats plus a write-up to judge it. - **An analyst modeling:** "Build a three-statement model from these assumptions." A working model to stress. - **A researcher on a sector:** "Summarize the landscape and key players." A structured brief. ## How it works 1. **Bring a question:** a strategy, assumptions, or a sector. 2. **It runs the work:** backtest, model, or research. 3. **You get output back:** results and a write-up for review. Built for quant researchers and financial analysts. Outputs are drafts for human review, not investment advice.
Paste AI-written text and get back a natural version with the tell-tale AI patterns stripped out. ## What it does - **Pattern cleanup:** the repetitive phrasing and hedging that mark AI text removed - **Natural rewrite:** rhythm and word choice loosened to read like a person wrote it - **Tone preserved:** your intent and register kept intact - **Drop-in:** paste in, get clean text back ## Where it fits - **A content creator polishing a draft:** "Make this blog intro read naturally." A version without the AI tells. - **A student tightening prose:** "Humanize this summary but keep my argument." Same point, cleaner voice. - **A marketer refining copy:** "Loosen up this product description." Warmer, less templated text. ## How it works 1. **Paste the text:** any AI-written passage. 2. **It rewrites:** AI patterns out, tone in. 3. **You get clean text back:** ready to use or refine further. Built for content creators, academic writing, and marketing copy. The rewrite is a draft for you to review; you own the final words.
Give it your product info and get back growth-experiment plans, sales-funnel analysis, and content-optimization recommendations. ## What it does - **Growth experiment plans:** a backlog of testable ideas with hypotheses and expected outcomes - **Sales-funnel analysis:** where users drop and what to do about it - **Content optimization:** what to change, add, or cut to convert better - **Actionable output:** recommendations structured for a team to pick up and run ## Where it fits - **A growth team planning a sprint:** "What experiments should we run this cycle?" A ranked backlog with rationale. - **A marketer diagnosing drop-off:** "Why are users leaving at checkout?" A funnel read with fixes. - **A content lead improving copy:** "Optimize this landing page for conversions." Specific recommendations to apply. ## How it works 1. **Give it your product info:** audience, funnel, and current performance. 2. **It analyzes and plans:** experiments, funnel, and content recommendations. 3. **You get a growth plan back:** ideas ranked by impact, ready to run. Built for growth marketers and product teams. Every recommendation is a draft for you to validate and act on.