Research & Search

crbnos Skill

Survey how best-in-class ERPs and point solutions implement a feature, and produce a findings file at .ai/research/{slug}.md. Use when designing a new feature, evaluating approaches, or answering "how do competitors / SAP / the industry do X". Required before designing any ERP-domain feature (accounting, costing, tax, inventory valuation, RMA, MRP, etc.). Do not use for UI styling questions (copy an existing Carbon screen instead) or for bugs (use root-cause).

gupsammy Bundle

This skill should be used when the user asks to "research a topic", "run-research", "last30", "what's happening with X", "what are people saying about X", "find the best X", "X prompts", "latest on X", "X news", "what are people recommending for X", "research X for me", or wants to know what's trending, discussed, or debated about any subject in recent weeks.

gupsammy Skill

Fetch and summarize a web page

guillaumelessard Skill

Sinter decoder entry points for QECTOR (manual 17.2). Covers `qector_sinter_decoders()` returning qector_blossom, qector_belief, qector_unionfind, qector_bposd, qector_unionfind_unweighted, the role of these in the community-standard sinter benchmark harness, and the qector-research.sinter_decoder_list probe. Load for any question about sinter, the community benchmark, or head-to-head LER comparisons.

guillaumelessard Skill

The PyMatching-compatible shim in qector-decoder-v3 (manual 17.1). Covers `qector_decoder_v3.pymatching_compat.Matching` as a drop-in for `pymatching.Matching`, the supported methods (from_check_matrix, from_detector_error_model, add_edge, add_boundary_edge, decode, decode_batch, decode_to_edges_array), the fact that it is backed by the exact Blossom decoder, the one-line import swap, and the smoke test pattern via `qector-research.pymatching_compat_check`. Load for any question about PyMatching compatibility, Stim / PyMatching pipelines, or a one-line decoder swap.

nadav011 Bundle

Use when user wants to 1. SCAN package.json, next.config, manifest 2. RESEARCH Context7 for vite-plugin-pwa + Workbox patterns

a-v-ershov Bundle

Map how users actually move through the product to get value — the customer journey and the step-by-step flows for each feature, informed by conventional patterns for the category and an adversarial review pass. Use after define-product-requirements (reads product-requirements.research.md) and before design-architecture. Writes a source-cited .dev-skills/project-spec/user-flows.research.md plus a short human summary; an independent reviewer returns findings and the phase applies them in place. The second product-layer step: it describes the experience (WHAT the user does), never the technical HOW and never visual UI design.

a-v-ershov Bundle

Define the project's development style guide once the stack is chosen: how code is organized (module/folder architecture), named, commented and documented, how errors are handled, and how tests are written. For each dimension where the chosen stack offers real alternatives it weighs the top 2–3 idiomatic options with trade-offs and recommends one; everything else inherits the stack's canon with a citation. Use after design-architecture and before design-dev-architecture. Writes a source-cited code-style.research.md, a short human summary, and the distilled code-style.md guide that implement-feature, verify-feature, refactor and write-tests follow on every task.

a-v-ershov Bundle

Turn a validated idea into the product definition: who it is for, and the full set of features being built — backed by real-world research (comparable products, table-stakes features) and an adversarial review pass. The committed set holds at most 15 features: sub-capabilities fold into the feature they belong to, and whatever does not earn a place is cut into non-goals rather than deferred. Use after validate-idea and before create-user-flows and design-architecture. Writes a source-cited product-requirements.research.md plus a short human summary. Defines the product layer (WHAT and for WHOM) — never the technical HOW, which is design-architecture's.

kovrichard Bundle

Analyze YouTube videos using Gemini's native video understanding — summarize, extract insights, answer questions. Use when analyzing, summarizing, or extracting information from a YouTube video.

mshahiddigital Skill

Content Gaps

mshahiddigital Bundle

Keyword Gaps

mshahiddigital Skill

Topical Gaps

mshahiddigital Bundle

Competitor Analysis

nahiddotai Skill

Find non-obvious connections across the user's own notes, drafts, research, transcripts, or work when they ask to daydream, connect dots, or surface hidden patterns.

cmdecker95 Bundle

Generate APA7 reference citations. Trigger when user asks for citation/reference/bibliography entry in APA format — URL given, source type named, partial details, or link pasted with 'cite this.' Also trigger when user needs citation for paper/essay/reference list. Handles: webpages, journal articles, books, YouTube videos, news articles, social media, reports, podcasts, etc.

zhnnky329 Skill

Manage and verify references for mathematical modeling contest papers, generating BibTeX entries, checking citation completeness, and ensuring all references are traceable to actual sources.

skryx-l-a Skill

Stand up a standalone quantitative TRADING STRATEGY project in a project folder from the user's answers — a walk-forward, leakage-free backtest with realistic costs and slippage, an honest BACKTESTS.md, and a reflexion loop that PROPOSES but never auto-deploys. A project-kit sub-skill loaded by new-project's routing whenever the user wants to BUILD a trading/quant strategy, backtest an edge, or research a signal. Built on a disciplined honest-eval culture. Paper/research only by default.

skryx-l-a Skill

The FALLBACK project-kit sub-skill loaded by new-project routing for ANY project with no specific type match — life-admin, an event, a hardware build, a personal system, a one-off, whatever. Use WHENEVER the user wants to start, set up, organise, or run a project that doesn't fit website / app / API / data / business / research / writing / game-mod / any other type. Makes zero code or business assumptions.

skryx-l-a Skill

Build and set up a research-and-decision project — a structured investigation that compares candidates against criteria to reach a sourced, logged recommendation. This is a project-kit sub-skill loaded by new-project routing. Use WHENEVER the user wants to research a question, weigh options, compare alternatives, build a decision matrix, or decide between candidates (which X to choose) by a deadline.

fivetaku Bundle

Comprehensive, citation-heavy research workflow with session state, structured outputs, and source-quality checks. Use when the user wants deep research, a long-form report, or citation-backed analysis on a topic. Korean triggers — "리서치해줘", "딥리서치", "심층 연구", "[주제]에 대해 리서치해줘". English triggers — "deep research on", "research report".

fivetaku Bundle

Structured research-query builder that turns a vague topic into a research brief and machine-readable query before full insane-research starts. Use when the user wants help framing a research request. Korean triggers — "리서치 쿼리 만들어줘", "쿼리 빌더". English triggers — "research query builder", "structured research query".

galleonlabs Bundle

Journal and review Hyperliquid orders, fills, positions, funding, fees, incidents, and trading process from the exchange record. Use when an action or trade has completed, for a daily or weekly review, or when the user asks what execution cost, outcome, or control failure occurred. Read-only; not for market research, planning, or execution.

genericservice Bundle

Open-source intelligence on people, companies, domains, and B2B accounts. Use when the user wants to investigate, vet, research, or build a dossier on a target — phrases like "OSINT", "due diligence", "background check", "research this person", "look into [company/domain]", "vet this prospect/vendor", "what does X do", "is this account worth pursuing", "find me a contact at", "who's the buyer for", or any open-source investigation task. Disambiguates identities before reporting and grades every claim by independent source count.

genericservice Bundle

Conduct comprehensive, multi-round research that produces rich visual reports. Use when asked for "deep research", "comprehensive analysis", "compare frameworks", "evaluate options", "research the state of X", or any task requiring investigation across 10+ sources. NOT for quick lookups — this is a 5-15 minute deep dive that produces a briefing-quality artifact with screenshots, diagrams, tables, and cited findings.

gnekt Skill

Process audio recordings, meeting transcripts, podcasts, or lectures. Runs an intake interview (date, mode, speakers, language) then processes into structured notes with action items, decisions, and glossary. Triggers: EN: "transcribe", "I have a recording", "process this audio", "meeting notes from recording", "summarize the call", "lecture notes", "podcast summary". IT: "trascrivi", "ho una registrazione", "processa questo audio", "note della riunione", "riassumi la call". FR: "transcrire", "j'ai un enregistrement", "résumer l'appel". ES: "transcribir", "tengo una grabación", "resumir la llamada". DE: "transkribieren", "Aufnahme verarbeiten". PT: "transcrever", "tenho uma gravação".

getlost01 Skill

Sweep the IPO calendar — what's open, closing, upcoming, or awaiting listing — and flag which merit a closer look. Use when the user asks what IPOs are open or coming up, or about allotment and listing dates. Read-only — never applies or subscribes.

getlost01 Skill

Track the rate environment — RBI stance, repo path, G-Sec curve, inflation — and translate it into implications for the user's debt holdings. Use when the user asks about RBI policy, rate cuts/hikes, yields, locking rates, or how rates affect their debt. Read-only.

getlost01 Skill

Health check across all the user's SIPs and funds as a set — expense ratio earned, category-rank drift, manager changes, overlap creep, continue/pause/redirect per SIP. Use when the user asks to review their SIPs, whether to continue one, or for a periodic MF checkup. Read-only — never changes a SIP.

getlost01 Skill

Analyze the user's F&O positions and candidate trades — greeks, open interest, payoff, straddle levels, margin. Use when the user asks about options/futures positions, greeks, open interest, payoff, straddle, or F&O margin. Read-only.

getlost01 Skill

Deep dive on one IPO — prospectus financials, valuation vs. listed peers, issue structure, subscription demand — ending in a subscribe/avoid view with sizing. Use when the user asks whether to apply for a specific IPO. Read-only — never applies, bids, or subscribes.

getlost01 Skill

Market briefing — movers, trending stocks and funds, macro/budget notes, calendar context — with anything touching the user's holdings called out. Use when the user asks what's happening in the market, for a briefing, or about market movers. Read-only.

getlost01 Skill

Analyze a bond, NCD, or debt fund — yield vs. G-Sec, credit rating, duration, issuer concentration, liquidity. Use when the user asks about a bond, NCD, debt fund, or fixed-income allocation. Read-only.

getlost01 Skill

Track upcoming results dates for the user's holdings and review announced results — vs. expectations, price reaction, thesis check. Use when the user asks about upcoming earnings/results, "who reports this week", or how a holding's results were. Read-only.

getlost01 Skill

Deep dive on one stock, ETF, or fund — fundamentals, technicals, peers, current news, and fit against the user's portfolio. Use when the user asks "should I buy <symbol>", wants research on a specific instrument, or a buy/hold/avoid view. Read-only.

getlost01 Skill

Project annual dividend income from the user's holdings — per-stock payout, yield-on-cost, upcoming ex-dates, sustainability flags. Use when the user asks about dividend income, portfolio yield, upcoming dividends, or building an income stream. Read-only.