Research & Search

getlost01 Skill

Watch for AMC-level red flags behind the user's funds — manager exits, SEBI action, AUM swings, scheme mergers. Use when the user asks about an AMC, a fund-manager change, or wants an "anything wrong at my fund houses" check. Read-only.

getlost01 Skill

Review the user's live brokerage portfolio — allocation, risk, per-holding buy/hold/avoid views, rebalancing. Use when the user asks to review their portfolio, check allocation or diversification, get stock/ETF/MF suggestions, or rebalance. Read-only.

getlost01 Skill

Track dividends, splits, bonuses, buybacks, rights issues, and demergers on the user's holdings — key dates, cost-basis and tax impact, hold/tender decisions. Use when the user asks about any of those, record or ex-dates, or "any corporate actions coming up". Read-only.

getlost01 Skill

Estimate unrealized and realized LTCG/STCG on the user's holdings and surface tax-loss and gain-harvesting opportunities. Use when the user asks about capital gains, tax, LTCG, STCG, harvesting losses, or filing prep. Read-only — estimates, not tax advice.

getlost01 Skill

Deep dive on a US-listed stock (e.g. AAPL, NVDA) — fundamentals, technicals, news, currency and LRS context. Use when the user asks about a US ticker or whether to buy one. Read-only.

getlost01 Skill

Sweep the watchlist in PORTFOLIO-PLAN.md — which triggers are hit, which are near, and what changed on the names now in range. Use when the user asks about their watchlist, whether anything hit their price, or "anything worth looking at today". Read-only.

getlost01 Skill

Review the gold/silver sleeve — SGB premium or discount to gold value and remaining tenor, gold/silver ETF tracking and liquidity, sleeve size vs. the plan's target. Use when the user asks about gold, silver, SGBs, gold ETFs, or a commodity allocation. Read-only.

getlost01 Skill

Estimate today's mutual fund NAV move before the AMC publishes it — last-disclosed holdings weighted by each constituent's live % change. Use when the user asks how a fund is moving today or what its NAV will do. Read-only; an estimate, never the published NAV.

getlost01 Skill

Diff the user's actual allocation against their PORTFOLIO-PLAN.md targets and produce sized rebalancing suggestions. Use when the user asks to rebalance, check if they're over/under-weight, or align to a target. Read-only — suggestions only.

getlost01 Skill

Judge an ETF or index fund on tracking difference vs. its index, expense ratio, premium/discount to iNAV, spread and depth at the intended order size, and AUM — comparing same-index alternatives. Use when the user asks which index ETF to hold, about tracking error, or whether an ETF is trading away from fair value. Read-only.

getlost01 Skill

Deep dive or peer comparison on mutual funds — expense ratio, alpha vs. benchmark and category, manager consistency, overlap with existing holdings. Use when the user asks about a specific fund, wants funds compared, or asks whether a fund is worth holding. Read-only — no SIP changes.

getlost01 Skill

Stress the portfolio against scenarios — market drawdown, sector crash, single-stock hit, rate shock, currency move, F&O margin call — measured against the plan's risk limits. Use when the user asks what happens if the market falls, how much they could lose, or about downside, drawdown, or scenario risk. Read-only.

getlost01 Skill

Review actual trade/order history — win rate, holding period, churn and cost, and whether real behavior matches the plan's stated horizon. Use when the user asks "how have I been trading", "am I overtrading", "what's my win rate", or wants a trade journal review. Read-only.

getlost01 Skill

Build or update the user's PORTFOLIO-PLAN.md by interviewing them against their real holdings — targets, risk limits, rebalancing rules, theses, fixed-income inventory, SIP register, tax context. Use when that file is missing, stale, or lacks a section another skill needs, or when the user asks to set up or change their plan. Writes only that file.

hartmut-ux Skill

Case law detective. Dig up UK Supreme Court + Swiss Federal Court precedents. Track legislative changes in GDPR UK, GwG, EU AI Act. Build rock-solid argumentation. Cite sources perfectly. Generate research memos partners can hand to clients."

hartmut-ux Skill

Internal firm brain. Build searchable knowledge base, organise precedents, manage templates, create onboarding materials for junior associates. Centralise firm expertise in one place. Make finding answers instant."

dineway Skill

Convert an accepted Dineway Research Result into one Writer-ready, evidence-linked Brief Result with human approval.

dineway Bundle

Collect and interpret source-attributed Dineway content performance, ranking, crawl integrity, traffic, and AI-citation observations. Use for scheduled monitoring, Google ranking changes, user-owned GSC evidence, ChatGPT/Perplexity/Claude/Gemini/Google AI visibility checks, content decay, anomaly review, or Fix-opportunity evaluation.

dineway Bundle

Build a complete SERP-first, source-attributed Dineway Research Result for any content Research type before Brief.

dineway Bundle

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.

dineway Bundle

Run a deep, evidence-linked GEO and AEO inspection of an exact Dineway CMS Draft Revision. Use for quotability, answer structure, citation readiness, entity clarity, cross-platform citation evidence, citation-gap diagnosis, and an independent deep GEO 0-100 Result.

federicoimparatta Bundle

Use this skill when the user asks to write or structure a leadership brief, a board update, or a one-page summary for executives. Trigger phrases include "exec brief", "board update", "one-pager for leadership", "resumen para el board", "brief for the CEO", "summarize this for the board". Produces a single page that leads with the bet, the number, and the ask. Works in English and Rioplatense Spanish.

federicoimparatta Bundle

Use this skill when the user asks to turn user research into patterns. Trigger phrases include "synthesize user interviews", "interview notes to patterns", "research synthesis", "what did we learn from these interviews", "cluster these findings", "sintetizar entrevistas". Produces patterns grounded in observed behavior, not a feature list. Separates what users do from what they say. Works in English and Rioplatense Spanish.

felinics Bundle

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command.

kdevos12 Bundle

Last-resort skill. Invoke when no obvious or coherent solution is available and hallucination risk is high. Searches peer-reviewed literature and validated sources (Perplexity, bioRxiv, PubMed) before attempting an answer. Generalist — applies to any domain.

bex-co Bundle

Summarize mobile changes since the previous release, bump the Beancount mobile version, prepare localized release notes and listings, and release to the Apple App Store and Google Play. Use for $mobile-release or requests to cut a mobile store release. Skip ordinary code shipping, OTA-only updates, release-status questions, and requests to create or edit this skill.

bjesuiter Skill

Use the summarize CLI when the user asks to summarize or extract content from URLs, local files, PDFs, images, audio, video, or YouTube.

deanpeters Bundle

PAIN stands for Persona, Activities, Insights, and Needs – the four main research topics explored in this structured method for gathering insights about users or user identities.

decocms Skill

Summarize site performance metrics for a given period, including bandwidth, requests, cache hit ratio, top paths, top countries, and anomalies.

decocms Skill

Quick fixes for common, isolated issues in deco.cx storefronts. Use when the user reports a specific symptom that doesn't warrant a full skill. This is a growing knowledge base — add new entries as they're discovered.

huang-sir1 Bundle

Draft or rebuild imaging-AI / radiomics / radiogenomics manuscript sections for Radiology (RSNA), Nature-portfolio/npj, European Radiology, NEJM, Science, or Lancet-family style from author-provided results, figures, notes, or Chinese drafts. Enforces the target venue's manuscript shape: Radiology Summary/Key Results, Nature-style broad scientific narrative, European Radiology key points/clinical relevance, NEJM four-part clinical abstract and SAP rigor, Science compact display-item story, or Lancet-series Research in context and AI/data transparency using The Lancet Digital Health guide as the default proxy. Use when the user wants to write or restructure imaging-research prose, not just polish it. Never invents data, metrics, or citations.

huang-sir1 Bundle

Find publishable frontier directions and innovation points for imaging-AI / radiomics / radiogenomics research, grounded in the publication patterns of high-impact journals (Radiology, Radiology: AI, Lancet Digital Health, Lancet Oncology, Nature Medicine, Nature Communications, npj Digital Medicine, npj Precision Oncology, eClinicalMedicine, Cell Reports Medicine). Use when the user asks for frontier directions, innovation points, hot vs suitable topics, "近三年前沿方向", "创新点", "what's novel in imaging AI", or wants to know the evidence/publication-pattern basis behind a recommendation ("有什么文献依据", "证据"). Translates trends (foundation models, self-supervised, vision-language, multimodal fusion, longitudinal, weak/federated learning, radiogenomics) into executable research questions matched to the user's actual data. Encodes publication-pattern heuristics, not a fabricated citation list — routes live verification to radiology-search and never invents PMIDs/DOIs.

huang-sir1 Bundle

Polish finished imaging-research prose to Radiology (RSNA), Nature-portfolio/npj, European Radiology, NEJM, Science, or Lancet-family house style: concise sentences, correct tense, precise statistical reporting, venue-specific p-value/number/reference style, AI/data-sharing declarations, abbreviation control, and overclaim/causal-language detection. Uses The Lancet Digital Health guide as the default Lancet-series proxy. Use when the user wants to tighten, copyedit, or align existing paragraphs to a target journal style, not draft new content. Returns clean copy-paste prose plus a short change log; never alters reported numbers or invents content.

iflytek Bundle

Retrieve and summarize current weather and forecasts for locations, rain, temperature, and travel planning using an available web tool or wttr.in over HTTPS.

lensetek Skill

Menganalisis, merangkum, dan mensintesis temuan dari beberapa publikasi ilmiah untuk menjawab pertanyaan riset tertentu secara komprehensif tanpa fabrikasi data.

lensetek Bundle

Membuat matriks perbandingan paper terstruktur, tabel ekstraksi data Systematic Literature Review (SLR), dan peta bukti (evidence map) secara otomatis dan konsisten.