Explorar skills

Activate for: macro overlay, macroeconomic scenarios, PIT PD, point-in-time PD, credit cycle adjustment, scenario weighting, forward-looking information, satellite model, GDP, unemployment, house price index, IFRS 9 scenarios, scenario probability. NOT for: ECL calculation mechanics (use ifrs9-ecl), staging assessment (use ifrs9-staging), stress testing for capital adequacy (use stress-testing).

This skill should be used when the user says "competitive analysis", "gap analysis", "competitive gap", "stress competitive", "compare competitors", "feature comparison", "competitive stress test", "market comparison", "competitor analysis", or wants to stress-test a product concept by conducting deep competitive gap analysis with feature comparison, gap identification, and positioning assessment.

This skill should be used when the user says "prfaq", "pr faq", "pr/faq", "press release stress test", "stress prfaq", "amazon pr faq method", "test the pitch with a pr/faq", "validate concept through pr/faq", "critique press release", "pr faq stress test", "will this marketing story hold up", or wants to stress-test a product concept by drafting a compelling press release and FAQ, then adversaria

Escreva testes adversariais que intencionalmente forçam caminhos de falha. Use ao fortalecer o tratamento de erros, testar suposições sob estresse, validar comportamento de limite ou caçar falhas silenciosas.

Routes banking regulatory queries to the correct product skill and jurisdiction overlay. Activate for any query involving IFRS 9, ECL, expected credit loss, Stage 1, Stage 2, Stage 3, SICR, PD, LGD, EAD, Basel III, Basel IV, CET1, RWA, capital ratio, LCR, NSFR, HQLA, ICAAP, stress test, AML, KYC, CDD, EDD, SAR, STR, sanctions, OFAC, HMT, PEP, FATF, reconciliation, nostro, suspense, FRTB, market ri

This skill should be used when the user says "spike", "arn spike", "validate risks", "technical validation", "proof of concept", "validate architecture", "risk spike", "test this risk", "will this work", "technical spike", "validate the stack", or wants to validate critical technical risks from the architecture vision by creating minimal proof-of-concept code and testing whether the chosen technol

Desenvolvimento Orientado a Testes (TDD) em qualquer linguagem suportada. Use ao implementar funcionalidades ou correções com a metodologia TDD, escrevendo testes antes do código, ou seguindo o desenvolvimento estilo XP.

Factor research framework for evaluating single-factor effectiveness across A-shares, HK, and US stocks — information coefficient (IC), information ratio (IR), decile portfolio backtests, and IC decay (serial autocorrelation). Triggers: "因子研究", "IC分析", "信息比率", "分层回测", "因子有效性", "单因子测试", "因子衰减", "因子评估", "IC分析", "信息比率", "分層回測", "因子有效性", "單因子測試", "factor research", "information coefficient", "IC", "IR

Revisa alterações de código em um PR do GitHub usando a CLI gh. Utilize quando o usuário solicitar a revisão de um pull request, a análise de diferenças de PRs ou o fornecimento de feedback em PRs abertos com avaliações estruturadas de qualidade, segurança e testes.

Cross-symbol comparison (2–5 stocks) via Longbridge — valuation (PE / PB / PS / dividend yield), current price + change, latest financial KPIs (revenue / net income / ROE), market cap. Renders as a single matrix; flags cross-currency or cross-industry caveats. Triggers: "X 和 Y 哪个值得买", "X vs Y", "几只股票对比", "同行业谁最强", "X 跟 Y 谁更便宜", "几只哪个增速快", "科技七姐妹谁最强", "X 跟 Y 對比", "X 跟 Y 哪個便宜", "X vs Y", "compare X

Swiss adversarial legal analysis — stress-tests any legal position by running three independent agents: Advocate (strongest case FOR), Adversary (strongest case AGAINST), and Judicial synthesizer (Erwägung-style balanced conclusion with probability). Trigger when: a user wants to stress-test a legal position, check for weaknesses before filing, validate that an analysis is not one-sided, or explic

Activate for: validate, build measure learn, BML, pivot, persevere, pilot results, what did we learn, experiment results, assumption test results, was I right, did it work, should I pivot, what should I change, learning synthesis, validated learning, invalidated assumption, pilot analysis, what our pilot taught us, early customer data, what customers told us, post-pilot analysis, pivot or continue