Loading...
Loading...
Found 6 Skills
The single entry point into the daily-work arc — a hybrid menu/argument router. Trigger whenever the user invokes /dev-workflows:daily, types /daily, asks "what should I do now", "where was I", "start my day", "what's next today", "wrap up my day", "end my day", or seems unsure which skill fits their current daily-work moment. Bare invocation shows a 5-station menu (starting / working / filing findings / reporting / wrapping up); with an argument (start | work | file | report | wrap, synonyms accepted) it jumps straight to the station and hands off to the right skill: ado-backlog:my-work, the situational toolbox (grill-then-plan, debug-mantra, study-design-verify, naming-audit, fit-gap-analysis, problem-description, ticket-trace, scrutinize, review-pr, dual-verifier, drive-to-legacy, crm-archaeology, generating-test-cases), findings-to-ado-backlog or ado-create-work-items (github-backlog twins on request), management-talk, or invoice-generator.
Governs any recommendation that depends on facts OUTSIDE the codebase that change faster than training data — vendor products, certifications, exam codes, SKUs, APIs, pricing, licensing, partner programs, job markets, industry trends, hype cycles. Use this skill whenever the user asks which certification or exam to take, whether a product/API/SKU/exam is still current or supported or retired, what a job market wants, whether to adopt a technology, what the trends are in a field, how a field will look in N years, or asks for any 1–5 year career or technology roadmap — and ALSO whenever your own answer is about to name a specific vendor product, credential, price, or market claim, even when the user never asked you to verify anything. The failure it prevents is confident, well-structured advice built on facts that quietly expired: model memory is stale by construction and vendors retire things faster than anyone expects. Do NOT use for questions answerable from the user's own code or system (that is study-design-verify), for a single fact lookup with no recommendation attached, or for pure preference questions with no external facts at stake.
Study design and validity review for radiology and medical AI research. Identifies analysis unit, cohort logic, leakage risks, comparator design, validation strategy, and reporting guideline fit before drafting or submission.
Use when planning and synthesizing product/user research as a method-and-repository discipline — selecting the right method for the goal (generative interviews vs usability test vs concept test vs validation), computing method-based saturation/sample size with an explicit confidence level, or synthesizing coded observations into insights while flagging single-source anecdotes. Never fabricates user insight; an insight requires recurrence across independent participants. Distinct from product-team/ux-researcher-designer (persona/journey artifacts), product-discovery (discovery-sprint planning), and experiment-designer (live A/B) — this is the research-ops method + insight-repository layer.
Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging), estimating sample size and power for two-arm designs (means / proportions / survival), or scoring a study plan for feasibility and a GO / GO-WITH-CONDITIONS / REDESIGN / NO-GO phase-gate decision. Every output is an ESTIMATE plus a named human owner (clinician / biostatistician / regulatory owner) — never clinical fact, never a finished protocol. Distinct from ra-qm-team, which handles the regulatory/QM submission (ISO 13485, EU MDR, FDA 510(k)/PMA/QSR), not the study design.
Reconcile what the numbers say with what users say, and design the study that settles it rather than restates it. Use when behavioural data and research findings point different ways. For reading the data on its own, use `behavioural-analytics`; for synthesising interviews on their own, use `affinity-diagram`.