AI Agent Skills

Runs a realistic mock interview in chat — builds an interviewer persona from the intel file, asks one question at a time with pressure follow-up chains, then scores the…

Choose the right Parallel API and configuration for cost, latency, and answer quality. Use when adding live web data to an app: current events and prices, a cited answer…

Discover entities (companies, people, products, etc.) matching a natural-language description. Use when the user asks to 'find all X' or 'list every Y that…' — e.g., 'Fi…

Use when the user asks to research, investigate, verify facts with sources, compare competitors, study a market or industry, review literature, prepare an evidence-backe…

Use for every progress update, status report, problem explanation, ETA, review, acceptance, or completion report to the operator/owner, especially when they ask “到哪了”, “…

Researches current web and external technical information through source-backed discovery, retrieval, and repository, document, or media inspection. Use this skill when…

Route work that is too large for a single chat into a structured plan. Use when the user describes a multi-step build, a migration, a rewrite, an audit, a refactor acros…

Transform any research material into SEO+GEO-optimized blog posts for Knox Hub. Takes any input (URL, article text, notes, video transcript, competitor post, topic idea)…

Use when the user wants an app idea turned into a Product Requirements Document (PRD) committed to a repo — "create a PRD", "/app-prd", "turn this idea into a PRD", or a…

Evidence-first deep reading for books, articles, PDFs, and document sets. Extract core claims, argument structure, supporting evidence, source locations, confidence leve…

Turn a refined requirements document into a structured implementation PLAN.md a fresh session can execute. Planning only — decides the "how", not the "what". Invoke manu…

Time tracking, worklogs, and time reports. TRIGGERS: 'log time', 'time spent on', 'log hours', 'log work', 'worklog', 'time tracking', 'timesheet', 'how much time', 'tim…

Handle tasks that exceed the context window by decomposing them: size and filter the input, chunk it, run recursive sub-agents on independent parts, verify on small wind…

Construction document review with PE judgment — RFI research, submittal analysis, coordination checking, scope gap detection. Use when reviewing drawings, specs, submitt…

Use when ending a session or passing work to another agent - produces a compact handoff document that transfers context, state, and next objective without copying source…

Portfolio and roadmap batch intake, turn a pile of asks into a prioritised verdict. Use when someone hands a BATCH and wants a decision: "prioritise this backlog", "scor…