测试与安全技能

Use when asked 大模型备案怎么做, 生成式人工智能服务备案还是登记, 算法备案流程, AI 生成内容标识怎么加, 我们接了已备案的大模型还要备案吗, or prepare a generative AI product for launch in mainland China. Produces the obligations that apply (generative AI service filing, registration for apps built on a filed model, algorithm filing, AI-generated content labelling), the documents and security self-assessment to prepare, a launch checklist, and the questions for the provincial cyberspace administration, each marked to confirm.

中文简介正在准备中。当前显示原文说明。

Fix a team's chat sprawl — the channel map with one purpose per channel, the naming scheme that makes purpose findable, the archive pass for the dead and duplicated, and the posting norms (threads, @-discipline, urgency signals) that keep signal findable. Use when asked clean up our Slack/Teams, we have 90 channels and nothing is findable, set channel norms, or where should things get posted. Produces the channel audit and map, the naming scheme, the norms card, and the archive pass.

中文简介正在准备中。当前显示原文说明。

Assess physical and transition climate risk for a site, product, or portfolio with scenario-based structure. Use when asked to run a climate risk assessment, evaluate physical or transition risk, prepare TCFD/ESRS-style climate risk analysis, or assess how climate scenarios affect an asset or business. Produces a hazard-exposure-vulnerability matrix across 2030/2040/2050 horizons and labelled scenarios, with financial-impact ranges, confidence levels, and adaptation options.

中文简介正在准备中。当前显示原文说明。

Diagnose a bug systematically instead of guessing — reproduce, isolate, form hypotheses, and test them to root cause. Use when debugging, chasing a defect, an intermittent failure, or 'why is this happening?'. Produces a structured diagnosis: a reliable repro, the narrowed-down location, ranked hypotheses with how to test each, and the root cause + fix once found.

中文简介正在准备中。当前显示原文说明。

Respond to a brand or executive impersonation incident — deepfaked executives, cloned support lines, fake apps, spoofed domains, or AI-generated scam content wearing your name. Use when a deepfake of a leader is circulating, customers report a fake version of your product or support channel, or to prepare the impersonation playbook before it happens. Produces an incident response: verification protocol, takedown sequencing by platform, customer and public communications, and the hardening plan. For general crisis comms use press-release/pm-crisis skills; for security incidents inside your systems use security-incident-response.

中文简介正在准备中。当前显示原文说明。

Convert a meeting into async work that actually decides — the doc-plus-deadline format that replaces the room, the comment-window rules, the decision-closure step that async usually fumbles, and the honest test for what still needs synchronous. Use when asked can this meeting be async, replace our status meeting with a doc, run this decision without a call, or async isn't working for us. Produces the conversion design, the async artifact format, the closure protocol, and the still-needs-a-room list.

中文简介正在准备中。当前显示原文说明。

Audit a week the way Arnold Bennett's 'How to Live on 24 Hours a Day' (1908) prescribes — time as the one income that cannot be increased, the day-within-the-day, and starting with 90 minutes, not a life overhaul. Use when someone says 'I have no time', 'work eats everything', 'I want to learn X but can't fit it', or asks for a time audit or evening routine. Produces a time ledger, one reclaimed 'inner day' block, and Bennett's own warnings about overreach.

中文简介正在准备中。当前显示原文说明。

Extract and risk-rate hidden assumptions in a product brief or PRD. Use when asked to review a product brief for assumptions, audit a PRD for risks, find hidden assumptions, validate product plans, or run an assumption analysis. Produces a prioritised assumption map with confidence and impact scores, recommended validation methods, and critical assumption flags.

中文简介正在准备中。当前显示原文说明。

Extract every hidden assumption from a plan or document and put a price on each one — what it costs if wrong, what it costs to test. Use when about to commit to anything whose author says 'obviously' or whose spreadsheet has hardcoded cells: the bounty hunt makes the invisible load-bearing beliefs explicit and tells you which three to test this week. Produces the assumption ledger (priced and ranked), the cheapest test for each dangerous one, and the document's honest confidence statement.

中文简介正在准备中。当前显示原文说明。

Plan tests for an API endpoint or service — functional, negative, and contract. Use when asked to test an API, write API test cases, plan REST/GraphQL endpoint testing, or validate an API contract. Produces an API test plan — per-endpoint cases (status codes, schema, auth, validation, errors), boundary/negative cases, contract checks, and non-functional notes — so the API is verified beyond the happy 200.

中文简介正在准备中。当前显示原文说明。

Run the worst-case drill before an agent goes autonomous — the 'if this agent were fully hijacked right now, what's the damage' walk-through, the containment controls (caps, kill-switch, reversibility, isolation), and the recovery plan. Use when asked what's the worst my agent could do, run a blast-radius assessment, prepare for an agent going rogue, or am I ready to let this run unattended. Produces the worst-case walk-through, the containment controls, the reversibility audit, and the incident-recovery runbook.

中文简介正在准备中。当前显示原文说明。

Use when asked to check whether a figure is audited, which headline numbers sit outside the audited accounts, what 'adjusted' or 'underlying' means in this report, or who is vouching for the numbers in the highlights. For every headline figure in the highlights, chairman's statement and CEO review of an uploaded annual report, states whether it sits inside or outside the audited statements and what was added or removed versus the nearest audited number. Produces a boundary table, the list of figures outside the boundary, and a plain-English summary of who is vouching for what. Educational, not financial advice.

中文简介正在准备中。当前显示原文说明。

Surface the hidden assumptions a plan or belief rests on, then test what happens when each one is wrong. Use when asked what am I assuming here, check my assumptions, what if I'm wrong about, or stress-test my thinking. Produces the unstated assumptions your conclusion depends on (ranked by how load-bearing they are), a flip of each to see which one breaking would change everything, and the cheapest way to check the riskiest ones — because the assumption you didn't know you were making is what sinks plans.

中文简介正在准备中。当前显示原文说明。

Audit the beneficiary designations that quietly override wills — the account-by-account sweep, the life-event triggers that make them stale, and the coordination check against actual intentions. Use when asked check my beneficiaries, does my 401k go to my ex, do beneficiary forms beat a will, or what should I update after marriage/divorce/a birth. Produces the account sweep list, the stale-designation red flags, the intent-vs-paperwork comparison table, and the update checklist with the verify-in-writing step.

中文简介正在准备中。当前显示原文说明。

Write a specification section that a contractor can price accurately and a site can build from — performance stated, products defined, workmanship and tolerances given, and the coordination with the drawings made explicit. Use when asked to write a specification, spec a material or system, prepare an NBS-style section, or when a specification produced wildly different tender prices. Produces the scope and interface definition, the performance requirements, the product or system definition, execution and tolerance requirements, and the submittals and testing schedule.

中文简介正在准备中。当前显示原文说明。

Audit a content library, docs site, or blog for AI-generated filler that's eroding trust and search performance — and triage what to fix, rewrite, or delete. Use when asked to find slop in a content library, audit AI-written content quality, explain why content engagement or rankings dropped after scaling with AI, or set a quality bar for AI-assisted publishing. Produces an audited inventory with per-piece verdicts, the detection signals used, a triage plan, and a publishing quality gate that prevents recurrence. For a single article's AI-citability use aeo-optimizer; for the strategy itself use content-calendar or seo-content-brief.

中文简介正在准备中。当前显示原文说明。

Generate a WCAG 2.2 accessibility audit checklist and remediation suggestions for any UI or design. Use when asked to audit for accessibility, check WCAG compliance, review a design for a11y issues, or create an accessibility remediation plan. Produces a prioritised checklist with pass/fail assessments and specific fixes.

中文简介正在准备中。当前显示原文说明。

Audit whether AI agents can actually use your product — docs, APIs, onboarding, errors, and discoverability, evaluated from a non-human user's perspective. Use when asked if a product is agent-ready, to audit a site or API for AI usability, to prepare for agentic traffic, or when agents keep failing against your product. Produces a scored readiness report with per-surface findings and a prioritised fix list. For optimising a single article for AI citation use aeo-optimizer; for designing the MCP server itself use mcp-server-spec.

中文简介正在准备中。当前显示原文说明。

Audit whether the organisation's AI spend actually paid — measured against baselines, not vendor math or vibes. Use when a CFO asks what the AI tools returned, when renewing AI contracts, when consolidating overlapping AI subscriptions, or to build the measurement plan before the next spend. Produces an ROI audit with per-tool verdicts (keep/consolidate/cut), the honest-measurement method behind each number, and a baseline plan for whatever can't be scored yet. To forecast ROI before an investment use roi-estimator; this skill measures what already happened.

中文简介正在准备中。当前显示原文说明。

Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system, assessing algorithmic risk, auditing a model for bias, or producing a responsible AI impact assessment. Produces a structured ethics review covering fairness, transparency, privacy, safety, accountability, and societal impact with a risk tier score, pre-deployment checklist, and prioritised mitigations.

中文简介正在准备中。当前显示原文说明。

Analyse a finished A/B test and write the readout — the result, whether it's statistically and practically significant, what it means, and the ship/no-ship call. Use when asked to analyse experiment results, write an A/B test readout, interpret test data, or decide whether to ship a variant. Produces a clear verdict with the lift and confidence, segment cuts, the risks (peeking, novelty, sample), and a recommendation. Distinct from planning a test — this reads results.

中文简介正在准备中。当前显示原文说明。

Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real. Use when asked how do I test my AI agent, make my automation reliable, my agent works sometimes, or how do I trust an AI workflow in production. Produces a map of where the agent can fail (bad input, hallucination, wrong tool call, edge cases, silent errors), the checks that catch each (validation, evals on real cases, human-in-the-loop gates, monitoring), a right-sized reliability plan scaled to the stakes, and a rollout that earns trust incrementally.

中文简介正在准备中。当前显示原文说明。

Simulate the acquirer's diligence team hunting for reasons to cut your price — their internal red-flags memo with a price-chip estimate per finding. Use when asked to red-team my company before a sale, how will an acquirer attack our valuation, pre-diligence audit, or what will DD find. Produces the acquirer's internal memo (revenue quality, key-person, tech debt, concentration, legal) and a debrief on which flags are fixable before a process.

中文简介正在准备中。当前显示原文说明。

Optimize an article for Answer Engine Optimization (AEO) so AI engines like ChatGPT, Perplexity, and Claude can extract, quote, and cite it. Use when asked to AEO-optimize, make content AI-readable, improve AI citation chances, or adapt an article for answer engines. Produces an AEO-optimised rewrite with question headings, 50–80 word answer capsules, a paragraph-length audit, and flagged trust signals.

中文简介正在准备中。当前显示原文说明。