Claude Code Skills · page 89

A discipline for running paid media that does not light money on fire. Hypothesis writing for paid spend, channel selection, budget allocation, audience targeting, bid strategy, campaign types, what NOT to spend on, attribution reality, and the failure modes that produce expensive lessons. Triggers on paid media strategy, ad budget allocation, channel selection, paid media plan, audit my Google Ads, audit my Meta Ads, scale paid media, kill underperforming campaign, paid media hypothesis, ad spend strategy, attribution reality, performance marketing strategy. Also triggers when a team is asking how to scale paid media, or whether to add a new channel, or how to reallocate spend across channels.

Diagnose and fix web performance issues including Core Web Vitals (LCP, INP, CLS), bundle size, asset optimization, render performance, and runtime efficiency. Use this skill whenever the user wants to improve page speed, fix Core Web Vitals, optimize assets, reduce bundle size, debug slow renders, or systematically improve a site's performance. Triggers on performance, page speed, Core Web Vitals, LCP, INP, CLS, FID, TTFB, bundle size, code splitting, image optimization, lazy loading, render blocking, slow page, performance audit, Lighthouse score. Also triggers when traffic or conversion is dropping due to perceived slowness.

How to design a content hub that earns topical authority. Pillar topic selection, cluster planning, internal linking architecture, URL structure, pillar and cluster page anatomy, topical authority signals for SEO and AEO/GEO, and the maintenance discipline that distinguishes intentional hubs from accidental orphans. Triggers on pillar content, content hub, topic cluster, topical authority, content architecture, hub and spoke, pillar page, cluster page, content silo, internal linking strategy. Also triggers when a content set is not ranking despite individual piece quality, when a pillar was launched without a cluster, or when content has accumulated without an architecture.

Translate ideas, feature requests, or vague concepts into specific, actionable dev briefs. Use this skill whenever the user has an idea they want to build, a feature to spec out, a bug to file, a project to scope, or needs to convert a half-formed idea into a clear implementation brief. Triggers on I want to add, we should build, can we make, what is the plan for, how do we implement, dev brief, feature spec, PRD, user story, acceptance criteria, scope this, prioritize. Also triggers when the user has a list of things they want to build and needs help converting them into well-formed tasks.

How to actually instrument product analytics correctly. Event taxonomy, property design, naming conventions, schema versioning, identity stitching, funnel design, retention cohorts, North Star metric selection, dashboard hygiene, instrumentation debt, and the failure modes that produce data nobody trusts. Triggers on product analytics setup, event taxonomy, tracking plan, instrumentation, schema versioning, North Star metric, retention cohorts, funnel design, naming conventions, instrument new feature, audit existing analytics, dashboard reconciliation, instrumentation debt, Mixpanel setup, Amplitude setup, PostHog setup, warehouse-native analytics. Also triggers when the team has data but cannot trust it, or when designing instrumentation for a new feature, or when auditing an existing setup that has drifted.

Designing build-your-own product configurators (Tesla-style, custom-pricing, plan-builders) with constraint logic, real-time pricing, validation, and save-and-share mechanics. Honest about infinite-options (decision paralysis), canned-bundles-only (no real customization), and guided-configuration (smart defaults plus meaningful constraints plus escape hatches) patterns. Triggers on configurator design, build-your-own, custom configuration, plan builder, product customizer, configuration tool. Also triggers when users abandon mid-configuration, when configurator conversion is poor, or when a configurator is being scoped for the first time.

How to design and run a programmatic SEO program that produces durable traffic instead of penalty-bait. Data source identification, template design, schema patterns, quality control at scale, internal linking architecture, crawl budget management, AEO/GEO for programmatic pages, refresh discipline, and the make-or-break question of whether pSEO is the right answer for your program at all. Triggers on programmatic SEO, pSEO, scaled content, page generation, template SEO, location pages, comparison pages, directory site, listing site, scaled landing pages, programmatic content. Also triggers when a content set is not ranking, has been hit by an algorithm update, or when a team is considering pSEO as a growth lever.

Run QA testing on a page, feature, or full site at one of three depth tiers (smoke, standard, full). Use this skill whenever the user asks to test a page, audit a site, check for bugs, verify a deploy, run a QA sweep, or review accessibility, performance, or SEO basics. Triggers on test, QA, audit, verify, check, is it working, does it look right, broken, 404, image not loading, post-deploy check, regression test. Also triggers proactively after any significant code change or new page launch where verification matters.

Designing quizzes, personality assessments, and recommendation tools that segment users into actionable categories rather than generating clicks for clicks' sake. Question architecture, scoring algorithms, result categorization, recommendation mapping, lead capture integration. Honest about clickbait-quiz (engagement only), vanity-result (entertaining, not useful), and actionable-segmentation (genuine categorization that drives next-step recommendations) patterns. Triggers on quiz, assessment, personality test, recommendation tool, scorecard, diagnostic, fit evaluator, what-type-of-X-are-you, persona quiz. Also triggers when an audience needs a categorization-driven lead magnet, when a vanity quiz is producing engagement but no qualified leads, or when an assessment is being scoped for the first time.

Build a multi-quarter roadmap from a backlog of ideas, requests, and ongoing initiatives. Use this skill when planning the next quarter, sequencing dependent work, balancing build vs improve vs maintain, or making the case for what NOT to do. Triggers on roadmap, quarterly planning, what should we build next, sequencing, prioritization, OKR planning, capacity planning, what's on the roadmap, plan the year, what to ship next quarter. Also triggers when stakeholders are pulling in different directions and the team needs a defensible plan.

Designing meeting schedulers and booking experiences that qualify leads, set up calls well, and convert at higher rates than a generic Calendly link. Availability logic, qualification gating, prep automation, follow-up sequencing. Honest about any-time-friction (no qualification, just a booking link), interrogation-gate (so much qualification it scares users off), and qualified-fast-path (just enough qualification to set up the call well) patterns. Triggers on scheduler design, meeting booking, demo scheduling, sales call scheduling, calendar tool, booking page, qualification flow. Also triggers when sales team complains about cold demos, when booking conversion is poor, or when scheduler is being scoped for the first time.

Establish a security baseline for a website or web app. Use this skill when configuring HTTPS and TLS, setting security headers, planning secrets management, evaluating CSP policies, doing a basic security audit, or hardening a site before launch. Triggers on security headers, HTTPS, TLS, CSP, content security policy, HSTS, secrets management, vulnerability scan, security audit, harden, OWASP, security baseline. Also triggers when a security review is required for compliance or before going live.

Optimize content and site structure for AI-driven search experiences including AI overviews, large language model citations, generative answer engines, and AI assistants. Use this skill whenever the user wants to optimize for AI search, get cited by language models, appear in AI overviews, build llms.txt, structure content for AI extraction, or future-proof their SEO for the shift from blue links to AI answers. Triggers on AEO, GEO, AI search, AI SEO, AI overview, generative search, LLM optimization, llms.txt, AI citation, ChatGPT search, Perplexity, Gemini, Claude search, AI assistant optimization, answer engine. Also triggers when the user expresses concern about AI eating their organic traffic or wants to understand how to remain visible as search shifts.

>

Experiment-specific - summarize the DARE executor's research design into a clean research_result report, forced to write back into the spec file produced by formated-specs.

Experiment-specific - replaces writing-specs, emits DARE's 4-layer call plan as a clean research_graph schema. Last step forces load formated-result.

loss-1 judge - read a sample's full dialogue and decide whether the user simulator semantically enacted its Policy Card. check-blind.

loss-2 judge - pairwise quality comparison across the n rungs within one topic; decide monotonicity and endpoint separation. check-blind, D1-D5 only.

Strategy: 面对异常的最佳解释推理

Remove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.

Map system architecture to ablatable units for ablation studies

Design ablation studies to isolate component contributions in ML systems

Remove components one by one from a system, record the response/impact of each removal.

Classify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.

Extract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.

Perform bisociation at multiple abstraction levels

Move between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.

Abstract biological principle to design principle. Bridge from biology to engineering.

Compute Risk Priority Number (RPN = S x O x D), classify failure modes into H/M/L action priority per AIAG-VDA tables.

Enumerate all implementation activities from an experiment design

Understand who the user is — background, resources, constraints, and deep motivations. Produces an ActorProfile that informs all downstream decisions. Use this tactic at the start of any crystallization process to build a model of the user's capabilities, limitations, and intent.

Iteratively select maximally informative pairs, execute comparisons, update ratings, and check convergence until ranking stabilizes.

Structured debate protocol that constructs an advocate, deploys critic attacks, and renders a judge verdict through iterative rounds.

Strategy: Progressive pressure escalation — starts with surface-level challenges and escalates to fundamental assumption attacks based on defender confidence decay.

Strategy: Role-play attacks from hostile personas — competing lab researcher, hostile reviewer, funding skeptic, domain outsider — each with distinct attack motivations and blind spots.

Tactic: Construct detailed hostile persona, attack artifact from that persona's perspective, record successful attack paths for aggregation.

Campaign: Logical extreme and boundary testing via reductio ad absurdum and edge-case analysis. Core question: Does this artifact collapse under logical limits and boundary conditions? Methods: Lakatos 1976, Dutilh Novaes 2016, BVA, Flyvbjerg Critical Case, Popper.

Construct the strongest possible case for a rejected candidate or counter-position.

Aggregate multiple ranking ballots into a consensus ranking using a specified social choice method.

SOP: 使用 AHP 层次分析法确定评分维度权重，输出权重向量

SOP: 使用 AHRQ PiCMe 框架对研究 gap 进行 6 维度系统评估

Classify gap root causes using AHRQ 4-reason framework (insufficient info, biased info, inconsistent info, not yet integrated).

Strategy: What-If Analysis, Alternative Futures, and Four Ways of Seeing — generate competing explanations and scenarios to challenge the dominant narrative.

Generate 2-4 divergent scenarios from the same evidence base, each representing a plausible alternative to the artifact's conclusions.

Generate alternative model formulations by relaxing, replacing, or generalizing specific assumptions.

Score each candidate alternative against all criteria to produce a score matrix.

Generate alternatives for every known approach — ensure no approach goes unchallenged.

Systematic structure-mapping from source to target domain (Gentner). Identify relational correspondences and transfer higher-order constraints.

Chain analogies to deeper levels (3-5 layers). Each layer reveals new aspects and insights not visible at the surface.

Extract transferable structural principles from source domains. Orchestrates source identification → abstraction → structural mapping → transfer validation.

Assess analogy depth (surface/structural/systemic). Determines whether an analogy warrants transfer investment.

KAOS-style recursive goal decomposition. AND decomposition for sub-goals that must ALL be satisfied. OR decomposition for alternative paths where any one suffices. Produces a GoalTree (DAG structure).

SOP: 描述和分类无法被现有理论解释的异常现象

Tactic: 归纳/溯因路径——描述异常现象，生成候选解释，按可信度排序

SOP: 设计子问题的最优回答顺序

Challenge industry best practices' hidden assumptions. Deconstruct benchmarks to reveal unexamined constraints.

Search for positive deviants and extract transferable principles using Appreciative Inquiry.

Find positive deviants and reframe the problem from deficit-based to asset-based using Appreciative Inquiry.

Establish acceptability standards through RAND/UCLA Appropriateness Method or Consensus Conference protocols.

Distill the strongest arguments from each perspective through Argument Delphi or Dialectical Delphi methods.

Extract and steel-man the core arguments supporting a given opinion cluster.

Detect annotation artifacts and shortcuts in benchmarks

Understand hard boundaries on the user's research — target venues, methodology preferences, areas to avoid, advisor/team requirements. Not limited to ML/AI — works for any research domain.

Present the GoalTree to the user for confirmation. Ask about reasonableness, missing elements, and priority ordering among sub-goals.

Deep WHY probing inspired by i* Intentionality modeling. Understand the user's motivation, success definition, risk tolerance, innovation preference, independence preference, time urgency, and learning willingness. The most important SOP in actor-profiling — understanding WHY drives everything downstream.

Present obstacles with their severity assessments and proposed mitigations to the user. Ask whether they can accept these obstacles. If unacceptable after 2 rounds, return to present-candidates.

Rate each identified obstacle's difficulty — overcomability, time cost, workaround existence. May optionally use search tools to validate assessments.

Standardize assignee names and identify corporate group affiliations across patent offices

Surface all assumptions, classify by vulnerability (load-bearing × likely-false), validate causal logic. Focus on dangerous assumptions — high load-bearing + non-explicit.

Build assumption dependency graphs and trace cascade failures when root assumptions are invalidated.

Tactic: Surface assumptions, sort by dependency, attack root assumptions first, then trace cascade failures through the dependency graph.

Construct the strongest counter-argument against a specific assumption and propose alternatives.

Challenge each assumption's validity — shared cross-repo SOP

Which assumptions are most fragile? — Vulnerability ranking + impact assessment of experiment assumptions

Measure how much conclusions change when each assumption is negated. Ranks assumptions by their impact on the final result.

Assumption Destruction Campaign — open new solution spaces by negating, reversing, and challenging fundamental assumptions.

Systematically identify all assumptions in a method/model — structural, parametric, distributional, and scope assumptions.

Systematic extraction, challenge, and sensitivity analysis of assumptions underlying a decision to identify load-bearing beliefs.

Systematically extract all assumptions (stated, implicit, boundary, mathematical, practical) from a method or model.

Classic reductio ad absurdum: negate the core claim, derive logical consequences, seek contradiction or absurdity.

One-at-a-time assumption perturbation — extract assumptions, define negations, re-derive conclusions under each negation, measure sensitivity. Identifies which assumptions are load-bearing.

Systematically extract implicit assumptions from methods, frameworks, or arguments. Identifies what is taken for granted without explicit justification.

Compute overall resilience score (0.0-1.0) based on attack results, coverage, and vulnerability severity distribution.

Generate specific attack strategies for a given threat surface, producing concrete probes that can be executed.

Identify and suspend fundamental assumptions via de Bono PO. Systematically negate axioms to reveal hidden solution spaces.

Gather independent ranking ballots from multiple judges or perspectives for a given candidate set.

SOTA Performance Baseline Campaign — 5 strategies for systematically collecting, standardizing, and analyzing performance data across methods. Produces standardized comparison tables, progress curves, and headroom analysis.

Select appropriate baselines for experimental comparison

Produce final structured baseline report integrating all analysis results

Evaluation Methodology Archaeology Campaign — 5 strategies for systematic analysis of AI/ML benchmarks, metrics, and leaderboards. Reveals construct validity issues, saturation, data contamination, and evaluation protocol inconsistencies.

Systematic quality assessment using BetterBench 46-criterion framework — 5 benchmarks, 30 papers, 40 web searches

Identify and negate benchmark assumptions. Deconstruct best practices to reveal hidden constraints and open new spaces.

Identify and catalog all relevant benchmarks in target domain

Systematically scan all known solutions, identify gaps in coverage and unexplored regions of the solution space.

Review legal contracts, NDAs, employment agreements, SaaS terms, and M&A documents. Identifies unfavorable terms, suggests redlines, and compares to market standards. Use for contract analysis, due diligence, or negotiation prep.

Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for /wish.

Convene real AI agents for multi-perspective deliberation on architecture, design, and strategy decisions.

Dispatch docs subagent to audit, generate, and validate documentation against the codebase.

Batch-execute SHIP-ready wishes overnight — pick wishes, orchestrate workers, review PRs, wake up to results.

Dispatch fix subagent for FIX-FIRST gaps from /review, re-review, and escalate after 2 failed loops.