Results for “rspec”

Front-door router for the product-shots ecosystem. Clarifies underspecified visual creation requests through a 4-stage state machine, injects platform visual DNA (Amazon + 7 social platforms) and industry visual DNA (7 industries), enforces a unified Negative Constraints prompt patch, then routes to one of five downstream business skills (product-shots-main-image / product-shots-detail-page / product-shots-multi-angle / product-shots-ad-creative / product-shots-social-post). Use when the user says "I need a product image", "design something for my listing", "I need content for Instagram", "make an ad for me", "make a cover image", "create a post", "做一个商品图", "帮我做个详情页", "帮我做个广告图", "做一个社媒图", "做一张图", "帮我设计", "做个封面" — i.e. any underspecified visual creation request that needs clarification before generation. This is the intent-routing hub of the product-shots ecosystem.

The English summary is being prepared. Showing the original description.

Paul Graham的思维框架与表达方式。基于200+篇essays、12个播客/访谈、 Twitter/X分析、7位核心批评者视角和完整人生时间线的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用PG的视角分析创业、写作、产品和人生选择。 当用户提到「用PG的视角」「Paul Graham会怎么看」「PG模式」「paul graham perspective」时使用。 即使用户只是说「帮我用PG的角度想想」「如果PG会怎么做」「切换到PG」也应触发。

The English summary is being prepared. Showing the original description.

Understanding and integrating multiple perspectives in historical analysis. Covers historical empathy (reconstructing how past actors understood their world), analyzing events from multiple viewpoints, constructing inclusive narratives that recover marginalized voices, and avoiding presentism (the imposition of contemporary values on past societies). Use when interpreting historical actors' motivations, assessing whose stories are told and whose are silenced, or guarding against anachronistic judgment.

The English summary is being prepared. Showing the original description.

BDD-Driven Mathematical Content Verification Skill Combines Behavior-Driven Development with mathematical formula extraction, verification, and transformation using: - Cucumber/Gherkin for specification - RSpec for implementation verification - mathpix-gem for LaTeX/mathematical content extraction - Pattern matching on syntax trees for formula validation Enables iterative discovery and verification of mathematical properties through executable specifications.

The English summary is being prepared. Showing the original description.

Review a code change for correctness-maintainability defects not owned by a narrower security/performance/accessibility perspective. Use for an independent quality perspective on a defined change set.

The English summary is being prepared. Showing the original description.

Multi-agent adversarial code review. Spawns three reviewer subagents (Auditor, Adversary, Pragmatist) on a single model, runs a cross-examination round, then deterministically synthesizes a single ranked report. Use this for non-trivial PRs, security-sensitive changes, refactors that touch many files, or any change where one perspective has obvious blind spots. Trigger phrases include "adverse review", "adversarial review", "multi-perspective review", "review my changes from multiple angles", "panel review". NOT suitable for trivial diffs (typos, dependency bumps, formatting).

The English summary is being prepared. Showing the original description.

Ask the minimum clarifying questions before implementation when requirements are ambiguous or missing crucial details

The English summary is being prepared. Showing the original description.

Polish screen recordings with Recordly (open-source Screen Studio alternative) — auto-zooms, cursor animations, webcam overlays, styled backgrounds, timeline editing. Also includes Slant: browser-based 3D perspective renderer with 12 animation presets and MP4/GIF export. Triggers on screen recording, demo video, Recordly, screen capture polish, product walkthrough, 3D perspective, Slant.

The English summary is being prepared. Showing the original description.

4人の異なる専門家ペルソナ（20年ベテランエンジニア、TDDエキスパート、Clean Codeエキスパート、バグハンター）で ソースコードを批判的にレビューするスキル。設計判断、テスト容易性、可読性、バグ検出の観点から コードの問題を検出し、改善提案を行う。Python/JavaScriptに対しては追加のチェックポイントを適用。 バグハンターは状態遷移、例外パス、依存関係、非同期競合に特化し、本番環境での問題を事前に検出する。 Use when reviewing source code from multiple expert perspectives to find design flaws, testability issues, code quality problems, and runtime bugs. Triggers: "critical code review", "multi-persona code review", "expert code review", "code quality assessment", "find bugs".

The English summary is being prepared. Showing the original description.

エラーや例外シナリオを顧客体験(CX)の観点で体系的に分析し、改善優先度を付ける スキル。6軸評価（影響度・頻度・復旧容易性・メッセージ品質・感情的影響・ ビジネスコスト）でスコアリングし、Impact vs Effort マトリクスで改善施策を 優先順位付けする。Use when analyzing error scenarios from customer experience perspective, evaluating error message quality, prioritizing error UX improvements, or creating CX-focused error analysis reports. Triggers: "CXエラー分析", "error experience", "エラーUX改善", "customer experience error", "エラーメッセージ品質", "error scenario analysis", "顧客体験エラー評価"

The English summary is being prepared. Showing the original description.

6つの専門レビュアーロールを並列実行し、consensusLevel（複数ロールの合意度）と Tech Lead レポート（top3指摘・blindSpots・consensusSummary）で結果を統合する マルチエージェントレビュー entry skill。 Parallel multi-role review with consensus scoring (consensusLevel) and Tech Lead report. Use when a major release needs exhaustive multi-angle review, or when a single-perspective review is not enough and you want confidence that no reviewer angle was missed（重要リリース前の網羅レビュー・多視点の確証が 欲しいとき）。

The English summary is being prepared. Showing the original description.

Webサービスを攻撃者目線でレビューし、実在する攻撃ベクターに基づいて脆弱性を発見・整理するスキル。 静的レビューと実証検証は別サブエージェントに委任し、メインセッションは両者の結果を 査読・比較して次アクションを判断する。Medium以上の実証済み所見、または実証未了でも 優先度が高い所見がある場合はメインセッションで対策プランの作成を促す。 Trigger: 脆弱性レビュー, セキュリティ診断, 攻撃者目線レビュー, ペネトレーション観点, /dev:attack-surface-review, attack surface review, pentest perspective, exploit path

The English summary is being prepared. Showing the original description.

孙宇晨(Justin Sun)的思维框架与表达方式。基于21,829条推文（14,418 EN + 7,411 ZH）、 1本自传《这世界既残酷也温柔》、155集音频课《财富自由革命之路》(~18小时)、 40+篇深度采访与调查报道、2篇核心中文长访谈（花总86分钟+晚点76分钟）、 2期英文深度播客（Bankless 90分钟+UpOnly 60分钟）、1段太空飞行纪录， 提炼14个核心心智模型、18条决策启发式和完整的表达DNA。 用途：作为思维顾问，用孙宇晨的视角分析加密行业、审视商业决策、提供反馈。 当用户提到「用孙宇晨的视角」「Justin Sun会怎么看」「孙哥模式」「sun perspective」时使用。 即使用户只是说「帮我用孙宇晨的角度想想」「如果Justin Sun会怎么做」「切换到孙哥」也应触发。

The English summary is being prepared. Showing the original description.

Requests a code review from a separate agent after implementation or before merging. It provides the change summary, requirements, and commit range, then guides follow-up work according to the severity of the findings.

• Reviewing a major feature after implementation
• Checking changes before merging
• Getting another perspective on a complex bug fix

Compare ambiguous choices through four advisory perspectives covering long-term consequences, assumptions, practical execution, and failure risks. The skill presents each position, highlights the strongest disagreement, and combines the findings into a recommendation for the decision.

• Deciding whether to release now or wait for improvements
• Comparing a gradual rollout with a full rollout
• Choosing between reducing scope and retaining broader goals

Test an app from the perspective of a frustrated, less technical user. Find confusing steps and barriers, separate actionable usability problems from personal complaints, and produce screenshots, suggested fixes, and prioritized tickets.

• Reviewing usability before a launch or demo
• Checking the experience of a new user
• Finding friction in signup and subscription flows

Coordinate large migrations, reviews, or research tasks across multiple agents. Keep plans and intermediate results in scripts and files, challenge findings with independent checks, and integrate verified work in controlled batches.

• Splitting large file migrations across agents
• Testing audit findings against counter-evidence
• Cross-checking research from different perspectives

Review a product or business plan from a founder’s perspective. Challenge assumptions and reconsider the problem, then explore whether to expand the scope, add selected ideas, keep it fixed, or reduce it to essentials.

• Reconsidering a product plan’s assumptions
• Exploring a more ambitious product direction
• Choosing which scope expansions to include

Clarify an unclear request through one question at a time, with the agent sharing its best guess for each answer. Produce a user-confirmed statement covering the desired outcome, audience, timing, success criteria, constraints, and exclusions.

• Clarifying the purpose behind a vague request
• Identifying intended users and success criteria
• Choosing priorities when values conflict

Work through complex or costly decisions with a structured process covering context, research, competing perspectives, planning, execution, and critical review. The workflow adapts its depth to the task and produces recommendations with tradeoffs, risks, and success criteria.

• Comparing system architecture options
• Planning changes across multiple systems
• Rechecking assumptions in an ambiguous request

Create HTML slide decks for humanities lectures and research presentations, organizing sources, arguments, and evidence. A coordinated navy and warm-yellow template gives the slides a calm, scholarly appearance.

• Preparing slides for a humanities lecture
• Presenting research in a graduate seminar
• Turning a research synthesis into a scholarly deck

Review interface designs with a senior designer's perspective. It scores each design dimension from zero to ten, explains what a top score requires, and flags generic AI-generated design patterns before UI changes are merged.

• Reviewing UI work before merging changes
• Comparing design scores across review dimensions
• Identifying generic AI-generated design patterns

Research a topic across multiple web sources before writing articles, reports, or presentations. Gather facts, examples, and expert views, then check current information, competing perspectives, and limitations to build a well-supported understanding.

• Researching evidence before writing an article
• Gathering data and examples for presentation slides
• Comparing technologies and their limitations

Define reusable reasoning and decision patterns for agents, embed them in executable workflows, and review their performance. Share successful approaches, including conditional decision trees, stepwise problem solving, analogies, and evaluation from multiple perspectives.

• Define conditional rules for agent decisions
• Turn problem-solving steps into executable workflows
• Solve new problems using similar past cases