「diff」の検索結果

Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.

日本語の概要は準備中です。原文の説明を表示しています。

Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202

日本語の概要は準備中です。原文の説明を表示しています。

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa

日本語の概要は準備中です。原文の説明を表示しています。

Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS.

日本語の概要は準備中です。原文の説明を表示しています。

You extend the browser to give users superpowers. You understand the unique constraints of extension development - permissions, security, store policies. You build extensions that people install and actually use daily. You know the difference between a toy and a tool.

日本語の概要は準備中です。原文の説明を表示しています。

You are an expert in the interface between LLMs and the outside world. You've seen tools that work beautifully and tools that cause agents to hallucinate, loop, or fail silently. The difference is almost always in the design, not the implementation.

日本語の概要は準備中です。原文の説明を表示しています。

Tests APIs for injection vulnerabilities including SQL injection, NoSQL injection, OS command injection, LDAP injection, and Server-Side Request Forgery (SSRF) through API parameters, headers, and request bodies. The tester crafts malicious payloads targeting different backend technologies and injection contexts to extract data, execute commands, or access internal services. Maps to OWASP API8:2023 Security Misconfiguration and API7:2023 SSRF. Activates for requests involving API injection te...

日本語の概要は準備中です。原文の説明を表示しています。

Review PRs: diffs, inline comments via gh or REST.

日本語の概要は準備中です。原文の説明を表示しています。

Use whenever SQL, ORM/jOOQ code, schema or migrations, indexes, N+1, or database load are in play, even without the word "review" — delegates the performance review of the current branch diff to the sql-performance-reviewer agent.

日本語の概要は準備中です。原文の説明を表示しています。

Use when user has ADHD or attention differences — tracks current task, catches conversation drift, and nudges back on topic without judgment or guilt.

日本語の概要は準備中です。原文の説明を表示しています。

Kelly's market-intelligence desk (Busabase App-in-Skill). Merges passive competitor monitoring (Radar), agent-run deep research with approved briefs and cited reports (Research), and keyword/topic demand signals (Trends) over one Busabase-backed snapshot, watchlist, and review model. Use when the user invokes $kelly-radar or /kelly-radar, or asks for competitor monitoring, market intelligence, market research, research reports, trends, rising keywords, pricing changes, product launches, changelog diffs, competitor reviews, funding or hiring news, or opportunity triage.

日本語の概要は準備中です。原文の説明を表示しています。

Ask the local Claude CLI to review plans, diffs, full codebases, completed work, and exploit chains when the user explicitly wants a Claude second opinion.

日本語の概要は準備中です。原文の説明を表示しています。

Visual regression: production-level screenshots, diff thresholds, anti-flake. Use when implementing, reviewing or testing visual regression for React, Vite, Next.js or Perfect_AI projects.

日本語の概要は準備中です。原文の説明を表示しています。

Check your work with a verification subagent. Spawns a verifier that reviews diffs, runs builds and tests, and evaluates correctness. Use when asked to "check work", "verify changes", "self-verify", "/check", "/verify", "/check-work", or "/self-verify".

日本語の概要は準備中です。原文の説明を表示しています。

Safely update an npm package by checking npmjs.com for the latest version, reading release notes, and handling minor vs major upgrades differently. For minor updates, just do it. For major updates, find the upgrade guide, validate breaking changes, and produce a detailed migration report.

日本語の概要は準備中です。原文の説明を表示しています。

Required reading before writing any HogQL/SQL or calling execute-sql against PostHog. Use whenever the user wants to search, find, or do complex aggregations PostHog entities (insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, data warehouse, persons, etc.) and query analytics data (trends, funnels, retention, lifecycle, paths, stickiness, web analytics, error tracking, logs, sessions, LLM traces). Covers HogQL syntax differences from ClickHouse SQL, system table schemas (system.*), available functions, query examples, and the schema-discovery workflow.

日本語の概要は準備中です。原文の説明を表示しています。

Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously. Use when onboarding onto a new project, understanding architecture, or investigating a cross-cutting concern.

日本語の概要は準備中です。原文の説明を表示しています。

Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.

日本語の概要は準備中です。原文の説明を表示しています。

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

日本語の概要は準備中です。原文の説明を表示しています。

Copy a feature flag from one PostHog project to one or more target projects in the same organization. Use when the user wants to duplicate a flag, promote a flag from staging to production, sync flags across projects, or replicate a flag configuration in a different workspace. Covers cohort remapping, scheduled-change handling, encrypted payloads, and the safe defaults (disabled in target, no scheduled changes).

日本語の概要は準備中です。原文の説明を表示しています。

Designs genomics experiments so technical nuisance variation (batch, lane, plate, flow cell, operator, reagent lot, processing day) is balanced against the biological variable of interest and therefore estimable rather than confounded, using constrained sample-to-batch assignment (designit, OSAT), the confounder/mediator/collider distinction, and the principle that no post-hoc correction recovers a fully confounded design. Covers detecting hidden batches with surrogate variable analysis, a decision table for downstream correction (ComBat-seq, RUVSeq, SVA) whose execution is deferred to differential-expression/batch-correction, and reproducibility metadata. Use when assigning samples to sequencing batches/lanes/plates, avoiding batch-condition confounding, deciding whether a design is salvageable by correction, choosing a correction method, or estimating the number of hidden batches. For the experimental unit, randomization, and blocking concepts see experimental-design/randomization-blocking.

日本語の概要は準備中です。原文の説明を表示しています。

Meta-analysis / evidence synthesis — pool effect sizes across studies (odds ratios, risk ratios, hazard ratios, mean differences, correlations, GWAS betas) with fixed- or random-effects models, quantify heterogeneity (Q, I², τ²), and build a forest plot. Use when you have results from MULTIPLE studies and need a single pooled estimate, or to synthesize evidence from a systematic review / multiple GWAS / replicated experiments. Handles the error-prone effect-size + standard-error preparation (converting OR/HR/CI, two-group means±SD, proportions, and correlations into the (effect, SE) the pooling step needs).

日本語の概要は準備中です。原文の説明を表示しています。

Computes sample size and power for clinical trials including continuous, binary, and time-to-event endpoints; superiority, non-inferiority, and equivalence designs; FDA 2016 non-inferiority margin selection with M1/M2 framework; Schoenfeld 1981 and Lakatos 1988 for survival; Schuirmann TOST and 80-125% bioequivalence; minimum clinically important difference (MCID) vs δ distinction. Use when justifying trial size in protocol or SAP per CONSORT 2025 item 7.

日本語の概要は準備中です。原文の説明を表示しています。

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.

日本語の概要は準備中です。原文の説明を表示しています。