Skills directory · page 59

Comprehensive PM resume review and tailoring against 10 best practices including XYZ+S formula, keyword optimization, job-specific tailoring, and structure. Use when reviewing a PM resume, preparing for job applications, or improving resume impact.

Review Paperclip stories for a feature or change using the Storybook catalog, production source, and existing browser tests. Report component, mock, interaction, and visual evidence separately.

Open other Claude Code sessions in Rex terminal panes or tabs and drive them: launch claude in a directory, answer the workspace trust dialog, send prompts, wait for each turn by its reported status (working, done, blocked on a permission prompt), read the screen, press keys and close the pane. Use when running inside the Rex terminal (REX_SESSION is set, TERM_PROGRAM=rex) and the user wants to start, delegate to, test in, watch or control a second Claude Code session side by side, for example to test a setting or permission in a fresh session, run a task in parallel in another pane, or check what another Claude pane is doing.

Use when an RFP, RFI, RFQ or security or vendor questionnaire arrives. Parses mandatory vs weighted requirements with rfp_parser.py, drafts proof-point answers with response_drafter.py and estimates win chance with winrate_predictor.py.

Use for ISO 14971 medical device risk management: hazard analysis, FMEA, fault trees, risk controls, benefit-risk or residual risk. Runs fmea_analyzer.py and risk_matrix_calculator.py.

Senior Risk Management specialist for medical device companies implementing ISO 14971 risk management throughout product lifecycle. Provides risk analysis, risk evaluation, risk control, and post-production information analysis. Use for risk management planning, risk assessments, risk control verification, and risk management file maintenance.

Write roadmap narratives, release notes, changelogs, stakeholder updates. Use whenever the user explains plans to execs, engineers or customers.

Roast an idea: a 5-angle panel (Critic, Champion, Analyst, Investigator, Customer) attacks it, then a Judge returns one GO / RESHAPE / KILL verdict with the cheapest test to de-risk it. Use whenever the user wants to pressure-test or validate a business idea, asks for a brutal second opinion before building, asks is this a good idea, says convene the panel, or runs /roast.

Technical SEO auditor and fixer. Runs Lighthouse/PageSpeed audits on websites or local dev servers, analyzes SEO/performance/accessibility scores, and automatically implements fixes for meta tags, structured data, Core Web Vitals, and accessibility issues.

Baixa o folheto do Roldão Atacadista da praça São Paulo (SP), lendo a página de ofertas do site. Use quando o usuário mencionar "baixar encartes Roldão", "encartes Roldao" ou colar a URL roldao.com.br/ofertas/.

Reproduces failures, traces causes, and verifies behavior with meaningful tests and explicit evidence. Activate when the user invokes Rook by name or assigns this persona; the specialty alone does not trigger it.

Build a decision-grade Pareto for downtime, defects, complaints or delays - with unit-of-measure discipline, category hygiene, exposure normalization and a follow-up metric. Use when the user mentions pareto analysis, kök neden, duruş analizi, downtime, arıza analizi, defect ranking, şikayet analizi, 80/20 analysis. Differentiator - treats the Pareto as the start of a causal investigation, not a bar chart deliverable.

Compile a proven agent skill (a SKILL.md plus references) into a deterministic pipeline that runs without an LLM in the loop, then serve it back to Claude as an MCP tool. Use when: rote, compile this skill, turn this skill into a workflow, make this skill deterministic, make this skill cheaper or faster, harden this skill for production, run this skill as a background job.

Write idiomatic Ruby code with metaprogramming, Rails patterns, and performance optimization. Specializes in Ruby on Rails, gem development, and testing frameworks.

Use when auditing, pruning, or cleaning up an agent's entire existing rule set in one bulk pass across every rule source at once (all CLAUDE.md files, all memory entries, AGENTS.md, ADRs, COORDINATION). This is whole-corpus hygiene; NOT for adding, editing, or fixing an individual rule (just edit that file directly).

スキルをスキャンしてドメイン横断的な原則を抽出し、ルールに蒸留する——既存のルールファイルへの追記、修正、または新規作成

Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files. Use when the same principle keeps recurring across skills and belongs in a rule file instead.

Use when a graded managed agent should run on a schedule, on an event trigger or on demand ('run it every morning'). Validates cron with cron_validator.py and builds the deployment with deployment_builder.py.

Use when a service needs runbooks for deploy, incident response, maintenance or rollback, before launch. Generates them per environment with runbook_generator.py.

Plan and build production-ready Rust CLI tools using clap for argument parsing, with subcommands, config file support, colored output, and proper error handling. Uses interview-driven planning to clarify commands, input/output formats, and distribution strategy before writing any code.

Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.

Patrones idiomáticos de Rust, ownership, manejo de errores, traits, concurrencia y buenas prácticas para construir aplicaciones seguras y eficientes.

慣用的なRustパターン、所有権、エラー処理、トレイト、並行処理、および安全で高性能なアプリケーションを構築するためのベストプラクティス。

Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.

Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications. Use when writing or reviewing Rust code and ownership, error handling, traits, or concurrency is in question.

Master Rust 1.75+ with modern async patterns, advanced type system features, and production-ready systems programming.

Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.

Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology. Use when writing Rust tests — unit, integration, async, property-based, or coverage.

Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.

Patrones de pruebas en Rust incluyendo pruebas unitarias, de integración, async, basadas en propiedades, mocking y cobertura. Sigue la metodología TDD.

単体テスト、統合テスト、非同期テスト、プロパティベーステスト、モック、カバレッジを含むRustテストパターン。TDD方法論に従う。

Use when someone shares SaaS revenue or customer numbers, or asks about ARR, MRR, churn, LTV, CAC, NRR or how their SaaS is doing. Computes metrics with metrics_calculator.py, quick ratio and unit economics.

Design and implement multi-tenant SaaS architectures with row-level security, tenant-scoped queries, shared-schema isolation, and safe cross-tenant admin patterns in PostgreSQL and TypeScript.

Use when starting a new SaaS app with auth, database, Stripe billing and a dashboard (Next.js App Router, TypeScript, Tailwind, shadcn/ui, Drizzle). Bootstraps it with project_bootstrapper.py.

Manage SABnzbd queues, history, NZBs, priorities, limits, RSS feeds, schedules, and server state through sabx.

Refactor JavaScript/TypeScript or Python code without changing behavior — extract functions, rename, split large files, remove duplication, modernize syntax, add types — with tests as a safety net. Use whenever the user asks to refactor, clean up, simplify, "rapikan kode", restructure, migrate JS to TS, add type hints, or reduce complexity.

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Guard against destructive operations with three modes: Careful intercepts dangerous commands (rm -rf, git push --force, DROP TABLE) for confirmation, Freeze locks writes to one directory, and Guard combines both. Advisory: the agent applies these rules itself; no hook ships with it. Use when working on production systems, running agents autonomously, restricting edits to a directory, or during migrations, deploys, and data changes.

Size or audit safety stock with assumption checks - the z*sigma*sqrt(LT) formula plus an empirical stress test of what it actually delivers (cycle service vs fill rate) per variability class. Use when the user mentions safety stock, emniyet stoku, emniyet stoğu, reorder point, service level, stok seviyesi belirleme. Differentiator - refuses to hand back a number without validating the demand-distribution assumptions behind it.

Explains system design, evaluates tradeoffs, and records architecture decisions and useful documentation. Activate when the user invokes Sage by name or assigns this persona; the specialty alone does not trigger it.

Research market rates, build negotiation strategy, and create counter-offer scripts. Use when the user mentions salary negotiation, counter offer, compensation discussion, or pay raise conversation.

Use for pre-sales work: RFP coverage gaps, competitive feature matrices or planning and scoring a proof of concept. Runs rfp_response_analyzer.py, competitive_matrix_builder.py and poc_planner.py.

Expert patterns for Salesforce platform development including Lightning Web Components (LWC), Apex triggers and classes, REST/Bulk APIs, Connected Apps, and Salesforce DX with scratch orgs and 2nd generation packages (2GP). Use when: salesforce, sfdc, apex, lwc, lightning web components.

Reference BASIC-tier skill used as a fixture by skill-tester. Counts words and characters and applies basic text transformations. Use when validating skill-tester itself or when you need a minimal, known-good skill layout to copy. Not a production skill.

Multi-agent adversarial verification: two independent reviewers with the same rubric must both pass before output ships, with a fix-and-re-review convergence loop and human escalation cap. Use when gating publishing, production deploys, compliance or brand-sensitive content, or hallucination-prone claims before they ship.

収束ループを持つマルチエージェント敵対的検証。2つの独立したレビューエージェントが両方合格して初めて出力を出荷できます。

Baixa todos os encartes da semana do Mercadinhos Sao Luiz (loja 355), todas as paginas. Use quando o usuario mencionar "baixar encartes Sao Luiz", "encartes Sao Luiz", "encartes Mercadinhos Sao Luiz", ou colar a URL mercadinhossaoluiz.com.br/loja/355/encartes.

Static Application Security Testing (SAST) tool setup, configuration, and custom rule creation for comprehensive security scanning across multiple programming languages.