发现 Skills

Development workflow, quality gates, and disciplined delivery.

Set up and use Bitwarden CLI (bw). Use when installing the CLI, unlocking vault, or reading/generating secrets via bw. Handles session management with BW_SESSION.

Enable agents and skills to challenge users for fresh two-factor authentication proof (TOTP or YubiKey) before executing sensitive actions. Use this for identity verification in approval workflows - deploy commands, financial operations, data access, admin operations, and change control.

Créer ou mettre à jour un fichier de test unitaire Vitest pour une fonction TypeScript donnée, namespacée via @scripts (namespace.function), en respectant les conventions de test du projet (ExpectType strict, compatibilité pipe, pas de helpers partagés).

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

Rulesync CLI tool documentation - unified AI rule file management for various AI coding tools

Parallel code search with Warp-Grep MCP. Use for codebase discovery, understanding how things work, data flow analysis, or when the user asks "how does X work" about the codebase.

Build structured datasets from academic papers. Use when the user wants to extract structured data from scientific literature, traverse citation graphs, search OpenAlex for papers, or create datasets from PDFs for research purposes.

Professional skills and methodology for testing IDOR (Insecure Direct Object Reference)

Critical review board for plans, proposals, and research findings. Deploys up to 6 reviewers (2 core + 4 on-demand) including Seneca, Codex, Scrutator, Novator, Librarius, and Censor. The orchestrator selects which optional subagents to launch based on review content. Use when the user asks to "think hard", "ultrathink", perform critical review, validate a plan, or before committing to a complex technical decision. Also triggers on large-scope tasks and PRD reviews. Also operates in brainstorm mode for problem exploration — generates and critiques solution approaches. Autonomous — runs without user interaction, presents combined findings.

Expert guidance for writing TypeScript code following modern best practices, targeting TypeScript 5.x and ES2022. Use this skill when writing, reviewing, or refactoring TypeScript code in any .ts or .tsx file. Provides comprehensive guidelines on type system usage, architecture patterns, security, testing, and performance.

Advanced semantic vocabulary and architectural patterns for the OCTAVE format. Requires octave-literacy to be loaded first.

Functional mythological compression for OCTAVE documents. Semantic shorthand for LLM audiences, not prose decoration

Plans LoRaWAN network deployments with gateway placement, coverage analysis, and device provisioning

React Three Fiber asset loading - useGLTF, useLoader, Suspense patterns, preloading. Use when loading 3D models, textures, HDR environments, or managing loading states.

Guide on deployment with Fly.io, multi-region setup, and CI/CD for Epic Stack

Multi-model brainstorming to challenge assumptions and reach consensus. Use when needing to double-check work, validate plans, or get diverse perspectives on decisions. Invokes Claude Opus 4.6, GPT-5.3-Codex, and Gemini 3 Pro with randomized roles to debate and find common ground.

Comprehensive knowledge system for addiction recovery environments, supporting both residential and outpatient (IOP/PHP) patients. Expert in evidence-based treatment modalities (CBT, DBT, MI, EMDR, MAT), recovery resources, coping strategies, crisis intervention, family systems, and holistic wellness. Activate on "rehab", "addiction recovery", "substance abuse", "treatment center", "IOP", "PHP", "detox", "sobriety support", "MAT", "Suboxone", "methadone", "12 step", "SMART Recovery". NOT for prescribing medications (consult medical professionals), emergency overdose situations (call 911), or replacing licensed counselors/therapists.

Parse and consolidate monthly Net Operating Revenue (NOR/ROL) from all 8 Nuvini portfolio companies into a unified dashboard. Detects uploaded files in Drive, normalizes revenue figures, computes MoM and YoY growth, aggregates at portfolio level, and alerts on declining companies. Triggers on: NOR ingest, revenue dashboard, portfolio revenue, ROL mensal, portfolio performance, receita líquida.

Master QA orchestrator: project-agnostic opus-powered autonomous agent. Detects project, checks for existing /qa-{project} skill (delegates if found), or runs full discovery + QA cycle from scratch and generates the skill for next time. Manages its own task list. Only stops for destructive actions. Delivers a fully working app. Triggers on: qa cycle, full qa, run qa, continuous qa, qa pipeline.

Targeted back-translation on flagged spans only (`<unsure>` / `<sense>` / reviewer-flagged). Scores semantic drift 1–5 with in-context back-translation (no false positives from isolated 3-word snippets). Emits diffs for `translate-translate` pass 2. Never back-translates the whole document.

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

Set up and test universal links for iOS using setup-safari