Revisão de segurança em nível de código-fonte focada exclusivamente em vetores de injeção e técnicas de bypass de sanitização. Ative ao receber código para auditoria de segurança ou ao investigar vulnerabilidades de injeção em qualquer linguagem/framework.
While you're out of office, watches a group chat and answers questions from your local knowledge docs (clearly marked AI-generated), logs anything it can't answer for later, and pings you on Teams if its setup is incomplete.
YC Office Hours — two modes. Startup mode: six forcing questions that expose
demand reality, status quo, desperate specificity, narrowest wedge, observation,
and future-fit. Builder mode: design thinking brainstorming for side projects,
hackathons, learning, and open source. Saves a design doc.
Use when asked to "brainstorm this", "I have an idea", "help me think through
this", "office hours", or "is this worth building".
Proactively suggest when the user describes a new product idea or is exploring
whether something is worth building — before any code is written.
Use before /plan-ceo-review or /plan-eng-review.
Standard operating runbook for rapid environment restoration after an OS wipe or new hardware setup. Restores git credentials, clones repositories via HTTPS/gh, cleans cache debt, boots local Sentinel daemons, and verifies zero-cost global deployments.
GitHub repository operations, automation, and management. Issue triage, PR management, CI/CD operations, release management, and security monitoring using the gh CLI. Use when the user wants to manage GitHub issues, PRs, CI status, releases, contributors, stale items, or any GitHub operational task beyond simple git commands.
Skill for autonomous agents. Secure & private P2P messaging (sidechannels), sparse state/data + contracts, and optional value transfer. For a true agentic internet.
Create, edit, reverse-decompile, and export presentations using the open PPTD format and native pptd compiler. For every PPT task, default deliverables are BOTH (1) a self-contained PPTD project folder (deck.pptd manifest + pages/*.page) and (2) a locally compiled native .pptx with vector shapes, connector arrows, LaTeX math formulas, speaker notes, and native tables. Completely offline — zero dependency on browser automation or cloud logins.
Use when installing Anthropic's Claude Science on a geo-blocked machine (e.g. China) or running it without a Claude account. Downloads the binary from the unblocked downloads.claude.ai CDN, sets up the claude-science-api-bridge local proxy to route requests to ANY OpenAI- or Anthropic-compatible API (Volcengine, DeepSeek, Kimi, Zhipu, OpenAI, local Ollama/vLLM), and applies a no-login patch so no Claude Pro/Max subscription is required.
Terminal security analysis for shell environments. This skill should be used when checking commands for supply-chain attacks before execution, scanning repositories for hidden content or config poisoning, scoring URLs for homograph attacks, setting up AI tool protection, inspecting Python package artifacts, governing untrusted tasks or Web3 commands, auditing browser extensions, creating provenance receipts, downloading and executing scripts safely, investigating why tirith blocked a command, managing trusted patterns, running security audits, configuring MCP gateway proxies, or working with threat intelligence databases. Also use when the user mentions "tirith", "pipe-to-shell", "homograph", "ANSI injection", "zero-width", "punycode", "terminal security", "shell hook", "cloaking detection", "supply chain attack", "bidi override", "invisible unicode", or "config poisoning". Even if the user does not explicitly name tirith, use this skill when they ask about protecting shell environments, intercepting dangerous commands, or hardening AI agent tool execution.
YC Office Hours — two modes. Startup mode: six forcing questions that expose
demand reality, status quo, desperate specificity, narrowest wedge, observation,
and future-fit. Builder mode: design thinking brainstorming for side projects,
hackathons, learning, and open source. Saves a design doc.
Use when asked to "brainstorm this", "I have an idea", "help me think through
this", "office hours", or "is this worth building".
Proactively suggest when the user describes a new product idea or is exploring
whether something is worth building — before any code is written.
Use before /plan-ceo-review or /plan-eng-review.