termstack

Find and fix a bug or issue — from any source (GitHub issue, error message, user report, or observed behavior)

Review code changes or a pull request — delegates to specialist agents for code quality, security, performance, and documentation.

Safely refactor code with test coverage as a safety net

Scan changes, commit, push, and create a PR — with confirmation at each step

Test-Driven Development loop — write a failing test first, then the minimum code to pass it, then refactor. Repeat.

Write comprehensive tests for new or changed code. Use automatically when new features are added, functions are created, or behavior is modified.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Master Python asyncio, concurrent programming, and async/await patterns for high-performance applications. Use when building async APIs, concurrent systems, or I/O-bound applications requiring non-blocking operations.

Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export. Use for security audits, compliance documentation, flow tracing, feature ideation, brainstorming, debugging, architecture reviews, or incident post-mortems. Triggers on audit, trace flow, document flow, security review, debug flow, brainstorm, architecture review, post-mortem, incident review.

Test for authentication bypass, broken access control, IDOR, and JWT vulnerabilities. Use when testing authorization controls, when escalating privileges, when manipulating tokens, or when the user needs to verify access control implementation.

When editing, creating, writing content and articles to avoid AI writing patterns ("AI-isms") that make text sound machine-generated. Follow the guidelines in the skill description to audit, rewrite, and summarize changes.

Write, review, and improve blog posts for the Sentry engineering blog following Sentry's specific writing standards, voice, and quality bar. Use this skill whenever someone asks to write a blog post, draft a technical article, review blog content, improve a draft, write a...

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Caching strategies — invalidation, TTL guidelines, cache keys, cache layers, and when not to cache. Use when implementing or reviewing caching logic.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

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.

Enumerate public cloud storage buckets and resources across AWS, Azure, GCP, and other providers. Use when targeting cloud infrastructure, when discovering misconfigured storage, or when the user mentions S3 buckets or cloud assets.

Provides verification checklists for code review including acceptance criteria validation, specification compliance checking, OWASP security patterns, and evidence-based assessment. Use when verifying task implementation quality.

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

Guides multi-pass codebase research using semantic search, grep, and file exploration. Produces structured context maps with primary files, secondary files, patterns, and implementation sequences. Use when researching a codebase before implementation.

Cryptographic attack templates for CTF challenges. Provides ready-to-run Python scripts for RSA attacks (small-e, Wiener, Hastad, common modulus, factorization), AES exploitation (ECB byte-at-a-time, CBC bit-flipping, padding oracle), hash attacks (length extension, collision), XOR key recovery, and Z3 constraint solving. Use when attacking RSA implementations, when exploiting block cipher misuse, when performing frequency analysis, when using Z3 for constraint satisfaction, or when automating crypto challenge solves.

Encoding detection and multi-layer decoding chains for CTF challenges. Provides Python templates for automated encoding identification, iterative base64/hex/binary/URL/rot13 decoding, XOR brute-force with frequency analysis, nested encoding unwrapping, custom alphabet detection, and esoteric encoding systems. Use when encountering unknown encodings in CTF data, when peeling multi-layer encoding wrappers, when brute-forcing XOR keys using character frequency, or when building automated decoders for misc/crypto challenges.

Digital forensics extraction pipelines for CTF challenges — binwalk, Volatility, PCAP, steganography, disk images, metadata. Lean skill with on-demand reference files.

Pwntools exploit boilerplate for CTF binary exploitation. Provides ready-to-use templates for remote/local process interaction, ROP chain construction, format string attacks, shellcode generation, and interactive shell management. Use when writing binary exploits, when connecting to challenge services with pwntools, when building ROP chains, when exploiting format string vulnerabilities, or when automating pwn challenge solves.

Network service interaction patterns for CTF — socket clients, multi-round solvers, flag extraction, PoW solvers. Lean skill with on-demand reference files.

Solve CTF (Capture The Flag) challenges by analyzing challenge descriptions, source code, and interacting with challenge environments to capture flags.

Write CVE-format security advisories following MITRE CNA operational rules and CVE Record schema. Use when publishing vulnerability disclosures, preparing coordinated disclosure documentation, or creating vendor security advisories that require CVE identifiers.

Database design patterns: schema design, migration conventions, indexing strategies, and query optimization. Use when designing schemas, writing migrations, or optimizing queries.

Defines the structured delegation protocol for coordinator-to-subagent communication. Includes base parameter requirements, agent-specific parameters, anti-laziness checklists, and RESULT block parsing. Use when delegating work to subagents.

Dependency auditing: vulnerability scanning, license compliance, outdated package detection, and update strategies. Use when checking or updating project dependencies.

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

CI/CD and DevOps patterns: GitHub Actions workflows, Docker best practices, environment configuration, and deployment checklists. Use when configuring pipelines, containers, or deployments.

Perform comprehensive DNS reconnaissance including record enumeration, zone transfers, and reverse lookups. Use when gathering DNS information about a target, when checking for zone transfers, when mapping DNS infrastructure, or when the user asks about DNS records.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Discovers URLs, endpoints, and paths from web applications using katana, gospider, and gau. Use when needing to enumerate application endpoints, find hidden paths, gather historical URLs, or map web application structure during reconnaissance.

Error monitoring and observability: tool comparison (Sentry, LogRocket, DataDog, New Relic), Sentry setup, structured logging, React error boundaries, alerting, and source maps. Use when setting up error tracking, observability, or debugging production issues.

Perform web fuzzing for content discovery, parameter enumeration, and virtual host detection using ffuf. Use when directory or file discovery is needed, when fuzzing parameters for hidden endpoints, when enumerating virtual hosts, or when brute-forcing authentication.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Git workflow conventions: conventional commits, branch naming, PR templates, merge strategy, and changelog generation. Use when creating commits, branches, or pull requests.