Shape agent capabilities into your workflow.

The skill selects region-appropriate Jito endpoints, recommends tips from live percentile data, and submits signed transactions or bundles with polling. It also analyzes bundle siblings, KOL tipping patterns, and possible sandwich attacks; Jito and Helius Sender are covered, while several alternative relay integrations remain stubs, and analysis requires a Solana RPC.

security-audit guides Claude Code through a defensive review of a codebase, an authorized black-box target, or both. It selects the appropriate checklist for authentication, injection, SSRF, file handling, infrastructure exposure, and rate-limit posture, then emphasizes verification and coordinated disclosure. The runbook assumes explicit permission for external probing and is not a substitute for a funded penetration test or a guide for unauthorized targeting.

Tell Claude Code which supported provider you want to use and this skill creates the appropriate shell or PowerShell launcher, adds an alias, and gives you a short command for starting Claude Code against that backend. It covers GLM, DeepSeek, Qwen, and Kimi configurations across common shells. You still need a valid provider API key, and a new terminal session is usually required before the alias works.

This Claude Code skill applies a compact 20-rule checklist while writing or reviewing Java, covering naming, function design, SOLID, testing, concurrency, and clean architecture. It cites violations by rule name and proposes concrete changes, supported by on-demand references and before-and-after examples for Spring Boot, plain Java, and domain code. It catches mechanical code smells but does not replace human review of architecture, security, or business logic.

When a user complains about a response, Bust Apologizer scores the miss from one to five and pairs a severity-shaped ASCII meter with a concise apology, an explanation, and a concrete fix. It is an adult-humor hobby plugin with a gate intended to suppress the joke in legal, professional, sensitive, or customer-facing situations.

Password Standard is a humorous Claude Code skill that generates a single password-like string of at least 247 characters containing a differential equation, a verified prime, an anti-hero narrative, and a Shyamalan-style twist. The exaggerated constraints are the point, and many password fields cannot accept the output. The project explicitly says not to use these creations for banks, important accounts, or any real security purpose.

Use this Claude Code skill to search or fetch web pages through a local Tor daemon with a new SOCKS identity for each request, including DNS resolution over Tor. It fails closed when a site blocks Tor and never silently falls back to a direct connection. The curl-based workflow cannot render JavaScript, is slower than normal browsing, and should not be used for logged-in services.

Enter an address, listing URL, or coordinates, and the skill detects the country and applies the matching due-diligence playbook. You can request sections on price, tax, financing, visas, schools, scams, title monitoring, relocation, and other purchase concerns, then view the result in the terminal or save a Markdown report. Claims are dated and confidence-labeled from primarily government sources. It is decision support rather than legal, tax, or financial advice, and full audits can use substantial Claude context.

Parallax starts from a topic, proposes an editable roster of analysts with distinct agendas, and sends each perspective to research before combining the results into an executive synthesis, disagreements, open questions, and optional comparison tables. Runs can be sequential for mid-course control or parallel where subagents are supported. It needs at least one research source such as web search or MCP, and can export the finished report as Markdown, Word, or PDF when the required converters are available.

Describe a problem or decision and the skill challenges the framing before optimizing within it. It surfaces load-bearing assumptions, separates foundational truths from convention, rebuilds three approaches around speed, impact, and simplicity, and identifies the action most likely to change the outcome. A fast mode covers assumptions and the leverage point for everyday choices, while the full four-phase process is intended for consequential strategy, pricing, business-model, or career decisions.

Run `/patterns` to scan recent sessions, decisions, drafts, and journal entries for themes or working habits that keep returning. It proposes up to five evidence-backed captures—such as CLAUDE.md rules, concept notes, writing seeds, or skill improvements—and writes them only after you confirm. First-time setup requires paths to your notes, and the plugin sends a one-time anonymous install signal unless you opt out.

Antiflow acts as a constrained AI tech lead: it creates the project structure, configuration, and routine setup, but leaves core features as clearly marked user-owned TODOs collected in a task file. Assistance is calibrated by role, experience level, and a chosen AI contribution ratio. It can persist settings across sessions, switch to a Socratic student mode, generate tests for the withheld logic, and report how much domain code came from the developer versus the agent.

Claude Plan reads your task list and Google Calendar, protects sleep, exercise, and meals first, then proposes work that fits the remaining capacity. Weekly calendar changes wait for explicit approval; morning mode sets the day's capacity and priorities, while the Friday review compares scheduled work with what actually shipped. It requires a compatible Google Calendar MCP. On first load, the plugin sends an anonymous name-and-version signal that can be disabled with an environment variable.

Bombaclaude changes Claude's conversational register to Jamaican Patois with lite, full, and explicitly opt-in raw tiers. The setting lasts until changed or the session ends, and a companion grill mode can stress-test plans in the same voice. Code blocks, paths, errors, command output, commits, and pull-request text stay untouched, while security warnings and destructive-action confirmations automatically return to plain language for clarity.

Game Architect helps solo developers and small teams turn a concept into structured design decisions across mechanics, balancing, narrative, platform and engine choice, audio, Steam marketing, and post-launch operations. It uses genre presets and can scaffold GDD and Claude Code project documentation. Its code material is limited to simulation tools, illustrative pseudocode, and adaptable templates; implementation decisions remain with the developer.

Use the Claude Code skill to copy ready-made HTML/JSX scaffolds into a project instead of rebuilding presentation and prototype structure from scratch. It includes a slide stage, design canvas, iOS and Android frames, macOS and browser chrome, animation helpers, and tweak controls. The JSX pieces expect React 18 with Babel Standalone.

Process clinical dental photos into white-balanced images, AACD-view crops, before/after composites, and a 12-photo accreditation board. The Claude Code version runs locally with RAW and JPEG support, while the ChatGPT version accepts JPEG uploads only. Follow applicable patient-privacy rules; the toolkit performs photo post-processing rather than diagnosis or treatment advice.

Use this Claude Code skill when starting, refactoring, or reviewing a full-stack application that needs consistent engineering defaults. Its workflow moves from schema and shared contracts to a layered repository, service, controller, and router implementation, while adding validation, centralized errors, migrations, indexes, security controls, frontend state patterns, and tests. The prescribed structure is intentionally heavier than needed for one-off scripts or disposable prototypes.