π
Plugins
Loading...
Showing 30 of 24181 results
A ground-first reflex: the agent judges (from its own training, any domain) when a request is complex/irreversible, grounds before acting, and is hard-blocked from the destructive step until it has.
Documentation-discovery telemetry: /tt status, /tt watch, /tt insights
Extract flight + hotel data from Aviasales / Ostrovok links and compile into a self-contained HTML itinerary.
Trip Planning and Travel Strategies: matching trip type to purpose, choosing a destination, constraints-first planning, timing and seasonality, budgeting, how airfare pricing actually works, flight strategy, points and miles honestly, accommodation, ground transport, booking order and optionality, documents and entry, travel insurance, health, safety in proportion, money abroad, itinerary pacing, packing, jet lag, connectivity and navigation, language and culture, food and water, travelling with others, long-term travel, and handling disruption.
Command-line tool for Slack integration enabling terminal-based message, channel, and cross-tool workflow management for developers.
Trust & Safety team β 2 agents for content-moderation and abuse-detection work. The trust-safety-policy-lead designs the policy taxonomy + enforcement ladder, the human-review operations layer (queue prioritization, reviewer wellness, escalation, appeals/due-process), and the measurement frame (prevalence, enforcement precision/recall, time-to-action SLA, appeal-overturn rate). The abuse-detection-engineer builds the detection stack: signals, rules-vs-ML classifiers, reviewer queues, thresholds tied to precision/recall. 3 skills, a 2-doc knowledge bank (a Mermaid enforcement decision tree + a T&S metrics catalogue with formulas), 2 templates, 3 best-practice rules, and 1 advisory hook. Seams: classifier-eval validity β applied-statistics; PII β data-governance-privacy; account-takeover β security-engineering; LLM-classifier build β claude-app-engineering. Enforcement is proportional; appeals are due process; measure prevalence, not just volume. Requires ravenclaude-core@>=0.7.0.
(Legacy name, kept for existing installs.) Drive the TrustLine/Fianza agent SDK (JS/TS or Python): register, underwrite, borrow, repay, and pay x402 APIs on credit (draw-on-402).
(Legacy name, kept for existing installs.) Drive the TrustLine/Fianza agent SDK (JS/TS or Python): register, underwrite, borrow, repay, and pay x402 APIs on credit (draw-on-402).
Enforces strict change transparency for code, notebook, config, and command edits so every delta is disclosed, including incidental changes.
Issue-to-PR workflow automation with worktree management for TypeScript/JavaScript projects
Turn owned-but-unread Kobo e-books into actionable skills (Claude Code CLI only).
Hardware bring-up helpers: oscilloscope SCPI driver (Keysight + RIGOL), RS485 Modbus RTU master, more to come
Text-to-speech system for Claude Code that reads Claude's responses aloud using kokoro-tts
Multi-platform Chinese TTS text-to-speech β 8 China-friendly backends (Edge/Doubao/CosyVoice/Azure/Tencent/Baidu/MiniMax/Xunfei), agent-native CLI with JSON envelope, schema introspection, auto-detect TTY, distinct exit codes (0/1/2/3/4), structured errors (code/message/retryable/field/backend), --fields filtering, dry-run, JSON provider registry, filterable HTML comparison page, voice cloning, SSML, emotion, dialects.
Design functional, readable terminal UIs with proper visual hierarchy, semantic color, and responsive layout. SessionStart hook auto-injects principles when Rich/Textual/Click detected.
Expert UX evaluator for terminal user interfaces (TUIs). Rates usability across 11 criteria from real captured or user-provided recordings, grounded in named design canons, with parallel evaluation agents, persistent memory, and a research mode that grows its TUI pattern library.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, proven techniques, personal engineering experience, and curated skills inspired by Superpowers, BMad, OWASP, and related ecosystems.