
from claude-skill-registry483
Two-step Solana swap workflow: quote/simulate first, present clear summary, then execute only after explicit user confirmation to avoid accidental trades.
Implements a safety-first two-step swap workflow for Solana using a w3rt runtime. The skill requires an initial quote/simulation step that produces a quoteId and a separate explicit execution step that only runs after the user confirms with a required passphrase. It includes clear output handling and policy limits for slippage and maximum input sizes.
Use this skill when performing programmatic token swaps on Solana where accidental or repeated execution would be costly — for example, in chat-driven trading assistants, testing environments, or automated bots that need human-in-the-loop confirmation.
w3rt_swap_safe.mjs) to quote and execute swaps, but the fetch indicated has_scripts=false in this repo packaging — verify before running.quote to generate a quoteId, inspect simulation results, present a compact summary (from/to/amount/slippage/route), and require an exact confirm phrase before calling exec. Also details failure handling and not re-executing the same quoteId.Useful for agents that orchestrate CLI or Node.js workflows and that enforce safety policies (Claude Code, Copilot-like assistants, runner agents with Node support). Requires access to wallet/runtime configs and careful policy checks.
Two-step Solana swap skill (quote then explicit confirm) with policy guards for slippage and max amounts. No bundled scripts — relies entirely on external w3rt runtime at a hardcoded absolute path (/home/davirain/clawd/web3AIRuntime). Safety design is solid but the skill won't work without significant manual setup of the w3rt runtime dependency.
w3rt runtimenode scripts/w3rt_swap_safe.mjsGood safety pattern (two-step confirm, policy limits). Main issues: hardcoded paths, no bundled scripts, heavy external dependency. Shell injection risk from unquoted args in example commands.
Uloop: Execute Dynamic Code
Run small C# snippets in the Unity Editor via the uloop CLI for editor automation tasks like prefab wiring, AddComponent flows, and scene edits—without writing
Bookmarklet Creation
Generates browser-executable JavaScript bookmarklets with strict formatting (IIFE wrapper, block comments) and provides ready-to-install links or installer inst
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
Bexio API (Swiss CRM & Invoicing)
Integrate and manage Bexio contacts, quotes, invoices, orders and products via the Bexio API. Useful for CRM and Swiss business document workflows.
Content Research Writer
A writing-partner skill that helps research, outline, draft, cite, and iteratively improve articles, tutorials, and thought pieces.
Agent Hierarchy Diagram
Generate visual hierarchy diagrams (ASCII, Mermaid, GraphML) that show agent roles, levels, and delegation for documentation and onboarding.
Review Pull Request
Automated, structured PR reviewer: gathers metadata, diffs, CI results, dependency changes and provides a concise verdict with testing and documentation recomme
Agent Ops — Testing Workflow
Guidance for designing, running, and analyzing test suites for agents: test isolation, execution patterns, and coverage-based enforcement.
libagent
Agent orchestration library for conversational AI — coordinates LLM completions, memory, tool execution, and multi-turn flows; useful for building chat agents a
Raindrop.io API
Manage Raindrop.io bookmarks, collections, tags and highlights via the Raindrop REST API with helper scripts and examples.