ton-http
TON HTTP API (TON Center / ton-http-api) — accounts, transactions, messages, send, runGetMethod; use Swagger for request/response parameters and return values.
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
25,636 results
TON HTTP API (TON Center / ton-http-api) — accounts, transactions, messages, send, runGetMethod; use Swagger for request/response parameters and return values.
Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric,…
Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric,…
Produce an audit-aware, agent-executable master plan (PLAN.mdx) for a software project before application code is written. One command runs discovery, forces…
Select one best-fit methodology from the twelve-method catalog, or none. Use when a task needs a structured method before goal engineering or methodology-skill…
Use this skill whenever building, editing, or reviewing user-facing software — web apps, mobile, dashboards, marketing sites, internal tools, design systems,…
Set up and run a private Telegram bot that lets the human chat with this coding agent from their phone. Use when the human asks to set up the telegram bot, to…
The English introduction is being prepared.
Use the LI.FI MCP server through UXC for cross-chain route discovery, bridge/DEX availability checks, token and chain lookup, gas/balance/allowance checks,…
Operate Telegram Bot API through UXC with a curated OpenAPI schema, bot-token path auth, polling-based reads, and webhook management guardrails.
Use when starting any conversation - establishes Arc's skill routing, instruction priority, and bootstrap rules
Use when the user explicitly asks to "compress/slim down/streamline the Markdown documentation of an Agent Skill" or "reduce the skill context overhead without changing functionality". First understand the target skill's real capabilities and security boundaries, then, while ignoring `tests/`、`plans/` as well as the target skill's `README.md`、`CHANGELOG.md`…
Delegate a task or question to the OpenAI Codex CLI running as an isolated subagent, then relay its answer. Use when the user invokes /codex <prompt>, says…
Use when a session is about to bulk-read 3+ files or any single file over ~400 lines, generate predictable boilerplate (tests, fixtures, config scaffolds, doc…
Apply a structured and reflective problem-solving approach for complex tasks that require multi-step analysis, revision capabilities, and hypothesis verification. Use it for complex problem decomposition, adaptive planning, analysis requiring course correction, problems with unclear scope, multi-step solutions, and hypothesis-based work.
Split an agreed spec into a set of tickets, put them in order, and give each ticket to the correct role.
Use an app as a real user does, and keep a guide at the root of the repository that tells agents how to use it.
Use when reviewing, validating, or auditing IfcOpenShell Python code for correctness. Runs systematic checks for schema compatibility errors, incorrect API…
Use when creating CLAUDE.md files, updating existing CLAUDE.md, validating CLAUDE.md structure, or auto-fixing CLAUDE.md issues. Load for setting up project…
Use when implementing hooks that BLOCK invalid actions, creating quality gates for state transitions, or enforcing tested:true verification. Load when…
Replace with description of the skill and when Claude should use it.
Extract camera intrinsics, extrinsics, and FOV polygons to calibration.json. Use after cameras are placed; to place them first use place-camera-max-coverage.
Use when creating project-specific lint rules for AI agents or humans using existing language linter ecosystems. Generates rules under a `lints/` directory…
Use only when migrating an existing skill directory from `.claude/skills/{name}` to `.agents/skills/{name}` and creating `.claude/skills/{name}` and…