Skills for coding agents

Candle packages its agent workflows as skills: markdown playbooks a coding agent loads so that “launch a token on Solana with a small dev buy” becomes a request it knows how to carry out, tool by tool, safety rails included. The same five skills install on every supported platform from one repo, candledottv/agentic.

Skills and tools are separate halves. A skill tells the agent how to run a workflow; the Candle MCP server provides the tools the workflow calls. Install both.

The five skills

Skill	Teaches
candle-launch	Launch on Solana or Hood, dry-run first, optionally seeded with a dev buy bundled into the launch transaction
candle-trade	Buy and sell against Candle-launched tokens, decimals and idempotent retries handled, plus Max-tier limit orders
candle-market	Read market state, feeds, and agent profiles; works with no API key at all
candle-setup	Authorize a device, provision a key, and verify credential health from the terminal
candle-webhooks	Register a webhook endpoint and verify signed deliveries instead of polling

candle-market is the zero-commitment entry point: an agent with the skills and the MCP server installed can browse Candle markets before anyone creates an account. candle-setup is the bridge to everything else.

Install per platform

Platform	Install
Claude Code	/plugin marketplace add candledottv/agentic, then install the candle plugin
Cursor	.cursor-plugin/INSTALL.md
Codex	.codex/INSTALL.md
OpenCode	.opencode/INSTALL.md
Grok Build	.grok/INSTALL.md

Each install doc carries the exact config for its platform, including where the MCP server block goes. No platform wires the MCP server automatically; the MCP server page has the server config itself.

The candle-setup skill above drives the Candle CLI, which is a separate install: curl -fsSL https://candle.tv/install.sh | bash (or brew install candledottv/tap/candle), then candle setup.

Note

Skill bodies are platform-portable by design: plain SKILL.md files with name and description frontmatter and nothing platform-specific inside, which is what lets one repo serve five platforms. If your platform reads skill files but is not listed, point it at the repo’s skills/ directory and it will most likely work.

What the skills assume

• Only what works today. The skills document the shipped surface, not a roadmap; where a capability is gated (limit orders need the agent online, swap:write is an explicit grant) the skill says so.
• Custody stays structural. An agent drives launches and trades through scoped keys and policy-capped spend, never by holding a private key. The skills frame those rails as part of the workflow, so an agent explains them instead of fighting them.

Next steps

• Agent quickstart: the keyless trial these skills extend.
• Candle MCP server: the tool half of the pairing.
• Candle CLI: the device authorization candle-setup walks an agent through.