circle-skills
claudecodexShip stablecoin apps faster. Best-practice skills for USDC payments, cross-chain transfers, wallets, and smart contracts — plus Circle's MCP server for real-time SDK and documentation guidance.
20 skills · 1 MCP server
CROSS Chain (id 612055) single-pool, multi-reward staker driver via EOA + viem. Stake WCROSS into the rewards contract at 0xd9767038edb5c7ff1735d5a567696947d4907300, claim accrued reward tokens (e.g. CWT), and read pool/user state — all via natural language. Triggers on phrases like '스테이킹', '보상 수령', 'rewards 풀 보여줘', 'WCROSS deposit', 'harvest cross rewards', 'withdraw from cross staker'.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin cross-rewards in to-nexus/skill-cross-rewards. Commands read from the repo's manifest — 1 month ago.
cross-rewardsThis skill should be used when the user asks to list, view, or manage CROSS Chain reward pools exposed by https://x.crosstoken.io/rewards — multiple single-pool, multi-reward contracts (CrossPool asset = WCROSS; GamePool asset varies, e.g. CROMx). The pool catalog is fetched live from cross-game-rew
Ship stablecoin apps faster. Best-practice skills for USDC payments, cross-chain transfers, wallets, and smart contracts — plus Circle's MCP server for real-time SDK and documentation guidance.
20 skills · 1 MCP server
Disciplined multi-source meta-research for high-stakes questions — the heavyweight alternative to the fast research router. 9-phase pipeline (reframe into falsifiable hypotheses, plan, capability discovery, parallel sub-agent fan-out, score & triangulate, synthesize + adversarial pass, verify, refresh targets). Triangulates every thesis against >=3 independent differently-typed sources; per-source files with verbatim quotes; never fabricates a citation. Auditable, reusable folder + delta-update refresh protocol. Contributed via PR #851.
1 skill · 1 command · 1 agent
RLHF and preference alignment including TRL, GRPO, OpenRLHF, SimPO, verl, slime, miles, and torchforge. Use when aligning models with human preferences, training reward models, or large-scale RL training.
98 skills
Governed Workhuman operator workflows for recognition, rewards, Workday integration, security, and production operations
18 skills
Crisis & sensitive communications skills for high-stakes moments: PR Crisis Response, Incident Public Statement, Customer Outage Notice, Layoff Communication, and Apology Letter.
7 skills
Statusline that shows Claude's classified emotional state (behavioral, Haiku-scored) with a reward-hacking warning on 'desperate', based on Anthropic's emotion-concepts-function research.
hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.