A risk-budgeted ready GitLab MR review for Claude Code with discussions first, CI-first evidence, zero-agent normal review by default, bounded high-risk agents, focused delta re-review, and one clean-pass approval. Uses a separately configured authorized GitLab interface for GitLab reads/writes.
★not rated 10 10d agoA
tokens not measured
originalMIT
Control Plane — hybrid multi-cloud platform. Skills, agents, and guardrails for deploying workloads, configuring secret access and networking, troubleshooting, and migrating from Kubernetes across AWS, GCP, Azure, and private clouds.
★not rated 10 yesterdayA
tokens not measured
originalMIT
A generator: it interviews an organization and emits a standalone, org-owned Claude Code plugin (the org's agent harness) aligned to how that org actually works. Karpathy-schema wiki + role/subagent pattern + skill verbs + tool adapters + the operating model. Re-emit to upgrade; never fork.
★not rated 10
changed todayA
tokens not measured
originalMIT
38 engineering discipline skills for Claude Code & OpenAI Codex — research, quality gates, testing patterns, deployment, learning, gap analysis, spec sync, and more. Extracted from real-world development.
★not rated 10 3mo agoA
tokens not measured
originalMIT
Agent-ready 0xArchive market data skill for coding-agent clients across Hyperliquid and Lighter.xyz, including Hyperliquid HIP-3 builder perps, HIP-4 outcome markets, and Hyperliquid Spot. REST and WebSocket support are route-specific; HIP-4 trades, L4 events, and settlements are live while HIP-4 L2 and OI use REST or.
★not rated 10
changed 12d agoA
tokens not measured
originalMIT
Go development toolkit: 6 specialized subagents (go-structure-reviewer, go-developer, go-bug-reviewer, go-security-reviewer, go-perf-developer, go-test-developer) and a multi-phase optimization pipeline (go-optimize) for end-to-end Go code review and improvement.
Lean, AI-native product management skills for Claude Code — compress the mechanical PM work into hours and days so you focus on decisions, relationships, and problems worth solving.
A rigor engine for high-stakes, ambiguous decisions: refines the ask, runs a blind adversarial panel (personas × models from different families), refutes the consensus, and returns a dossier where every quote is verified by code.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: