{"id":"d73ebddf-68e9-4018-a87d-72e7ae9a9e9b","slug":"shared-agent-assets","kind":"skill","name":"shared-agent-assets","summary":"Security-reviewed skills, rules, and reusable memory for AI agents","owner":"wunderforge","repoUrl":"https://github.com/wunderforge/shared-agent-assets","license":"Apache-2.0","licenseTier":"permissive","trust":"community","stars":0,"match":null,"fewStars":true,"format":"skill","createdAt":"2026-09-11T09:07:57.000Z","addedAt":"2026-11-01T00:49:32.792Z","logoUrl":"https://avatars.githubusercontent.com/u/247966177?u=97ae2de8645bf6fcbf501fdb14f10e9d34cc4594&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["developer-tools","memory-knowledge"],"tags":["ai-agents","claude-code","codex","security","skillspector"],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-11-01T00:50:49.109Z","sample":false,"url":"https://conduits.dev/tools/shared-agent-assets","language":"Python","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# Shared Agent Assets\n\nSecurity-reviewed, reusable assets for AI agents used by the team.\n\n| Directory | Purpose |\n| --- | --- |\n| `skills/` | Executable agent skills in the open Agent Skills layout |\n| `rules/` | Reusable instruction and policy text that a project can adopt |\n| `memory/` | Sanitized, durable knowledge that is safe to share publicly |\n\nThis repository is public. Never add credentials, customer data, personal data,\nprivate conversation exports, or internal-only project history.\n\n## Install skills\n\nList the available skills:\n\n```sh\nnpx skills add wunderforge/shared-agent-assets --list\n```\n\nInstall one skill for a supported agent:\n\n```sh\nnpx skills add wunderforge/shared-agent-assets --skill <skill-name> --agent codex\n```\n\nThe same repository can target Claude Code, Cursor, and other clients supported\nby the [`skills` CLI](https://github.com/vercel-labs/skills).\n\n## Contribute\n\n1. Create a branch and add one coherent asset or change.\n2. Run `./scripts/check.ps1` on Windows or `./scripts/check.sh` on macOS/Linux.\n3. Open a pull request using the repository template.\n4. Merge only after owner review and the required CI gate pass.\n\nEvery skill is scanned with\n[NVIDIA SkillSpector](https://github.com/NVIDIA/SkillSpector). The gate is\nfail-closed: only a `SAFE` recommendation is accepted.\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for the asset contracts and review flow.\n\n"}