andreasasprou/agent-skills
3 skills0 installs21 starsGitHub
Install
npx skills add https://github.com/andreasasprou/agent-skillsSkills in this repo
1Opensrcopensrc is an agent plugin skill that fetches published npm package source so your coding agent can reason about real implementation details—not just typings and marketing docs. Solo builders hit this wall constantly: a dependency exposes a confusing API, edge cases are undocumented, or stack traces point inside node_modules and you need to read the actual code without tab-hopping across GitHub and registry tarballs. Install opensrc when you are in active build work and integration decisions depend on how a package handles retries, bundling, hooks, or internal modules. It is intentionally narrow and powerful: it does not replace reading official documentation first, but it steps in when docs and types stop matching runtime behavior. The skill fits backend and frontend integration tasks alike anywhere npm packages appear, and it also helps during Ship review when you need evidence for a security or correctness question about a transitive dependency.0installs2OracleOracle is an agent skill that plugs in a GPT-5.2 strategic advisor with emphasis on deep reasoning. It is built for solo and indie developers who need a careful second brain on architecture decisions, security implications, and gnarly debugging—without granting write access that could accidentally change the codebase. Use it when you are stuck between design options, unsure about a security boundary, or need structured hypotheses before you instrument or patch production issues. Because the skill is read-only by design, it complements your primary coding agent: you stay in the driver's seat while Oracle pressure-tests assumptions and surfaces risks. It is not a substitute for automated scanners or penetration tests, but it shines as a reasoning layer across build-time design, pre-ship security review, and operate-phase incident analysis when you want narrative clarity before you act.0installs3Safety NetSafety Net is a journey-wide agent plugin skill that stops destructive shell commands before they run, giving solo builders a default guardrail when Claude Code, Cursor, or similar agents touch git, filesystem, or cloud CLIs. Instead of trusting the model to refuse risky suggestions, the plugin enforces blocks on patterns such as recursive deletes, force pushes, and AWS resource deletions called out in the skill description. It fits indie developers who automate infra and cleanup via agents but cannot afford one mistaken rm -rf or forced git history rewrite. Complexity is low: install the plugin and let pre-execution hooks filter commands while you still review Security Audits on the catalog page. It does not replace backups, branch protection, or least-privilege IAM—it narrows the blast radius of agent-initiated terminal mistakes across every phase where a shell is used.0installs