PetriLahdelma/project-spine
Context compiler for software projects. Turns brief + repo + design inputs into a repo-native operating layer — AGENTS.md, CLAUDE.md, copilot-instructions, scaffold, QA, sprint-1 backlog.
Context compiler for software projects. Turns brief + repo + design inputs into a repo-native operating layer — AGENTS.md, CLAUDE.md, copilot-instructions, scaffold, QA, sprint-1 backlog.
npx skills add PetriLahdelma/project-spineContext compiler for software projects. Turns brief + repo + design inputs into a repo-native operating layer — AGENTS.md, CLAUDE.md, copilot-instructions, scaffold, QA, sprint-1 backlog.
Claude Memory X 2026: Persistent AI Plugin for Smarter Coding Workflows
FCJ Workshop: Build an AI Product Designer Agent on Amazon Bedrock (Claude + Stability Stable Image, AWS CDK, Docker-free)
Claude skill to create prototypes using the USWDS
Claude Code / Codex skill for generating images via any OpenAI-compatible API
Hermes Agent skill for deep reading academic papers. MinerU Cloud extraction + NotebookLM figure analysis + LLM structured analysis. 4 modes: full/quick/figures-only/speed-read.
BenchClaw is a Codex/OpenCode skill workflow for benchmark construction, evaluation, and maintenance. It standardizes the full pipeline—from idea drafting and data generation to evaluation, reporting, failure diagnosis, and skill refinement—so agents can build reproducible, auditable benchmarks with clear quality gates, lineage, and rollback.