Use Potpie for spec-driven codebase workflows
Index a repository with Potpie, turn it into a code knowledge graph, and drive focused implementation or review tasks from specs.
npx skills add agentskillexchange/skills --skill use-potpie-for-spec-driven-codebase-workflows
Use Potpie when an engineering operator wants codebase-aware agent work anchored in a repository model before edits are proposed. The workflow is to deploy Potpie, index the target repository into its knowledge graph, write or select a focused implementation spec, ask targeted codebase questions, and review generated changes or plans against the indexed context. The scope boundary is spec-driven codebase work for a particular repo; it is not just a developer tool listing because the skill starts with repository indexing and ends with reviewable, context-backed engineering output.
What this skill actually does
Inputs and prerequisites: Docker; Git; Python 3.11+; uv; configured LLM provider.
Setup notes: Clone https://github.com/potpie-ai/potpie with submodules, copy .env.template to .env, configure the LLM and database settings, then run the repository quickstart.
Source and verification boundary: use https://docs.potpie.ai as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.