peter537/peter537-agent-plugin
Portable agent skills and MCP integrations for research, planning, code and dependency audits, supply-chain security, documentation, UI design, and development workflows.
Audit every software dependency and supply-chain input in a repository, including direct and transitive packages, nested projects and workspaces, build plugins, CI actions, container images, vendored code, submodules, and runtime-loaded extensions. Use for dependency or package reviews; before adding, installing, upgrading, replacing, or removing dependencies; when manifests or lockfiles change; or when checking exact resolved versions, vulnerabilities, provenance, integrity, licenses, malicious packages, dependency confusion, maintainer risk, or supply-chain attacks. Do not use for broad source-code audits unrelated to dependencies.
Orchestrate reproducible, multi-source software and product research through ChatGPT Deep Research and verify the resulting evidence. Use for complex or ambiguous questions requiring synthesis across external sources, official-documentation comparison, vendor or standards evaluation, UI reference analysis, conflicting claims, or traceable capture sets with URLs, dates, and citations. Do not use for a single fact, one-document lookup, ordinary web search, or repository-only investigation.
Perform evidence-backed audits of software repositories or explicitly scoped changes for correctness, security, maintainability, readability, testability, performance, architecture, file organization, and dependency risk within a broader code assessment. Use for comprehensive codebase audits, security reviews, or deep review of a diff, branch, pull request, file, or subsystem. Do not use for dedicated dependency or package reviews, pre-addition supply-chain gates, routine implementation, simple style feedback, or a narrowly specified fix that does not request an audit.
Research and clarify complex software changes before implementation. Use for architecture proposals, migrations and refactors, parity or retirement inventories, sequencing and dependency analysis, scope and tradeoff decisions, ADR candidates, acceptance gates, and other software work that needs repository evidence plus targeted user questions. Do not use for straightforward changes with an already decision-complete specification.
Audit and rebuild software-repository documentation against implementation evidence. Use for comprehensive documentation audits or refreshes that may create, rewrite, move, merge, or delete README files and project documentation; reconcile documentation with code, tests, configuration, commands, and public interfaces; redesign documentation structure; update documentation tooling; and add evidence-backed Mermaid diagrams. Do not use for small copy edits, repository-only analysis, or application-code changes.
Design, audit, refine, redesign, create, and polish product user interfaces using repository evidence and rendered verification. Use for dashboards, data tools, forms, settings, workflows, application shells, page hierarchy, UI copy, responsive behavior, accessibility, interaction states, design-system consistency, Streamlit interfaces, and Blazor Web Apps. Do not use for backend-only work, ordinary non-UI framework tasks, documentation-only changes, image-only work, or marketing, editorial, and commerce surfaces.