ai-plugins

Use when preparing local changes, a branch, pull request, merge request, or merge-to-main for final review before publishing, opening a PR, merging, or claiming readiness.

Use when implementing any feature, bugfix, behavior change, or refactor before writing production code.

Use when the user asks to shape fuzzy planning, product/design/engineering tradeoffs, scope/spec/ticket plans, or says "challenge this/help me think"; delegate to an advisor subagent. Good for rough ideas, second opinions, load-bearing decisions, or scope cuts. Skip scoped implementation, narrow bugs, reviews, and "just build" requests.

Use when setting up a project-local eval harness for prompts, agents, judges, RAG, tools, or other LLM behavior, especially when the default should be free/OSS promptfoo with repo-owned artifacts.

Use when a pull request or merge request needs to be driven to merge — watching CI, responding to review feedback, and merging once green and approved, across GitHub, Forgejo, or GitLab.

Use when the user wants repository task tracking, shared agent task state, cross-worktree coordination, tiber setup/install/scaffold guidance, or task create/list/show/prioritize/validate/close workflows. Plugin install and session start are non-mutating; setup integration starts with dry-run previews.

Use when the user asks to add, capture, file, or record a new repository task or backlog ticket through Tiber from chat.

Use when a plugin, skill, prompt, tool, command, or agent behavior was surprising, wrong, partial, unsafe, brittle, or worth preserving as a future eval fixture; also use when the user asks to report, submit, capture, or file an eval case.

Use when receiving human, automated, GitHub, CodeRabbit, or other review feedback before changing code.

Use when a bug, failing test, broken command, unexpected output, or confusing runtime behavior appears.

Use when claiming work is done, fixed, passing, ready, reviewed, committed, or safe to merge.

Use when creating or editing skills in this marketplace or preparing skill behavior fixtures.

Use when planning or delivering an LLM or agentic-system project, especially for experiment loops, walking skeletons, demos, data stories, scope control, and release-readiness evidence.

Use when designing, implementing, reviewing, or debugging LLM-backed or agentic systems, including prompts, structured outputs, tool use, RAG, agent loops, orchestration, observability, security, cost/provider routing, and AI delivery plans.

Use when evaluating prompts, LLM features, agents, RAG, judges, tool-use policies, or any stochastic behavior where one successful run is not reliable evidence.

Use when starting or making substantive changes to a project that should follow a strict, portfolio-grade engineering regime — the default standards for architecture, type-safety, error handling, testing, linting, ADRs, and review to apply as you work. (To set up the tooling that enforces them, use the scaffold skill.)

Use when making a repository worktree-ready for parallel development — per-worktree isolation (ports, containers, caches, secrets), lifecycle hooks, and the main-checkout enforcement guard.

Use when setting up, bootstrapping, or scaffolding a new or existing project's tooling and config to enforce the engineering standards — generating a reproducible dev environment, pinned toolchain, strict lints, mutation and BDD harnesses, ADR structure, and CI/CD gates tailored to the detected stack.