toolkit

Turn a repo-local spec, rollout doc, design note, or implementation plan into a compact /goal prompt. Use when the user wants to run Codex /goal from an existing spec-first workflow and needs the goal to preserve scope, non-goals, validations, and local constraints.

Evaluate a repository's first-rung readiness for high-quality AI code contributions and produce concrete, copy-pasteable file changes that make the repo AI-ready. Use when asked to audit AI contribution quality, diagnose why AI PRs are low quality, prepare a repo for AI-assisted engineering, or move a repo from no harness toward a basic v0.5 contribution harness.

Bootstrap a small, deterministic repo-local AI harness by adding only the docs, skills, or checks that have concrete repo-specific content. Use when a repo already has basic AI contribution readiness and the user wants continuous harness improvement without placeholder process.

Evaluate a real AI-assisted work session against the repo-local harness, classify reusable misses, and update or propose updates to docs, skills, scripts, MCP/tooling, or sensors. Use after substantial work, review feedback, failed validation, or human correction in a repo with an AI harness.

Investigate established Pulumi-vs-Terraform parity gaps in bridged providers by creating or refining bridge cross-tests, after routing has already determined that bridge parity work is the next step, or when the user explicitly asks for that help. Use when the agent already knows that Pulumi has the problem and Terraform does not, and the next step is to capture, narrow, and explain that parity gap inside pulumi-terraform-bridge without debating alternate harnesses.

Run Claude Code as a chat-only reviewer for a local diff or branch, including adversarial pressure-testing when requested. Use when the user explicitly wants a Claude second opinion without posting GitHub comments.

Work back and forth with the user to understand intent, success criteria, constraints, and open questions before or during implementation. Use explicitly when the task is fuzzy, high-context, or benefits from shared thinking rather than immediate execution.

Generate a visual local webpage that explains a GitHub PR as a decision and behavior change, not a defect-finding review. Use when the user asks to understand a PR, asks what a PR is doing, wants a walkthrough, wants a plan-review-style assessment, or wants root problem, before/after examples, tradeoffs, compatibility risks, proof gaps, and reviewer questions.

Manage stacked GitHub pull requests with git-spice from branch creation through submit, restack, and update cycles. Use when work should be split into reviewable stacked branches, when a stack must be submitted or repaired, when branch base relationships must be changed, or when a branch-to-PR map needs to be captured and maintained.

Implement, refactor, modernize, and debug production Go code using Google-style API, error, concurrency, testing, and readability rules plus version-gated modernization guidance. For Go code review, prefer request-review with its Go reviewer lens.

Use when a command is killed by memrun, exits 137, exceeds an RSS limit, or produces a memrun JSONL log; inspect the log, identify the largest process, preserve diagnostics, and choose the next safe step before rerunning.

Use when the user explicitly wants multiple model perspectives on a document, plan, or decision, or when independent comparison would materially change a high-risk judgment.

Implement, refactor, modernize, and debug Neovim plugins in Lua using official runtimepath/module-loading, startup/lazy-loading, keymap/autocmd, health, documentation, and release practices. For review-only work, prefer request-review and load the Neovim reviewer reference when needed.

Investigate Pulumi engine, bridge, and provider lifecycle behavior from gRPC logs, architecture docs, and provider code. Use when diagnosing confusing Pulumi preview/update/refresh/import/replacement behavior, bridged provider failures, unexpected Check/Diff/Read ordering, provider upgrade regressions, stale or surprising inputs/state, Terraform bridge translation issues, or questions about which layer owns a lifecycle bug.

Audit and rationalize Go-heavy Pulumi provider or component test suites by producing a row-level inventory, provenance scan, ownership analysis, and decision-bucket report. Use when working in Pulumi bridged providers, native providers, or component libraries and you need to classify expensive, legacy, example, integration, or regression tests into keep, remove, rewrite-cheaper, move-upstream, conditional-run, or always-run buckets.

Run a focused manual review of a diff, branch, file set, or spec-aligned implementation using the smallest useful set of independent review lenses, then synthesize verified findings.

Review a GitHub PR by loading PR context, running or reusing the core request-review findings, drafting comments for approval, and posting only after explicit go-ahead.

Stage durable Pulumi-side repro artifacts for provider issues after the routing question has already narrowed to a Pulumi repro, or when the user explicitly asks for that help. Use when the agent needs to create maintainer-quality examples or tests in a provider repo, preserve the exact lifecycle path that matters, prefer repo-native repros over ad hoc temp directories, and report what can or cannot be executed without credentials.

Stage durable Terraform-side repro artifacts for provider issues after the routing question has already narrowed to a Terraform discriminator, or when the user explicitly asks for that help. Use when the agent needs to answer whether Terraform reproduces, build an upstream acceptance-style repro, preserve the exact discriminator being tested, and avoid replacing a strong Terraform path with a weaker local experiment just because credentials are unavailable.

Triage Pulumi provider issues end-to-end without forcing a one-shot conclusion. Use when the agent needs to assess likely attribution, decide what evidence is already settled, choose the next best action, and explicitly switch to helper skills for Pulumi repros, Terraform repros, bridge parity investigations, or workaround work.

Investigate practical workarounds for provider issues after the ownership boundary is already clear enough to act, or when the user explicitly asks for workaround help. Use when the agent needs to keep going past attribution, look for narrow mitigations or behavioral guards, evaluate whether a workaround is realistic, and report the tradeoffs without pretending the final fix is already known.