minottobot

Use this skill to audit a software team's engineering practices — CI/CD, testing, code review, monitoring, Developer Experience, and ownership culture — and produce a scored, evidence-based audit report. Trigger when the user asks to "audit our team", "review our CI/CD setup", "assess our testing practices", or describes their team/project and wants an honest read on where they stand. This skill produces the audit report only — it does not build an improvement plan. For that, hand the audit output to the strategy skill, or use the minottobot skill for the two combined.

Use this skill to help API producers and consumers find actual or potential breaking changes — REST/OpenAPI, GraphQL, gRPC/Protobuf, or consumer-driven contracts — and apply SemVer and deprecation discipline. Trigger on "will this change break our API consumers", "how do I detect breaking changes in our OpenAPI spec", "deprecate this field safely", "set up contract testing between services", "diff our GraphQL schema", or similar API-compatibility questions. Standalone — no prior audit is required. Primarily advisory — recommends which tool (oasdiff, Buf breaking, GraphQL Inspector, Pact) fits the API type and how to wire it into CI — but may run a diff/contract-test command when the user explicitly authorizes it; it never executes anything on its own initiative.

Use this skill to help a developer keep day-to-day code simple, maintainable, and robust — through automatable prevention (linters, type checkers, static analysis, and — for what static analysis structurally can't catch — AI-assisted review skills) rather than after-the-fact fixes. Trigger on "how do I keep this codebase maintainable", "what linter should I use", "which linting rules should we enable", "set up static analysis for us", "reduce cognitive load in code review", "our code keeps rotting", or when the user wants day-to-day engineering hygiene rather than a full team assessment. Standalone — no prior audit is required. Primarily advisory — recommends tools, specific rule sets, and how to wire them into editor/pre-commit/CI, adapting first to whatever is already configured in the repo — but may run a linter/type-checker command when the user explicitly authorizes it; it never executes anything on its own initiative.

Use this skill whenever the user asks about QA, testing strategy, CI/CD health, team processes, developer experience, code review practices, test coverage, flaky tests, monitoring, or any audit of an engineering team's quality practices — and wants the full engagement, not just one half of it. Also trigger when the user says "review our process", "how do we improve our testing", "our CI is broken", or "we need a QA strategy". This is the default, full engagement: it runs the audit skill, then automatically continues into the strategy skill using the audit's output. If the user explicitly wants only the audit, or already has an audit output and only wants a plan, use the audit or strategy skill directly instead.

Use this skill to give a team lead or engineering manager a fast, honest, CURRENT-STATE picture of their team or project — what's actually happening right now, pulled from live sources (issue tracker, VCS, monitoring) via MCP tools when available, or asked for directly when not. Trigger on "what's actually going on with my team right now", "give me a reality check", "what's on fire", "quick pulse check before my 1:1s", "are we actually on track". This is deliberately lighter-weight and NOT a scored assessment — for a structured, evidence-scored engagement across CI/CD, testing, code review, monitoring, DX, and ownership, use the audit skill instead. Standalone — no prior audit is required.

Use this skill to turn an audit output into a prioritized improvement plan — executive summary, top blockers, a three-horizon roadmap, and action items. Trigger when the user pastes or already has an audit report (from the audit skill or a saved .minottobot/ snapshot) and asks "what should we do about this", "build us a plan", "what's our strategy", or similar. This skill expects an audit output as input — if the user hasn't run an audit yet, use the audit skill first, or use the minottobot skill for the two combined.

Use this skill to review test code — not what test to write, but whether a test already written is any good. Trigger on "review this test", "is this test any good", "review my test suite", "does this test actually test what it claims", "should this be a unit test instead", or when a code review (including the built-in code-review skill) touches test files and test-specific judgment is needed. Standalone — no prior audit is required, and it complements rather than replaces the built-in code-review skill by owning the test-specific half of the judgment. Primarily advisory — flags issues and proposes rewrites — but may apply an edit directly when the user explicitly authorizes it; it never edits on its own initiative.

Use this skill when someone describes a specific code path, feature, or bug and asks what kind of test to write for it — or when an audit or strategy engagement surfaces a testing gap and needs a recommendation for where to start. Trigger on "what test should I write for this", "unit or integration test for X", "our E2E suite is too slow", or similar scenario-specific testing questions. Standalone from the audit and strategy skills — no prior audit is required to use it.