v1truv1us/ai-eng-system

1

architect Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use …

v1truv1us/ai-eng-system

1

2

arena Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /…

v1truv1us/ai-eng-system

1

3

auto-research Premier research workflow for systematic investigation, synthesis, and verification. Use for literature reviews, comp…

v1truv1us/ai-eng-system

1

4

automate-me Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a s…

v1truv1us/ai-eng-system

1

5

check-agent-compatibility Run the full repository compatibility pass: scanner score, startup path, validation loop, and docs reliability.

v1truv1us/ai-eng-system

1

6

check-compiler-errors Run compile and type-check commands and report failures

v1truv1us/ai-eng-system

1

7

cli-for-agents Design or review CLIs so coding agents can run them reliably: non-interactive flags, fast actionable errors, idempote…

v1truv1us/ai-eng-system

1

8

continuous-learning Extract reusable patterns from sessions, score confidence, and promote high-confidence instincts into durable skills.…

v1truv1us/ai-eng-system

1

9

control-cli Build a local harness to drive, inspect, and profile an interactive CLI or TUI. Use for CLI UX checks, startup regres…

v1truv1us/ai-eng-system

1

10

control-ui Build a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for UI verification, screensho…

v1truv1us/ai-eng-system

1

11

create-goal Transform a vague idea, request, or prompt into a concrete, actionable goal with clear success criteria, scope bounda…

v1truv1us/ai-eng-system

1

12

create-learning-path Build a personalized learning roadmap with milestones and practice checkpoints

v1truv1us/ai-eng-system

1

13

cross-repo-refactor Coordinate a multi-repo refactor by fanning out subagents per repo onto one feature branch. Use for cross-repo change…

v1truv1us/ai-eng-system

1

14

cursor-sdk Guide building apps, scripts, CI pipelines, and automations with the Cursor TypeScript SDK (`@cursor/sdk`).

v1truv1us/ai-eng-system

1

15

doc-review Structured document review for structure, clarity, and technical accuracy. Use for \"review this doc\", feedback, cri…

v1truv1us/ai-eng-system

1

16

docker Build, run, and secure Docker containers with current best practices. Use for Dockerfile review, multi-stage builds, …

v1truv1us/ai-eng-system

1

17

docs-canvas Render a documentation-style Cursor Canvas that organizes architecture notes, API references, walkthroughs, and how-t…

v1truv1us/ai-eng-system

1

18

dreaming-consolidator Read the auto-memory graph (~/.claude/projects/*/memory/*.md), find cross-session patterns, and write a digest. The s…

v1truv1us/ai-eng-system

1

19

dynamic-claude-router Conductor/subagent routing for tasks across multiple harnesses. Assesses task complexity and intent, then dispatches …

v1truv1us/ai-eng-system

1

20

dynamic-router Conductor/subagent routing for tasks across multiple harnesses. Assesses task complexity and intent, then dispatches …

v1truv1us/ai-eng-system

1

21

fix-ci Find failing PR checks, inspect logs or external check links, and apply focused fixes

v1truv1us/ai-eng-system

1

22

fix-merge-conflicts Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution

v1truv1us/ai-eng-system

1

23

gemini-agent-sdk Build Gemini-backed agent workflows and adapters. Use for Google Gemini API/ADK-style runners, Gemini CLI workflow pa…

v1truv1us/ai-eng-system

1

24

get-pr-comments Fetch and summarize review comments from the active pull request

v1truv1us/ai-eng-system

1

25

github Operate GitHub repositories, workflows, and PRs efficiently. Use for Actions optimization, PR hygiene, repo maintenan…

v1truv1us/ai-eng-system

1

26

grill-me Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of …

v1truv1us/ai-eng-system

1

27

grill-with-docs Extend grill-me by producing or updating a CONTEXT.md or ADR-style decision record while stress-testing a plan. Use w…

v1truv1us/ai-eng-system

1

28

how Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering question…

v1truv1us/ai-eng-system

1

29

interrogate Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\…

v1truv1us/ai-eng-system

1

30

investigation-loop Long-running Jira investigation that self-continues past natural stops until a written hypothesis with evidence citat…

v1truv1us/ai-eng-system

1

31

k8s Deploy, manage, and troubleshoot Kubernetes workloads. Use for manifest review, Helm chart validation, resource tunin…

v1truv1us/ai-eng-system

1

32

loop-on-ci Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.

v1truv1us/ai-eng-system

1

33

make-pr-easy-to-review Prepare PRs for review: clean noisy history, improve descriptions, add reviewer guidance without changing behavior. U…

v1truv1us/ai-eng-system

1

34

monitoring Design and operate application observability with metrics, logs, traces, and alerts. Use for SLO definition, dashboar…

v1truv1us/ai-eng-system

1

35

morning-brief Daily briefing synthesizing calendar, tasks, and priorities. Use for "morning brief", "daily briefing", "start my day…

v1truv1us/ai-eng-system

1

36

new-branch-and-pr Create a fresh branch, complete work, and open a pull request

v1truv1us/ai-eng-system

1

37

npm-trusted-publishing Publish npm packages via GitHub Actions with OIDC trusted publishing and provenance. Use when setting up automated np…

v1truv1us/ai-eng-system

1

38

orchestrate Use only when the user explicitly types `/ai-eng/orchestrate <goal>` to decompose a large task, spawn a tree of paral…

v1truv1us/ai-eng-system

1

39

playwright Write, run, and maintain reliable end-to-end tests with Playwright. Use for test generation, CI integration, trace de…

v1truv1us/ai-eng-system

1

40

poteto-mode poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verifie…

v1truv1us/ai-eng-system

1

41

pr-review-canvas Generate an interactive PR review walkthrough as an HTML page. Fetches PR data via gh API, categorizes files into cor…

v1truv1us/ai-eng-system

1

42

principle-boundary-discipline Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, co…

v1truv1us/ai-eng-system

1

43

principle-encode-lessons-in-structure Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode th…

v1truv1us/ai-eng-system

1

44

principle-exhaust-the-design-space Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 compe…

v1truv1us/ai-eng-system

1

45

principle-experience-first Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship…

v1truv1us/ai-eng-system

1

46

principle-fix-root-causes Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach…

v1truv1us/ai-eng-system

1

47

principle-foundational-thinking Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what…

v1truv1us/ai-eng-system

1

48

principle-guard-the-context-window Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagent…

v1truv1us/ai-eng-system

1

49

principle-laziness-protocol Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias towar…

v1truv1us/ai-eng-system

1

50

principle-make-operations-idempotent Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Con…

v1truv1us/ai-eng-system

1