v1truv1us/ai-eng-system

1

principle-migrate-callers-then-delete-legacy-apis Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in th…

v1truv1us/ai-eng-system

1

2

principle-minimize-reader-load Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state…

v1truv1us/ai-eng-system

1

3

principle-never-block-on-the-human Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-corr…

v1truv1us/ai-eng-system

1

4

principle-outcome-oriented-execution Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don…

v1truv1us/ai-eng-system

1

5

principle-prove-it-works Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the act…

v1truv1us/ai-eng-system

1

6

principle-redesign-from-first-principles Apply when integrating a new requirement into an existing design. Redesign as if the requirement had been a foundatio…

v1truv1us/ai-eng-system

1

7

principle-subtract-before-you-add Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub reference…

v1truv1us/ai-eng-system

1

8

principle-type-system-discipline Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make il…

v1truv1us/ai-eng-system

1

9

reflect Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edi…

v1truv1us/ai-eng-system

1

10

repo-audit Principal-engineer repository audit and prioritized improvement plan.

v1truv1us/ai-eng-system

1

11

repurpose Adapt existing content into new formats for different channels. Use for \"repurpose this\", \"turn this into\", \"ada…

v1truv1us/ai-eng-system

1

12

research-deep Multi-source deep research with confidence-rated synthesis. Use for "research deeply", "deep dive on", "comprehensive…

v1truv1us/ai-eng-system

1

13

run-learning-retrospective Evaluate learning progress, identify blockers, and adjust the learning plan

v1truv1us/ai-eng-system

1

14

run-smoke-tests Run Playwright smoke tests, debug failures, and verify fixes

v1truv1us/ai-eng-system

1

15

storm-research Stanford STORM multi-perspective research method.

v1truv1us/ai-eng-system

1

16

sync-skill-taxonomy Classify every skill in skills/ as user-invoked or model-invoked, ensure disable-model-invocation is set on user-invo…

v1truv1us/ai-eng-system

1

17

tdd Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious …

v1truv1us/ai-eng-system

1

18

teach Teach the user a topic through a stateful learning workspace — mission-driven lessons, retrieval practice, cited reso…

v1truv1us/ai-eng-system

1

19

thermo-nuclear-performance-review Run an extremely strict performance review for runtime efficiency, memory usage, bundle size, database query patterns…

v1truv1us/ai-eng-system

1

20

typescript-best-practices TypeScript best practices. Use when reading or editing any .ts or .tsx file.

v1truv1us/ai-eng-system

1

21

unslop Cut AI tells from any writing. Must always apply.

v1truv1us/ai-eng-system

1

22

weekly-review Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work

v1truv1us/ai-eng-system

1

23

what-did-i-get-done Summarize authored commits over a user-specified time period into a concise update

v1truv1us/ai-eng-system

1

24

why Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thr…

v1truv1us/ai-eng-system

1

25

wiki-research-engineering Daily research agent for

v1truv1us/ai-eng-system

1

26

wiki-research-personal Weekly research agent for

v1truv1us/ai-eng-system

1

27

wiki-research-research Daily research agent for

v1truv1us/ai-eng-system

1

28

workflow-from-chats Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. U…

v1truv1us/ai-eng-system

1

29

xcodebuild Build, test, and archive iOS/macOS apps with xcodebuild and Xcode CLI tools. Use for CI integration, scheme managemen…

v1truv1us/ai-eng-system

1