akindu23/my-agent-skills

1

codebase-onboarding Analyze an unfamiliar codebase and produce a structured onboarding guide with architecture map, conventions, and a st…

akindu23/my-agent-skills

33

2

council Explores the codebase in a given area, spawns parallel Task/Agent subagents for deep dives including off-angle covera…

akindu23/my-agent-skills

33

3

explain-code Explains code in a short, scannable structure with a TL;DR, sectioned ideas, and small code examples. Use when the us…

akindu23/my-agent-skills

31

4

architecture-decision-records Captures architectural decisions as lightweight ADRs with detailed rationale, optional expanded sections, scaffolding…

akindu23/my-agent-skills

28

5

improve-codebase-architecture Architecture review: scan a codebase for deepening opportunities, present them as a visual HTML report, then grill th…

akindu23/my-agent-skills

28

6

karpathy-guidelines Strict coding discipline — think before coding, simplify, surgical changes only, verifiable success criteria.

akindu23/my-agent-skills

28

7

handoff Writes a compact handoff to docs/handoffs/CURRENT.md from the current Agent chat so a new session or another agent ca…

akindu23/my-agent-skills

27

8

grill-me A relentless interview to sharpen a plan or design.

akindu23/my-agent-skills

21

9

recursive-decomposition Based on Recursive Language Models (RLM) research (Zhang, Kraska, Khattab, 2025), this skill guides handling tasks th…

akindu23/my-agent-skills

19

10

best-practices-research Runs recon on current best practices for a language, framework, or domain via live web search before implementing. Us…

akindu23/my-agent-skills

18

11

document Creates or updates durable project documentation—README sections, architecture docs, API docs, examples, migration no…

akindu23/my-agent-skills

18

12

grill-with-docs Stateful interview to sharpen a plan or design against this codebase — updates CONTEXT.md and offers ADRs via domain-…

akindu23/my-agent-skills

18

13

grilling Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building…

akindu23/my-agent-skills

18

14

codebase-design Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find…

akindu23/my-agent-skills

17

15

diagnosing-bugs Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports …

akindu23/my-agent-skills

17

16

to-prd Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis.

akindu23/my-agent-skills

17

17

domain-modeling Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous la…

akindu23/my-agent-skills

16

18

golang Routes Go work to the right reference guides and conventions for the task. Use when working on Go architecture, imple…

akindu23/my-agent-skills

16

19

implement-plan Heavy one-shot implement of an attached plan (council → best practices → Karpathy → YAGNI).

akindu23/my-agent-skills

16

20

postgres-patterns PostgreSQL patterns for SQL, migrations, schema design, indexing, RLS, and query/ops diagnostics. Use when writing or…

akindu23/my-agent-skills

16

21

prototype Build a throwaway prototype to flesh out a design — a shareable HTML demo for state/business-logic questions, or seve…

akindu23/my-agent-skills

16

22

triage Move issues on the project issue tracker through a state machine of triage roles.

akindu23/my-agent-skills

16

23

to-issues Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet verti…

akindu23/my-agent-skills

15

24

docker-patterns Applies Dockerfile, Docker Compose, BuildKit, and container security patterns for local development and hardened depl…

akindu23/my-agent-skills

14

25

caveman Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keepi…

akindu23/my-agent-skills

13

26

frontend-design Distinctive, intentional visual design when building new UI or reshaping an existing one.

akindu23/my-agent-skills

13

27

setup-matt-pocock-skills Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo…

akindu23/my-agent-skills

13

28

tdd Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, me…

akindu23/my-agent-skills

13

29

mermaid Authors Mermaid diagram source for documentation and technical communication (flowcharts, sequences, class/ER/C4/stat…

akindu23/my-agent-skills

11

30

review Reviews changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (whether the code…

akindu23/my-agent-skills

11

31

code-simplifier Simplifies code for clarity, consistency, and maintainability while preserving exact behavior, using project standard…

akindu23/my-agent-skills

10

32

decision-mapping Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.

akindu23/my-agent-skills

10

33

frontend-slides Create animation-rich HTML presentations from scratch or by converting PowerPoint files.

akindu23/my-agent-skills

10

34

gpt-taste Awwwards-level GSAP marketing/landing page design with strict editorial typography and motion discipline.

akindu23/my-agent-skills

10

35

prompt-optimizer Analyzes raw prompts, surfaces intent and gaps, maps them to Cursor context (AGENTS.md, Rules, Agent Skills via /name…

akindu23/my-agent-skills

10

36

python-patterns Applies Python idioms, PEP 8 norms, typing, packaging, concurrency, tooling, and performance discipline to everyday P…

akindu23/my-agent-skills

10

37

web-design-guidelines Reviews UI code for Web Interface Guidelines compliance. Use when the user asks to "review my UI", "check accessibili…

akindu23/my-agent-skills

10

38

design-taste-frontend Architects premium React/Next.js interfaces with metric-based baselines (design variance, motion, visual density), st…

akindu23/my-agent-skills

9

39

zoom-out Produces a higher-level map of relevant modules, callers, and domain vocabulary when a code area is unfamiliar. Use w…

akindu23/my-agent-skills

9

40

diagnose Runs a disciplined diagnosis loop for hard bugs, flaky failures, and performance regressions—reproduce, minimise, hyp…

akindu23/my-agent-skills

8

41

yagni YAGNI mode - shortest working solution, climb the ladder, until stopped.

akindu23/my-agent-skills

7

42

teach Teaches the user a topic over multiple sessions using a grounded learning workspace under docs/learning/, with Exa-ve…

akindu23/my-agent-skills

6

43

supabase-postgres-best-practices Postgres performance and schema guidance from Supabase: queries, indexes, connection pooling, RLS, and monitoring. Us…

akindu23/my-agent-skills

5

44

vercel-react-best-practices React and Next.js performance rules from Vercel Engineering (RSC, data fetching, bundle size, re-renders, waterfalls)…

akindu23/my-agent-skills

5

45

coding-standards Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detaile…

akindu23/my-agent-skills

3

46

humanizer Rewrites text to remove AI-generated tells (significance inflation, promo tone, superficial -ing phrases, vague attri…

akindu23/my-agent-skills

3

47

golang-pro Guides high-performance and concurrent Go patterns including goroutines, channels, generics, gRPC, and microservice-o…

akindu23/my-agent-skills

2

48

mermaid-diagrams Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or…

akindu23/my-agent-skills

2

49

redesign-existing-projects Audits existing sites and apps for generic AI-era patterns, then applies premium design upgrades without a full rewri…

akindu23/my-agent-skills

2

50

research Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Us…

akindu23/my-agent-skills

2