Coding

Plugin coding from marketplace lightbridge-skills in Lightbridge-KS/agent-stuff. Commands read from the repo's manifest — 6 days ago.

Skills (23)

• agentic-architecture

  Explain an existing agentic system — an AI agent as the central "CPU" with its organs (loop, memory, tools, skills, MCP, subagents, hooks) — or design one from requirements. Use on name or near-match. version: "2026-09-24

• ax-interface

  The agent-experience ("AX") lens for any interface an AI agent drives — CLI, MCP server, REST API, or SDK. Audit an existing surface against the AX principles, or apply them while designing a new one. Use on name or near-match ("AX analysis", "agent-friendly interface"). For a whole-surface doc acro

• balanced-coupling

  Apply Vlad Khononov's balanced-coupling lens when explaining dependencies, designing module seams, or refactoring change propagation: weigh integration strength, distance, and volatility. version: "2026-10-23

• c4-architect

  Design a system as C4 diagrams (C1–C3) through phase-gated Q&A — ASCII inline, Mermaid to disk. Use when the user wants to design or model a system through dialogue, or mentions C4. For compiling already-settled inputs without elicitation, use `system-architecture` instead. version: "2026-08-15

• clean-architecture

  How I apply Clean Architecture + DDD — pragmatic, right-sized by complexity tier, reconciled with deep modules. Use when designing, reviewing, or refactoring a codebase's architecture or layering, deciding how much architecture a project needs, or whenever Clean Architecture / DDD / SOLID comes up.

• codebase-blueprint

  Reconcile settled design docs with each other and the chosen framework, then compile the object model that satisfies all of them — prose rules become machine-checked invariants. Use when design is settled and you are about to build, or on name / near-match. version: "2026-09-24

• codebase-design

  Shared vocabulary for designing deep modules — terms and principles, no document produced. Use when designing or improving a module's interface, placing a seam, or making code testable or AI-navigable; also loaded by other skills needing this vocabulary. For the pre-code object-model document, use `

• data-architecture

  Explain an existing codebase's data architecture — where data rests (stores, schema) and how it moves (dataflow, lineage) — or design one from requirements. One Markdown doc with Mermaid diagrams. Use on name or near-match. version: "2026-09-24

• design-md

  Author, extract, lint and export a repo's root DESIGN.md — the visual identity spec (Google design.md format: YAML design tokens + prose rationale) that any coding agent follows when building UI. Use when a repo needs a design system agents can follow across harnesses, when asked for design tokens,

• domain-modeling

  Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

• extensibility-architecture

  Explain how an existing system changes after it ships — runtime config, declarative composition, hooks, plugins, in-process extensions. version: "2026-09-24

• grill-with-docs

  A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

• harness-design

  Decide how much agent harness to own — off-the-shelf, middleware on one, a custom loop, or an explicit graph — from the task's distribution distance and its need for control; then shape what stays yours (instructions, skills, environment, evals) and the flywheel that improves it. Use when designing

• pr

  Git workflow: commit, push, and create/update a draft PR. If a PR exists for the current branch, update its body. Trigger: 'pr' or /pr.

• reproducible-codebase

  Remove hidden local-environment dependencies when writing, changing, or reviewing maintained code and scripts, or promoting experiments into maintained use. version: "2026-10-27

• security-architecture

  Explain an existing system's security architecture — what is worth protecting, where trust changes hands, what crosses each boundary uninvited, and which control (located in code) stops it — or design one from requirements. One Markdown threat-model doc with Mermaid diagrams. Use on name or near-mat

• surface-architecture

  Explain or design a codebase's user-facing surface — UX/DX/API from outside the boundary, for end user, developer, or agent. One Markdown doc with Mermaid diagrams. Use on name or near-match. version: "2026-09-24

• switch-pull-prune

  Git workflow: after a PR merges, switch to the base branch, pull, and prune the merged branch. Trigger: 'I've merged the PR' or /switch-pull-prune.

• system-architecture

  Explain an existing codebase's system architecture, or design one from a PRD or rough ideas — either way one C4-style Markdown doc with Mermaid diagrams. Use on name or near-match. version: "2026-09-24

• testability-architecture

  Explain how an existing system proves it works — the claims it must keep, which test level proves each, where seams let a test swap real for double, which gate runs it, and who judges (developer, CI, AI agent, end user) — or design that test architecture from requirements. One Markdown doc with Merm

• toy-example

  Explain or design an idea, pattern, or algorithm through the smallest code example that still shows the mechanism — a toy implementation. version: "2026-09-28

• write-for-the-clone

  Make durable repository documentation usable without the original session when writing or reviewing agent instructions, README files, docs, or runbooks. version: "2026-10-27

• yolo-ship

  Autonomous git workflow for low-risk work: commit → push → PR → watch CI → fix if red → merge when green → switch-pull-prune. OPT-IN ONLY: invoke only when the user explicitly says 'yolo ship' or /yolo-ship in the current turn — never self-select, never chain from another task.

Similar plugins