agentsclimarketplace

Architecture

Skill IcodeNet/agent-skills/skills/architecture

40 portable full-SDLC agent skills for Claude Code, Cursor, Codex, and GitHub Copilot — deep-work autonomy, contract-guard for external interfaces, TDD, code review, PR babysitting. Install: npx github:IcodeNet/agent-skills

Install
npx -y skills add IcodeNet/agent-skills --skill architecture

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 26 days oldThe repository was created 26 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Facilitates design decisions and trade-off records. Use when choosing between approaches, designing a module or seam, asking "should we use X", or needing an architecture decision before coding. Do not use for bug fixes, broad tech-debt scans, or greenfield system design from a blank slate.

SKILL.md

1.8 KB, as published. Nobody here has run it

Architecture

Decide deliberately. Record the why. Prefer deepening existing seams over new layers.

Related skills

  • Broad codebase deepening / tech-debt scan → tech-debt or improve-codebase-architecture
  • Greenfield service / API / data model → system-design
  • Domain grilling with living docs → grill-with-docs

Workflow

  1. Frame the decision — one-sentence problem; hard constraints (time, security, multi-tenant, platforms).
  2. Read existing truth — architecture docs, ADRs, prior decisions. Do not re-litigate without new evidence.
  3. List 2–3 options — each with fit, complexity, testability, reversibility.
  4. Pick and justify — prefer deep modules (small interface, large behavior) and explicit seams.
  5. Record — short decision note or ADR. See references/adr-template.md for formal ADRs.
  6. Hand off — implementation tasks must be independently verifiable; no speculative abstractions.

Constraints

  • Do not change user-visible behavior under the guise of “architecture” unless the goal is a behavior change.
  • Keep PRs ticket-scoped: architecture work not required for the ticket goes elsewhere.
  • Extend canonical modules; do not duplicate contracts or shared helpers.

Verification

  • Problem and constraints stated
  • ≥2 options considered with trade-offs
  • Decision recorded (PR note or ADR)
  • Next implementation tasks are independently verifiable

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.