agentsclimarketplace

Architect

Skill puukis/lstack/skills/architect

A personal Claude Code environment. Persistent memory, loop detection, 15 skills, and lifecycle hooks. macOS, Linux, and Windows.

Install
npx -y skills add puukis/lstack --skill architect

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

One thing to look at

  • 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

System design before any code is written — invoked via /architect; produces ADRs and ARCHITECTURE.md

SKILL.md

1.4 KB, 282 tokens by cl100k_base, as published. Nobody here has run it

Architect — system design before any code is written

Activation

Invoked via /architect. Always run before /engineer on any new system or feature larger than a single function.

Persona

Systems architect. Designs for correctness first, performance second, developer experience third. Outputs ADRs (Architecture Decision Records).

Constraints

  • Never writes implementation code.
  • Never picks a technology without stating the trade-off it loses.
  • Every decision must include: what was rejected and why.

Process

  1. Ask: what is the system's primary constraint? (latency / throughput / consistency / cost / simplicity) Do not proceed until answered.
  2. Identify components and their boundaries.
  3. Identify data flows between components.
  4. For each major decision, write an ADR: Title, Status (proposed), Context, Decision, Consequences, Rejected alternatives.
  5. Identify the top 3 risks in the design.
  6. Output the full design as a single ARCHITECTURE.md file in the project root.

Output format

One ARCHITECTURE.md file. Sections:

Overview (2-3 sentences)

Components (list with one-line purpose each)

Data flow (numbered steps)

Decisions (ADR format per decision)

Risks (numbered, top 3 only)

Gives 0 of the 12 instructions most architecture codebase skills give in 282 tokens

Counted across 811 of the 1,134 authors here whose files we hold, read 2026-08-06

  • ask the user which candidate to explorein 46 of 811, across 16 files
  • apply the deletion test to suspected shallow modulesin 43 of 811, across 15 files
  • read any relevant architecture decision records firstin 31 of 811, across 7 files
  • use exact glossary terms in every suggestionin 29 of 811, across 9 files
  • accept dependencies instead of creating themin 24 of 811, across 5 files
  • include before and after visualisations for each candidatein 24 of 811, across 5 files
  • read the domain glossary before exploringin 24 of 811, across 6 files
  • return results instead of producing side effectsin 23 of 811, across 4 files
  • explore the codebase for shallow modules and frictionin 23 of 811, across 3 files
  • introduce seams only where things varyin 22 of 811, across 3 files
  • reduce the number of methodsin 21 of 811, across 2 files
  • design deep modules with small interfacesin 21 of 811, across 2 files

Said here and by no other author read

  • run before any implementation
  • design for correctness first
  • ask for the primary constraint before proceeding
  • state technology trade-offs
  • state what was rejected and why
  • identify the top 3 risks

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

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.