w-architecture — Claude Code skill: planning and install
The w-architecture Claude Code skill plans an implementation structure against a project's architecture docs and ADRs. It runs on requests to plan a change.
MIT 647 installs ★ 1 updated 2026-10-02
npx skills add blockmatic-icebox/basilic-skills --skill w-architecture -a claude-codeWhat w-architecture does
w-architecture drafts an implementation-structure plan for a user request. It reads matching architecture MDX files and ADRs, separates implementation goals from nice-to-haves, and lists constraints, trade-offs, alternatives, and 3–5 assumptions. High-risk items are flagged for a human.
If the area has no reconciled exploration for the current turn, the skill first follows steps 1–3 of w-council. A lasting change to an architectural boundary belongs in the existing ADR and docs system; the skill must not create a second ADR tree. It returns the plan in chat unless the user provides a path, and it does not create a branch.
What it helps with
- plan the structure of an implementation
- check a proposed change against existing ADRs and architecture docs
- separate required goals from nice-to-haves
- record constraints, trade-offs, and assumptions
Example prompts for the agent
- Use w-architecture to plan the implementation structure for this change.
- Check this plan against the project's architecture MDX files and ADRs.
- Draft the plan and save it to
docs/architecture/plan.md.
How to install w-architecture
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-architecture -a claude-code2Manually: put the files in place
~/.claude/skills/w-architecture/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/w-architecture/
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-architecture -a codex2Manually: put the files in place
.agents/skills/w-architecture/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-architecture -a cursor2Manually: put the files in place
.cursor/skills/w-architecture/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install blockmatic-icebox/basilic-skills skills/workflow/w-architecture2Manually: put the files in place
.github/skills/w-architecture/SKILL.md1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-architecture -a gemini-cli2Platform CLI
gemini skills install https://github.com/blockmatic-icebox/basilic-skills --path skills/workflow/w-architectureManually: put the files in place
.devin/skills/w-architecture/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-architecture -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about w-architecture
How do I install w-architecture in Claude Code?
Run npx skills add blockmatic-icebox/basilic-skills --skill w-architecture -a claude-code. The skill file is at ~/.claude/skills/w-architecture/SKILL.md.
What does w-architecture do?
It creates an implementation plan grounded in the project's architecture docs and ADRs. The plan covers goals, trade-offs, alternatives, and assumptions.
Where does w-architecture save its plan?
It saves the result to a path supplied by the user. Without one, it returns the plan in chat.
Source text
SKILL.md · MIT
--- name: w-architecture description: Plan an implementation structure; durable decisions belong in ADRs and architecture docs. disable-model-invocation: true --- Produce an implementation-structure plan for the user's question. Durable system decomposition belongs in existing ADRs and architecture MDX. Do not mint a second ADR tree. Do not create a branch. 1. If this turn has no reconciled exploration for the area, follow [council](../w-council/SKILL.md) steps 1–3, then continue. 2. Read the matching architecture MDX and ADRs. If the change is a durable boundary, stop and document it in the existing ADR/docs system. 3. State implementation goals vs nice-to-haves. Stay inside the existing architecture unless the user already authorized a durable architecture decision. 4. List constraints, trade-offs, and alternatives that affect this change. Flag high-risk items for a human. State 3–5 assumptions. 5. Add Mermaid only when structure or flow is otherwise unclear. 6. Save only if the user gave a path; otherwise return in chat. Include Assumptions and **References** (plain paths). Commands and generated-source owners come from inspected docs.
© blockmatic-icebox · MIT · blockmatic-icebox/basilic-skills