w-clarify — Claude Code skill: what it does, how to install
The w-clarify Claude Code skill finds missing decisions that could block correct work. It checks the request against the project’s code and documentation first.
MIT 647 installs ★ 1 updated 2026-10-02
npx skills add blockmatic-icebox/basilic-skills --skill w-clarify -a claude-codeWhat w-clarify does
w-clarify compares a request with the project’s code and documentation, then asks about gaps that could change the result. It looks through the README, relevant MDX files, and ADRs before raising questions.
The skill focuses on behavior, trust boundaries, and destructive operations. Reversible details are left out, and it proceeds with assumptions the user has already stated. Model-triggered invocation is disabled, so the agent will not start it on its own.
For a detailed decision-tree interview, the repository has w-grill; w-wayfinder is for unclear work that spans more than one session.
What it helps with
- find missing requirements that block correct work
- check whether the code or docs already answer a question
- surface gaps in behavior or trust boundaries
- skip questions about reversible details
Example prompts for the agent
- Use
w-clarifyto find requirements that block this task. - Check the request against the README and code with
w-clarify, then ask only the key questions. - Run
w-clarifyto look for gaps involving behavior or destructive operations.
How to install w-clarify
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-clarify -a claude-code2Manually: put the files in place
~/.claude/skills/w-clarify/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/w-clarify/
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-clarify -a codex2Manually: put the files in place
.agents/skills/w-clarify/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-clarify -a cursor2Manually: put the files in place
.cursor/skills/w-clarify/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install blockmatic-icebox/basilic-skills skills/workflow/w-clarify2Manually: put the files in place
.github/skills/w-clarify/SKILL.md1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-clarify -a gemini-cli2Platform CLI
gemini skills install https://github.com/blockmatic-icebox/basilic-skills --path skills/workflow/w-clarifyManually: put the files in place
.devin/skills/w-clarify/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-clarify -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-clarify
How do I install w-clarify in Claude Code?
Run npx skills add blockmatic-icebox/basilic-skills --skill w-clarify -a claude-code, then use ~/.claude/skills/w-clarify/SKILL.md.
What does w-clarify do?
It checks a request against the code, README, relevant MDX files, and ADRs. Then it asks about unresolved decisions that could prevent correct work.
How is w-clarify different from w-grill and w-wayfinder?
w-clarify limits questions to decisions that block the work. w-grill runs a detailed decision-tree interview, while w-wayfinder addresses unclear work that extends beyond one session.
Source text
SKILL.md · MIT
--- name: w-clarify description: Resolve consequential missing requirements from inspected context. disable-model-invocation: true --- Ask only for decisions that block correct work. Stay inside the request. Do not invent product scope. A relentless design-tree interview is [grill](../w-grill/SKILL.md). Fog bigger than one session is [wayfinder](../w-wayfinder/SKILL.md). 1. Inspect code, README, and matching MDX/ADRs for answers that already exist. 2. List remaining consequential gaps (behavior, trust boundary, destructive ops). Skip reversible details. 3. Ask the smallest set of questions. Continue with stated assumptions when the user already covered them.
© blockmatic-icebox · MIT · blockmatic-icebox/basilic-skills