Vahlame/create-vkm-kit

Vahlame/create-vkm-kit

Skill Claude Code

Professional, anti-generic design for REAL design work — a new surface, redesign, identity, dataviz, or critique. Forces a 3-line brief, live precedents (not this skill's menu), a named direction, computed checks, verified libraries. NOT for one-line tweaks or logic with no visible surface.

Vahlame/create-vkm-kit

Skill Claude Code

Use when implementing, fixing, refactoring, migrating, debugging, deploying, cleaning data, reviewing a PR, or writing a postmortem/README — reads intent, scales depth to stakes, ends in executed evidence. NOT one-line single-file edits (typo, bump), questions, explainers, or scope the user set.

Vahlame/create-vkm-kit

Skill Claude Code

Task intake BEFORE non-trivial execution. Restate objective, deliverable and non-goals in 3 lines, one closed question max on ambiguity, inventory what attached images actually show, assemble minimal context, then execute exactly that scope. NOT for one-line edits or tasks already scoped.

Vahlame/create-vkm-kit

Skill Claude Code

Consolidates a RESEARCH/ bank into a quality summary.md — reads hub + unconsolidated sources, synthesizes with wikilinks + supersedes, validates, marks done. Imports external reports. Invoke for "consolidate ", "write up the research on X", or after obscuraresearch persisted sources.

Vahlame/create-vkm-kit

Skill Claude Code

Use when building, auditing, or optimizing how a website ranks in search and AI answers — "audit my SEO", "why don't we rank", meta/title/schema fixes, local/multi-location pages, synonym/intent coverage, GEO/AEO. Ships a before/after audit. NOT paid ads/SEM, social, rank tracking, or non-web.

Vahlame/create-vkm-kit

Skill Claude Code

Turns a vague idea into a precise, testable, vault-grounded spec before any code — one assemblecontext call, a filled template, machine validation, human review. Use when the user says "spec this", "write a spec", "plan this feature", or hands over an idea that needs requirements first.

Vahlame/create-vkm-kit

Skill Claude Code

Measured visual judgment for ANY GUI. Web: live-page audit (viewports × light/dark, WCAG contrast, overflow, tap targets, insets, overlap, component drift). Flutter: generated a11y tests. Other native: screenshot-evidence loop. Fix by severity, before/after proof.

Vahlame/create-vkm-kit

Skill Claude Code

Prove a green check actually ran, covered the change, and can fail. Use before claiming done / tests pass / CI green / committed / deployed, when a guard or lint has never once fired, or when a pass contradicts a symptom the user still sees. NOT for writing tests or debugging a known-red failure.