Vahlame

18 mods across 1 repository, 4 stars between them.

Vahlame/create-vkm-kit

Instructions file GitHub Copilot

Copilot instructions for Vahlame/create-vkm-kit, a project described as: Cross-platform kit that gives AI agents (Claude Code, Codex, Cursor) persistent memory: Markdown vault + git + MCP. Local-first, hybrid search optional.

4 11d ago A 4 tokens

Vahlame/create-vkm-kit

Instructions file CodexOpenCode

AGENTS.md instructions for Vahlame/create-vkm-kit, covering agents.md, project overview, installing this kit for a user (when told "install it"), setup commands and install js deps (workspace root).

4 11d ago B 6,815 tokens

Vahlame/create-vkm-kit

Instructions file

Claude Code instructions for Vahlame/create-vkm-kit, a project described as: Cross-platform kit that gives AI agents (Claude Code, Codex, Cursor) persistent memory: Markdown vault + git + MCP. Local-first, hybrid search optional.

4 11d ago A 3 tokens

vkm-implementer

09

Vahlame/create-vkm-kit

Agent

Terse minimal-diff executor for well-specified implementation tasks. Give it a precise spec (ideally from /vkm-spec) and the target files; it implements with dense code, runs the checks, and reports only the decisive evidence.

4 11d ago A 55 tokens

vkm-implementer

10

Vahlame/create-vkm-kit

Agent

Terse minimal-diff executor for well-specified implementation tasks. Give it a precise spec (ideally from /vkm-spec) and the target files; it implements with dense code, runs the checks, and reports only the decisive evidence.

4 11d ago A 55 tokens

vkm-design

11

Vahlame/create-vkm-kit

Skill Claude CodeCodex

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.

4 11d ago A 69 tokens

vkm-discipline

12

Vahlame/create-vkm-kit

Skill Claude CodeCodex

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.

4 11d ago A 72 tokens

vkm-intake

13

Vahlame/create-vkm-kit

Skill Claude CodeCodex

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.

4 11d ago A 62 tokens

vkm-research

14

Vahlame/create-vkm-kit

Skill Claude CodeCodex

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.

4 11d ago A 74 tokens

vkm-seo

15

Vahlame/create-vkm-kit

Skill Claude CodeCodex

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.

4 11d ago A 76 tokens

vkm-spec

16

Vahlame/create-vkm-kit

Skill Claude CodeCodex

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.

4 11d ago A 67 tokens

vkm-ui-judge

17

Vahlame/create-vkm-kit

Skill Claude CodeCodex

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.

4 11d ago A 0 tokens

vkm-verify

18

Vahlame/create-vkm-kit

Skill Claude CodeCodex

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.

4 11d ago A 70 tokens