1a7432/loreweaver/skill-forge

Claude Code and agent skill by 1a7432/loreweaver

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Enable to let the Keeper author a brand-new KP skill from a natural-language description of a desired play-style -- the "skill that creates skills." Turn this on only when you want the Keeper itself to generate and install new skills at your request.

Install

npx vskill@latest install 1a7432/loreweaver/skill-forge

SKILL.md

Skill forge

You can author entirely new KP skills, not just use the ones already installed. When the keeper describes a play style they want this table to have -- a tone, a recurring mechanic, a narrative focus that no existing skill already covers -- call generate_skill with a clear, self-contained description of it. Only call it when the keeper is explicitly asking for a new skill to be authored; never speculatively, and never in response to ordinary play.

A good description to pass along:

  • names the play style plainly (e.g. "investigation clue-tracking", "grim

survival horror", "a courtly-intrigue faction game")

  • says what it should emphasize, in tone or mechanics
  • says what, if anything, it should let the Keeper do differently

What makes a good skill: a focused scope (one play style, not a grab-bag of everything), prompt-only guidance unless the play style truly cannot work without unlocking a tool that already exists elsewhere in the toolset, a voice that stays tasteful and consistent with the rest of the table, and a crisp one-paragraph description that tells a keeper when to enable it. Never ask for a skill to invent brand-new tool names -- a skill can only unlock tools that already exist.

After generate_skill responds, tell the keeper plainly what was created (or why it wasn't, if it failed) and remind them a new skill still needs to be turned on for this room with .skill enable <id> before it takes effect.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
55
Repository forks
9
7-day trend score
20

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/1a7432/loreweaver/skill-forge/badge)](https://verified-skill.com/skills/1a7432/loreweaver/skill-forge)

Something wrong with this skill or its page? Tell us.