1a7432/loreweaver/rule-forge
Claude Code and agent skill by 1a7432/loreweaver
- community
Checking that the SKILL.md file is still in the repository.
Enable to let the Keeper author a brand-new TTRPG rule system (a rulepacks/<id>.yaml data pack) from a natural-language description of its sheet and checks. Turn this on only when you want the Keeper itself to generate and install a new rule system at your request.
Install
npx vskill@latest install 1a7432/loreweaver/rule-forgeSKILL.md
Rule forge
You can author an entirely new TTRPG rule system, not just play the ones already installed (coc7, dnd5e). When the keeper describes a rule system they want available -- its core attributes/skills, how a check succeeds or fails, and any derived stats it needs -- call generate_rulepack with a clear, self-contained description of it. Only call it when the keeper is explicitly asking for a new rule system to be authored; never speculatively, and never in response to ordinary play.
CoC 7e and D&D 5e are the reference packs: both are just rulepacks/<id>.yaml data files, so a good description gives the same kind of detail their own sheets have.
A good description to pass along:
- names the system plainly (genre, tone, or the real TTRPG it's modeling, if any)
- lists its core attributes/skills and roughly what a starting character's values look like
- says how a check is resolved (roll-under, roll-over a target, dice-pool successes, ...)
- names any derived stats it needs (health, a damage bonus, per-attribute modifiers, ...) and, if
you know it, roughly how each should be computed
What makes a good rule system: internally consistent math, sensible starting defaults for every stat, and derived stats expressed as data wherever possible rather than reaching for a named code computer. generate_rulepack will refuse (writing nothing) if the generated pack doesn't parse, if its derived stats don't compile through the safe formula vocabulary, or if its id would collide with a built-in system.
After generate_rulepack responds, tell the keeper plainly what was created (or why it wasn't, if it failed) and note that the new system is now discoverable by its id/names.
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
- SKILL.md in the repositoryCheckingskills/rule-forge/SKILL.md
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
[](https://verified-skill.com/skills/1a7432/loreweaver/rule-forge)