AGENT SKILL

magic-quill

暂无简介

License 许可
MIT
最近更新
2026-06-07
Stars
★ 0
Forks
1

03 SKILL.md 正文

Magic Quill

A magical quill that inscribes themed spell mappings for OpenClaw Spellbook with high coverage for popular skills.

Inputs

  • --topic <name> or --url <https://...> (primary inputs; spell-list lookup searches by topic/theme first, and --url is treated as a high-priority reference candidate when provided)
  • Optional --theme <name> to override the final theme name (or run heuristic-only mode with just --theme)
  • Optional --out <path> (alias: --output) (default: spells/<theme-slug>.yaml)
  • Optional --limit <n> (alias: --top) for top-N coverage (default: 50)
  • Optional --author <name> (default: @magic-quill)

What To Do

  1. Gather popular skills from both sources when possible:
    • skills.sh trending installs
    • ClawHub downloads API endpoint
  2. Merge and de-duplicate the results into a target set (fill gaps from built-in fallback skills if fetch fails).
  3. Gather spell-list references first (primary spell source):
    • Build dynamic web search queries from topic/theme (for example <topic> spell list and <topic> spells api)
    • Parse top search result links (DuckDuckGo HTML results) into candidate reference URLs
    • Include --url as a high-priority candidate when present
    • Fetch discovered JSON/HTML references (for example dnd5eapi.co if discovered), extract spell names, and merge/de-duplicate names from successful references
  4. Gather lore/context (secondary style keywords only):
    • If --url is provided, fetch and extract page text
    • Else if --topic is provided, try Wikipedia summary API
    • If fetch fails, use built-in theme lexicon/heuristics
  5. If spell-list references fail or do not produce enough names, generate spell mappings with the built-in heuristic spell-name generator.
  6. Write YAML to the requested output path (usually under spells/), including # spell-list-references: comment links for successful dynamically discovered spell-list sources/endpoints when available.
  7. Validate with npm run validate:spells if the output file is under spells/.

Commands (Users)

npm run generate:spellbook-theme -- --theme "Studio Ghibli" --limit 50 --author "@you"
npm run generate:spellbook-theme -- --topic "Cyberpunk 2077" --limit 75 --out spells/cyberpunk-2077.yaml --author "@you"
npm run generate:spellbook-theme -- --url "https://en.wikipedia.org/wiki/The_Lord_of_the_Rings" --limit 50 --author "@you"
npm run generate:spellbook-theme -- --topic "DnD 5e" --limit 20 --author "@you"

Commands (Agents)

node magic-quill/scripts/generate-spell-mapping.mjs --theme "The Legend of Zelda" --topic "The Legend of Zelda" --limit 50 --out spells/zelda.yaml --author "@example"
node scripts/validate-spells.mjs

Install From This Repo (Subpath)

Use a repo subpath source with npx skills add, for example:

npx skills add wynnsu/openclaw-spellbook/magic-quill

⚠️ Requires Hook for Use

This skill generates spell YAML mapping files — to actually use the themed spells in agent sessions, you need the openclaw-spellbook hook installed. Install the full spellbook package:

# Install the spellbook hook (includes magic-quill skill)
npx skills add wynnsu/openclaw-spellbook

Or install just the hook directly from the repo:

npx skills add wynnsu/openclaw-spellbook/hooks/spellbook

The hook handles the translation between magical spell names and actual skill IDs at runtime.

Usage after install (example prompt):

Use magic-quill to create a Star Wars spell mapping with top 50 coverage and write it to spells/star-wars.yaml.

04 同仓库更多 Skills

javimosch
javimosch/open-claw-skills

crowd-prompting

A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.

★ 0
javimosch
javimosch/open-claw-skills

ceaser

Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).

★ 0
javimosch
javimosch/open-claw-skills

ceaser-send

Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.

★ 0
javimosch
javimosch/open-claw-skills

dilemm-ai

Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).

★ 0
javimosch
javimosch/open-claw-skills

moldium

Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.

★ 0
javimosch
javimosch/open-claw-skills

arxiv-paper-reviews

Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.

★ 0