MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Use Horosa (星阙) local metaphysics MCP tools correctly — 110 techniques: Western astrology natal chart, solar return, progressions, primary directions, horary, electional 择日, birth-time…
Install Horosa Agent
$ npx skills add Horace-Maxwell/horosa-skill --skill horosa-agent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Horace-Maxwell/horosa-skill horosa-agent --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Horace-Maxwell/horosa-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/horosa-agent .claude/skills/horosa-agent && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "horosa-agent" agent skill from https://github.com/Horace-Maxwell/horosa-skill/tree/main/.agents/skills/horosa-agent into .claude/skills/horosa-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "horosa-agent", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Horace-Maxwell/horosa-skill/tree/main/.agents/skills/horosa-agentType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Horace-Maxwell/horosa-skill --skill horosa-agent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Horace-Maxwell/horosa-skill horosa-agent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Horace-Maxwell/horosa-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/horosa-agent .agents/skills/horosa-agent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "horosa-agent" agent skill from https://github.com/Horace-Maxwell/horosa-skill/tree/main/.agents/skills/horosa-agent into .agents/skills/horosa-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "horosa-agent", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Horace-Maxwell/horosa-skill --skill horosa-agent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Horace-Maxwell/horosa-skill horosa-agent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Horace-Maxwell/horosa-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/horosa-agent .cursor/skills/horosa-agent && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "horosa-agent" agent skill from https://github.com/Horace-Maxwell/horosa-skill/tree/main/.agents/skills/horosa-agent into .cursor/skills/horosa-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "horosa-agent", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Horace-Maxwell/horosa-skill.git --path .agents/skills/horosa-agent--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Horace-Maxwell/horosa-skill --skill horosa-agent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Horace-Maxwell/horosa-skill horosa-agent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Horace-Maxwell/horosa-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/horosa-agent .gemini/skills/horosa-agent && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "horosa-agent" agent skill from https://github.com/Horace-Maxwell/horosa-skill/tree/main/.agents/skills/horosa-agent into .gemini/skills/horosa-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "horosa-agent", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Horace-Maxwell/horosa-skill horosa-agentInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Horace-Maxwell/horosa-skill --skill horosa-agent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Horace-Maxwell/horosa-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/horosa-agent .github/skills/horosa-agent && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "horosa-agent" agent skill from https://github.com/Horace-Maxwell/horosa-skill/tree/main/.agents/skills/horosa-agent into .github/skills/horosa-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "horosa-agent", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Horace-Maxwell/horosa-skill --skill horosa-agent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Horace-Maxwell/horosa-skill horosa-agent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Horace-Maxwell/horosa-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/horosa-agent .opencode/skills/horosa-agent && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "horosa-agent" agent skill from https://github.com/Horace-Maxwell/horosa-skill/tree/main/.agents/skills/horosa-agent into .opencode/skills/horosa-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "horosa-agent", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
horosa-agent- GitHub stars
- 450
- Token cost
- ~1.1k tokens
- SKILL.md length
- 423 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- AGPL-3.0-only
At a glance
Use Horosa (星阙) local metaphysics MCP tools correctly — 110 techniques: Western astrology natal chart, solar return, progressions, primary directions, horary, electional 择日, birth-time…
- Works in 6 steps: Never hand-calculate any Horosa/星阙… → Clarify before calling: if a… → Read results only from… → …
- 起盘 排盘 起课 起卦 算命 推运 看盘 合盘 卜卦 择日 生时校正
- SKILL.md covers Non-negotiable rules and Shell-only agents (no MCP)
- Calls codex and uv
What it does
Horosa Agent is an agent skill from Horace-Maxwell/horosa-skill. Use Horosa (星阙) local metaphysics MCP tools correctly — 110 techniques: Western astrology natal chart, solar return, progressions, primary directions, horary, electional 择日, birth-time rectification, 八字 bazi, 紫微斗数 ziwei, 大六壬, 奇门遁甲 qimen, 太乙, 金口诀, 六爻, 梅易卦义, 河洛理数, 铁板神数, 塔罗 tarot, 天文地占 geomancy, 老黄历, AstroCartoGraphy, celebrity birth data, Chinese esoteric history. Trigger on 起盘 排盘 起课 起卦 算命 推运 看盘 合盘 卜卦 择日 生时校正, fortune-telling, divination, chart casting, or any Horosa/星阙 reading. Never hand-calculate.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering MCP servers. The repository describes itself as: 让你的 AI 本地挂载一个玄学家：92 个术数/占星技法全部离线本地算（MCP + CLI）。西占本命·转盘·中点·调波·巴比伦·印占·20+ 推运·主限·卜卦·择日·占星地图·合盘｜八字·紫微·大六壬·奇门遁甲·法奇门·奇门择日·太乙·金口诀·三式合一｜六爻·河洛理数·邵子参评数·一掌经·小六壬·飞宫小奇门·小成图·皇极轨策·统摄法·宿占·灵棋经｜14… The licence is AGPL-3.0-only.
When your agent uses it
- 起盘 排盘 起课 起卦 算命 推运 看盘 合盘 卜卦 择日 生时校正
- Fortune-telling
- Any Horosa/星阙 reading
Example prompts
- “/horosa-agent”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Never hand-calculate any Horosa/星阙 technique (no shell/Python/JS/web formulas, no memorized
- Clarify before calling: if a result-changing setting is missing (birth/event time, place,
- Read results only from export_snapshot.export_text / .sections — that text is the chart.
- If horosa tools are absent from the tool list: first turn after a cold start may simply be too
- Errors carry structured recovery: on details.agent_recovery, relay prompt_to_user verbatim
- Compact surface. Codex gets the 11 facade tools by default (HOROSA_MCP_COMPACT=1); call any technique
What it can do on your machine
Read from SKILL.md and the folder at commit 7ba3ab6. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
codexuv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Horosa Agent loads about 1.1k tokens when it runs. Until then it costs about 129 tokens; SKILL.md has 423 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Horace-Maxwell/horosa-skill at commit 7ba3ab6, republished under its AGPL-3.0-only licence (© Horace-Maxwell). 423 words, ~1,092 tokens.
Download SKILL.mdSave it as
.claude/skills/horosa-agent/SKILL.md (or your agent's skills folder).- name
- horosa-agent
- description
- Use Horosa (星阙) local metaphysics MCP tools correctly — 110 techniques: Western astrology natal chart, solar return, progressions, primary directions, horary, electional 择日, birth-time rectification, 八字 bazi, 紫微斗数 ziwei, 大六壬, 奇门遁甲 qimen, 太乙, 金口诀, 六爻, 梅易卦义, 河洛理数, 铁板神数, 塔罗 tarot, 天文地占 geomancy, 老黄历, AstroCartoGraphy, celebrity birth data, Chinese esoteric history. Trigger on 起盘 排盘 起课 起卦 算命 推运 看盘 合盘 卜卦 择日 生时校正, fortune-telling, divination, chart casting, or any Horosa/星阙 reading. Never hand-calculate.
- license
- AGPL-3.0-only
Horosa Agent Skill (Codex / agentskills.io entry)
Thin client-agnostic contract. The single policy source is
skills/horosa-agent/SKILL.md — read it
(and its references/) before deep work. Maintainer/repo law: AGENTS.md.
Non-negotiable rules
- Never hand-calculate any Horosa/星阙 technique (no shell/Python/JS/web formulas, no memorized
tables). Every 盘/课/卦/运 comes from a
horosaMCP tool call (horosa_astro_chart,horosa_cn_qimen,horosa_cn_liureng_gods, …) or thehorosa-skillCLI. - Clarify before calling: if a result-changing setting is missing (birth/event time, place,
timezone, gender, house system, 起局方式, 贵人体系, target year), ask the user a short question
with options first. Tools reject unconfirmed calls with
agent_guidance.required; after the user answers, retry withagent_confirmed_settings: true(ordefaults_accepted: truewhen they accept defaults) plusclarification_notes. Never self-confirm; never switch tools to bypass the gate. In non-interactive runs (codex exec), surface the question as your final answer instead of guessing. - Read results only from
export_snapshot.export_text/.sections— that text is the chart. Do not restate numbers that are not in it, and do not invent sections it lacks. - If
horosatools are absent from the tool list: first turn after a cold start may simply be too early (Codex waits ~1s for optional servers; the runtime warms in ~45s) — retry next turn. Still absent → the server is not configured; point the user atexamples/clients/codex.md. - Errors carry structured recovery: on
details.agent_recovery, relayprompt_to_userverbatim and stop. On transport errors, suggesthorosa-skill doctor/horosa-skill selfcheck. - Compact surface. Codex gets the 11 facade tools by default (
HOROSA_MCP_COMPACT=1); call any technique by name viahorosa_tool_run(tool_name="qimen", …)— the catalogue is thehorosa://catalog/techniquesresource. A missing flathorosa_*name is not a missing technique.
Show full SKILL.md (160 more words)Show less
Shell-only agents (no MCP)
codex exec without MCP, CI bots, plain shell tools: the CLI carries the same contract. Parse stdout only
(exactly one JSON document; progress lines and error envelopes go to stderr). On Windows PowerShell 5.1 pass
payloads as --input / --output files, never through the pipe (it re-encodes bytes and mangles Chinese).
| Need | Command |
|---|---|
Tool names + aka: aliases | horosa-skill tool list |
| What to confirm before a call | horosa-skill agent guidance --tool qimen |
| Run one technique | horosa-skill tool run qimen --input payload.json --output result.json |
| Natural-language routing | horosa-skill dispatch --input query.json --output result.json |
| One-command onboarding on a fresh machine | horosa-skill setup --client codex (uv run horosa-skill setup --client codex inside a checkout) |
Exit 2 + stderr code: "agent_guidance.required" = ask the user with details.agent_recovery.prompt_to_user,
then rerun with agent_confirmed_settings: true + clarification_notes (or defaults_accepted: true only when
the user explicitly accepts defaults). Exit 0 with ok: false = a real engine error (error.code), not a missing
technique. Read results only from data.export_snapshot.export_text; quote data.technique_card afterwards.
© Horace-Maxwell, AGPL-3.0-only. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/horosa-agent of Horace-Maxwell/horosa-skill.
Open the folder on GitHubat commit 7ba3ab6
Compare with similar skills
Horosa Agent next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Horosa Agent this skillHorace-Maxwell/horosa-skill | 450 | — | ~1.1k | Automated safety check: Pass | AGPL-3.0-only | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Microsoft Skill CreatorMicrosoftDocs/mcp | 1.9k | 3 repos | ~2.1k | Automated safety check: Pass | CC-BY-4.0 | |
| Crush Configurationcharmbracelet/crush | 29k | — | ~3.7k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
- Official
MCP Integration for Plugins
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
- Official
Microsoft Skill Creator
MicrosoftDocs/mcp
Create agent skills for Microsoft technologies using official documentation.
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
More from Horace-Maxwell/horosa-skill
Horosa Agent
Horace-Maxwell/horosa-skill
Call Horosa (星阙) local metaphysics tools correctly over MCP or CLI — 110 real techniques: Western natal/predictive astrology (returns, progressions, primary directions, horary 卜卦, election 择日), 八字…
Related
Categories
Questions about Horosa Agent
What does Horosa Agent do?
Use Horosa (星阙) local metaphysics MCP tools correctly — 110 techniques: Western astrology natal chart, solar return, progressions, primary directions, horary, electional 择日, birth-time…. Horosa Agent is an agent skill from Horace-Maxwell/horosa-skill. Use Horosa (星阙) local metaphysics MCP tools correctly — 110 techniques: Western astrology natal chart, solar return, progressions, primary directions, horary, electional 择日, birth-time rectification, 八字 bazi, 紫微斗数 ziwei, 大六壬, 奇门遁甲 qimen, 太乙, 金口诀, 六爻, 梅易卦义, 河洛理数, 铁板神数, 塔罗 tarot, 天文地占 geomancy, 老黄历, AstroCartoGraphy, celebrity birth data, Chinese esoteric history.
When should I use Horosa Agent?
Horosa Agent fits situations like: 起盘 排盘 起课 起卦 算命 推运 看盘 合盘 卜卦 择日 生时校正; fortune-telling; any Horosa/星阙 reading.
How do I install Horosa Agent in Claude Code?
Run `npx skills add Horace-Maxwell/horosa-skill --skill horosa-agent -a claude-code`. Or copy the skill folder (.agents/skills/horosa-agent in Horace-Maxwell/horosa-skill) into .claude/skills/horosa-agent in your project. Claude Code loads it when a task matches its description.
How do I install Horosa Agent in Codex?
Run `npx skills add Horace-Maxwell/horosa-skill --skill horosa-agent -a codex`. Or copy the skill folder (.agents/skills/horosa-agent in Horace-Maxwell/horosa-skill) into .agents/skills/horosa-agent in your project. Codex loads it when a task matches its description.
Can I use Horosa Agent in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Horace-Maxwell/horosa-skill --skill horosa-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/horosa-agent, .gemini/skills/horosa-agent, .github/skills/horosa-agent and .opencode/skills/horosa-agent in your project.
What does Horosa Agent need to run?
Going by SKILL.md and its folder, Horosa Agent needs the command-line tools its instructions call (codex and uv). Our summary lists: Python 3.
Does Horosa Agent access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Horosa Agent safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Horosa Agent use?
Horosa Agent is published under the AGPL-3.0-only licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Horosa Agent use?
About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Horosa Agent?
Skills that share tags, products or a category with Horosa Agent: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Microsoft Skill Creator (MicrosoftDocs/mcp, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Horosa Agent?
Horace-Maxwell (a GitHub user) maintains it in Horace-Maxwell/horosa-skill, which has 450 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 6, 2026.
Source: Horace-Maxwell/horosa-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.