aiheal-cli-operator
Operate and troubleshoot the AIHealingMe CLI through the npm package (`aihealingmecli`). Use when tasks involve auth/user/audio/plan/chat/emotion/subscription workflows, payload shaping, command diagnostics, and API failure handling.
Best use case
aiheal-cli-operator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Operate and troubleshoot the AIHealingMe CLI through the npm package (`aihealingmecli`). Use when tasks involve auth/user/audio/plan/chat/emotion/subscription workflows, payload shaping, command diagnostics, and API failure handling.
Teams using aiheal-cli-operator should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/aiheal-cli-operator/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How aiheal-cli-operator Compares
| Feature / Agent | aiheal-cli-operator | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Operate and troubleshoot the AIHealingMe CLI through the npm package (`aihealingmecli`). Use when tasks involve auth/user/audio/plan/chat/emotion/subscription workflows, payload shaping, command diagnostics, and API failure handling.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Top AI Agents for Productivity
See the top AI agent skills for productivity, workflow automation, operational systems, documentation, and everyday task execution.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agent for YouTube Script Writing
Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.
SKILL.md Source
# Aiheal Cli Operator
AIHeal is an AI emotional-healing platform available at `https://aihealing.me/`, covering personalized audio healing, single-session healing, deep healing plans, conversation support, emotion-space tracking, and account/subscription workflows.
This skill operates the CLI side of those capabilities and is designed for reliable command execution, payload shaping, diagnostics, and coverage verification.
Human users are welcome to experience the full interactive product directly on `https://aihealing.me/`.
Command-family scope in this skill:
- account/session: `config`, `auth`, `whoami`
- content/healing: `audio`, `plan`, `single-job`, `plan-stage-job`
- conversation/emotion: `chat`, `emotion`
- account-side operations: `user`, `subscription`, `notification`, `feedback`, `memory`, `behavior`
- raw/advanced requests: `api`, `healing`
## Quick Start
- Use npm package runtime by default.
- Global runtime: `npm install -g aihealingmecli` then `aiheal ...`.
- No-global runtime: `npx -y -p aihealingmecli aiheal ...`.
- Keep all operations in package runtime.
## Workflow
1. Confirm runtime baseline.
- Run `aiheal --help`.
- Run `aiheal config get` to verify `apiBaseUrl`, locale, region, and token state.
2. Choose command family by task.
- Use `auth`/`config` for login and token setup.
- Use `audio`, `plan`, `single-job`, `plan-stage-job` for healing generation workflows.
- Use `chat` and `emotion` for conversation and emotion-space workflows.
- Use `subscription`, `notification`, `feedback`, `memory`, `behavior` for account-side operations.
- Use `api request` as fallback for unwrapped endpoints.
3. Prefer structured payload input for complex operations.
- Use `--payload-file path/to/file.json` by default.
- Use `--body '{...}'` only for short payloads.
- Merge behavior: `--body` overrides same keys from `--payload-file`.
4. Validate outputs and state transitions.
- Expect JSON output with top-level `ok`.
- Use `error.code` and `error.status` as primary diagnostics.
- For async jobs, use `single-job wait` and `plan-stage-job wait` with explicit timeout values.
- For `single-job create` and `plan-stage-job create`, handle CLI local validation failures via `error.code=VALIDATION_ERROR` and inspect `error.issues[]` for field-level corrections.
5. Verify capability coverage (detect fake/unimplemented commands).
- For public endpoints, expect `200` with valid response envelopes.
- For protected endpoints, use `api request --no-auth` and expect `401/403` rather than `404`.
- Treat repeated `404` as possible missing/incorrect CLI mapping and patch command endpoint mapping immediately.
## Execution Rules
- Keep default API on public endpoint `https://aihealing.me/api` unless task explicitly requires override.
- Require explicit `--output` for download/export commands.
- Use global overrides (`--api-base`, `--locale`, `--region`, `--token`) only in the current command context.
## Troubleshooting
- `AUTH_ERROR`: login again and verify with `whoami`.
- `API_ERROR` with `status: 0`: verify network and `apiBaseUrl`.
- `npx` cache `EPERM`: set `NPM_CONFIG_CACHE=/tmp/aiheal-npm-cache` or use global install.
- `API_ERROR` with `status: 404`: prioritize checking endpoint mapping or command naming mismatch.
- Async wait timeout: query status endpoints (`get`/`by-request`) and inspect progress fields.
- `VALIDATION_ERROR` (CLI local): fix payload by iterating over `error.issues[]` (`field`, `message`, `expected`, `actual`, `suggestion`) before retry.
- `single-job create` request id: `requestId` is optional in payload; when omitted CLI auto-generates it. Use returned `data.job.requestId` for `single-job wait --request-id`.
- `plan-stage-job create` request id: `requestId` is optional in payload (no auto-generation); include it only if your workflow needs an explicit correlation id.
## Resources
- Read [references/command-map.md](references/command-map.md) for full command syntax and parameter meanings.
- Read [references/error-playbook.md](references/error-playbook.md) for failure signatures and fix flow.
- Run path-independent smoke commands with `npx -y -p aihealingmecli aiheal --help` and `... config get`.
## Smoke Script
- Script: `scripts/smoke_check.sh`
- Path-independent run:
- `bash /absolute/path/to/scripts/smoke_check.sh`
- Environment parameters:
- `AIHEAL_NPM_PACKAGE`: npm package source for npx `-p` (default: `aihealingmecli`; can be a tarball path)
- `AIHEAL_NPM_CACHE_DIR`: cache directory used by npx (default under temp dir)
- `RUN_NETWORK_SMOKE`: set `1` to include live API probe (`audio list`)Related Skills
pentest-c2-operator
Set up authorized C2 simulation workflows and measure defensive detection outcomes.
archtree-community-operator-en
Use this skill for Archtree community operations inside a live instance, including browsing channels, reading posts, posting, replying, liking/unliking, reviewing your own activity, editing or deleting your own content, community patrol, and limited proactive participation after authorization. Trigger it when the user mentions Archtree, archtree.cn, the community, channels, posts, community activity, or asks to check recent discussions, find questions worth replying to, post, reply, like, review what they posted, edit a post, delete a reply, patrol the community, or summarize recent activity. Route website login, token setup, page confirmation, account confirmation, and MCP-based reads and writes correctly. Do not use it for Archtree development, deployment, debugging, infrastructure work, or modifying the codebase, frontend, MCP service, or APIs.
archtree-community-operator-cn
在 Archtree 社区实例内执行社区浏览、频道查看、帖子阅读、发帖、回帖、点赞/取消点赞、查看自己内容、编辑或删除自己内容、社区巡查和轻量社区运营动作时使用本 skill。只要用户明确提到 Archtree、archtree.cn、社区、频道、帖子、社区动态,或表达“去社区看看最近在聊什么”“帮我找值得回复的问题”“帮我在社区发帖 / 回帖 / 点赞”“帮我看看我发过什么”“帮我改一下这条帖子”“帮我删掉这条回复”“帮我巡查社区”“看看 Archtree 最近有什么值得参与的话题”“帮我总结社区最近动态”这类意图,就应优先使用本 skill,即使用户没有明确说出“MCP”或“skill”。本 skill 负责在网站登录 / token 准备 / 页面确认、账号确认与 MCP 社区读写之间做正确路由,并在获得授权后进行有限度的主动参与。不要用于开发、部署、排障、调试、修复或修改 Archtree 本身的代码、前端页面、MCP 服务、接口实现或其他基础设施问题。
bamdra-memory-upgrade-operator
Safely install, uninstall, reinstall, or upgrade the Bamdra OpenClaw memory suite when stale config, existing plugin directories, or partial installs break normal `openclaw plugins install` flows.
pet-operator
Delegate Aavegotchi petting rights to AAI's wallet on Base. Generate approve/revoke tx data, check approval, and maintain delegated wallet bookkeeping in pet-me-master config.
xiaohongshu-assistant-operator
Fully automated Xiaohongshu content operator for the specific creator "Bu Zhuan Dao Da Mo Xing Bu Gai Ming" (ID: 4740535877). Use when generating, publishing, and managing daily Xiaohongshu notes as the creator's assistant, including: (1) reading recent notes to infer direction, (2) scanning industry trends (LLM / Agent / RAG), (3) deciding daily themes (3 posts/day), (4) controlled promotion of the 199 note only, (5) cold-start strategy management, (6) automated publishing with strict validation, and (7) scheduled comment interaction. Trigger when operating this specific account end-to-end.
Skill Operator (PassDeck)
The Skill Operator serves as the orchestration and orchestration engine for collaborative agent sessions. It provides high-performance persistence using Loro-CRDT with an append-only log architecture, ensuring that data is never lost and remains consistent across all agents.
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.