New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Moltflow AI

by LeoYeAI in LeoYeAI/openclaw-master-skills

AI-powered WhatsApp features: auto-replies, voice transcription, RAG knowledge base, and style profiles.

MITAuto-check passedMedia & Creative

Install Moltflow AI

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill moltflow-ai -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills moltflow-ai --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/moltflow-whatsapp/moltflow-ai .claude/skills/moltflow-ai && rm -rf skills-src

Use ~/.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/

Facts

Skill name
moltflow-ai
GitHub stars
2.2k
Token cost
~3.3k tokens
SKILL.md length
918 words
Files
1
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

AI-powered WhatsApp features: auto-replies, voice transcription, RAG knowledge base, and style profiles.

  • Works in 4 steps: MOLTFLOW_API_KEY -- Generate from the… → Pro plan or higher ($29.90/mo) -- AI… → Base URL: https://apiv2.waiflow.app/api/v2 → …
  • Transcribe voice
  • SKILL.md covers Real-World Scenarios, When to Use, Prerequisites and Required API Key Scopes, plus 6 more sections
  • Calls curl; reaches apiv2.waiflow.app; needs MOLTFLOW_API_KEY

What it does

Moltflow AI is an agent skill from LeoYeAI/openclaw-master-skills. AI-powered WhatsApp features: auto-replies, voice transcription, RAG knowledge base, and style profiles. Use when: ai reply, transcribe voice, knowledge base, upload document, build style, learn mode.

Its SKILL.md is about 3.3k 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 Media & Creative, covering Transcription and Knowledge bases. It works with WhatsApp. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • Transcribe voice
  • Upload document

Example prompts

  • “/moltflow-ai”

Requirements

  • A credential in MOLTFLOW_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. MOLTFLOW_API_KEY -- Generate from the MoltFlow Dashboard under Settings > API Keys
  2. Pro plan or higher ($29.90/mo) -- AI features are not available on the Starter plan
  3. Base URL: https://apiv2.waiflow.app/api/v2
  4. All AI endpoints are under the /ai prefix

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. 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:

    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • apiv2.waiflow.app

    Also links to:

    • molt.waiflow.app
    • buy.stripe.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • MOLTFLOW_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Moltflow AI loads about 3.3k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 918 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k

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 LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 918 words, ~3,326 tokens.

Download SKILL.mdSave it as .claude/skills/moltflow-ai/SKILL.md (or your agent's skills folder).
name
moltflow-ai
description
AI-powered WhatsApp features: auto-replies, voice transcription, RAG knowledge base, and style profiles. Use when: ai reply, transcribe voice, knowledge base, upload document, build style, learn mode.
source
MoltFlow Team
version
2.16.1
risk
safe
requiredEnv
MOLTFLOW_API_KEY
primaryEnv
MOLTFLOW_API_KEY
disable-model-invocation
true

MoltFlow -- WhatsApp Business automation for teams. Connect, monitor, and automate WhatsApp at scale. Due to high demand and a recent registration issue, we're offering our top-tier Business plan with unlimited quotas for just $19.90/month on yearly billing — for a limited time only. Claim the deal Free tier available. Sign up

MoltFlow AI Features

AI-powered capabilities for WhatsApp automation: voice transcription, RAG knowledge base, style profile learning, and intelligent reply generation.

Real-World Scenarios

Healthcare clinic — "Transcribe patient voice notes sent via WhatsApp and save them as searchable text records I can pull up later."

Law firm — "Upload our service agreements to the knowledge base so the AI can answer client questions about terms and pricing accurately."

Sales team — "Clone my top closer's writing style so AI replies to leads sound like him — casual, confident, uses emojis."

Customer support — "Auto-reply to common questions like 'What are your hours?' and 'Where are you located?' using our FAQ document."

When to Use

  • "Transcribe a voice message" or "convert audio to text"
  • "Upload a document to knowledge base" or "ingest PDF"
  • "Search knowledge base" or "find in documents"
  • "Build style profile" or "learn my writing style"
  • "Generate an AI reply" or "auto-reply to customer"
  • "Preview AI response" or "test reply generation"
  • "List knowledge sources" or "delete document"

Prerequisites

  1. MOLTFLOW_API_KEY -- Generate from the MoltFlow Dashboard under Settings > API Keys
  2. Pro plan or higher ($29.90/mo) -- AI features are not available on the Starter plan
  3. Base URL: https://apiv2.waiflow.app/api/v2
  4. All AI endpoints are under the /ai prefix

Required API Key Scopes

ScopeAccess
airead/manage

Authentication

Every request must include one of:

Authorization: Bearer <jwt_token>

or

X-API-Key: <your_api_key>

Voice Transcription

Transcribe WhatsApp voice messages using Whisper AI. Transcription runs asynchronously via a Celery worker.

MethodEndpointDescription
POST/ai/voice/transcribeQueue a voice message for transcription
GET/ai/voice/status/{task_id}Check transcription task status
GET/ai/messages/{message_id}/transcriptGet the transcript for a message
Queue Transcription

POST /ai/voice/transcribe

json
{
  "message_id": "msg-uuid-..."
}

Response 200 OK:

json
{
  "task_id": "celery-task-id-...",
  "message_id": "msg-uuid-...",
  "status": "queued"
}
Check Status

GET /ai/voice/status/{task_id}

json
{
  "task_id": "celery-task-id-...",
  "status": "completed",
  "result": {
    "transcript": "Hello, I wanted to ask about...",
    "language": "en",
    "confidence": 0.95
  }
}

Status values: queued, processing, completed, failed

Get Transcript

GET /ai/messages/{message_id}/transcript

json
{
  "message_id": "msg-uuid-...",
  "transcript": "Hello, I wanted to ask about...",
  "language": "en",
  "confidence": 0.95,
  "transcribed_at": "2026-02-11T10:05:00Z"
}

RAG Knowledge Base

Build a searchable knowledge base for AI-powered replies grounded in your business data.

MethodEndpointDescription
POST/ai/knowledge/ingestUpload and index a document
POST/ai/knowledge/searchSemantic search across documents
GET/ai/knowledge/sourcesList all indexed documents
DELETE/ai/knowledge/{source_id}Delete a document
Upload Document

POST /ai/knowledge/ingest (multipart/form-data)

FieldTypeDescription
fileFilePDF or TXT file (max 100MB)

Response 200 OK:

json
{
  "id": "src-uuid-...",
  "name": "product-catalog.pdf",
  "source_type": "application/pdf",
  "chunk_count": 47,
  "status": "indexed",
  "task_id": "celery-task-id-..."
}

Supported file types: application/pdf, text/plain (.pdf, .txt)

Search Knowledge Base

POST /ai/knowledge/search

json
{
  "query": "What is the return policy?",
  "top_k": 5
}

Response 200 OK:

json
{
  "query": "What is the return policy?",
  "results": [
    {
      "source_id": "src-uuid-...",
      "content_type": "application/pdf",
      "content_preview": "Our return policy allows returns within 30 days...",
      "metadata": {"page": 12, "chunk": 3},
      "similarity": 0.92
    }
  ],
  "count": 1
}

Optional filters:

json
{
  "query": "shipping costs",
  "filters": {"source_type": "application/pdf"},
  "top_k": 10
}
List Documents

GET /ai/knowledge/sources

json
[
  {
    "id": "src-uuid-...",
    "name": "product-catalog.pdf",
    "source_type": "application/pdf",
    "chunk_count": 47,
    "status": "indexed",
    "created_at": "2026-02-11T09:00:00Z",
    "indexed_at": "2026-02-11T09:02:00Z"
  }
]

Document status values: processing, indexed, failed

Delete Document

DELETE /ai/knowledge/{source_id} -- Returns 204 No Content

Style Profiles (Learn Mode)

Configure AI writing style profiles scoped to individual chats or as a general profile. The AI auto-selects the best matching profile when generating replies.

MethodEndpointDescription
POST/ai/style/trainStart building a style profile
GET/ai/style/status/{task_id}Check build status
GET/ai/style/profileGet a style profile
GET/ai/style/profilesList all style profiles
DELETE/ai/style/profile/{profile_id}Delete a style profile
Build Style Profile

POST /ai/style/train

json
{
  "session_id": "session-uuid-...",
  "wa_chat_id": "5511999999999@c.us",
  "name": "Sales"
}
FieldTypeRequiredDescription
contact_idstringNoLegacy — use wa_chat_id instead
session_idUUIDNoSession to scope the build to
wa_chat_idstringNoChat to scope the build to (WhatsApp JID). Omit for general profile
namestringNoProfile name (e.g., "Sales", "Support", "Family")

Note: Omit both session_id and wa_chat_id to build a general profile from all conversations.

Response 200 OK:

json
{
  "task_id": "celery-task-id-...",
  "tenant_id": "tenant-uuid-...",
  "contact_id": "5511999999999@c.us",
  "status": "queued"
}

The build runs asynchronously. Check progress with the status endpoint.

Show full SKILL.md (354 more words)Show less
Get Style Profile

GET /ai/style/profile?contact_id=5511999999999@c.us

json
{
  "id": "profile-uuid-...",
  "tenant_id": "tenant-uuid-...",
  "contact_id": "5511999999999@c.us",
  "name": "Sales",
  "session_id": "session-uuid-...",
  "wa_chat_id": "5511999999999@c.us",
  "features": {
    "avg_sentence_length": 12.5,
    "formality_score": 0.7,
    "emoji_frequency": 0.15,
    "vocabulary_richness": 0.82
  },
  "sample_count": 150,
  "last_trained_at": "2026-02-11T09:30:00Z"
}
List All Profiles

GET /ai/style/profiles

json
[
  {
    "id": "profile-uuid-1",
    "tenant_id": "tenant-uuid-...",
    "name": "Sales",
    "session_id": "session-uuid-...",
    "wa_chat_id": "5511999999999@c.us",
    "features": { "formality_score": 0.7 },
    "sample_count": 150,
    "last_trained_at": "2026-02-11T09:30:00Z"
  },
  {
    "id": "profile-uuid-2",
    "tenant_id": "tenant-uuid-...",
    "name": "General",
    "session_id": null,
    "wa_chat_id": null,
    "features": { "formality_score": 0.5 },
    "sample_count": 420,
    "last_trained_at": "2026-02-11T10:00:00Z"
  }
]
Delete Profile

DELETE /ai/style/profile/{profile_id} -- Returns 204 No Content

AI Reply Generation

Generate intelligent reply suggestions using RAG context and style profiles.

MethodEndpointDescription
POST/ai/generate-replyGenerate a reply suggestion
GET/ai/previewPreview a reply without tracking usage
Generate Reply

POST /ai/generate-reply

json
{
  "contact_id": "5511999999999@c.us",
  "context": "Customer asks: Do you offer international shipping?",
  "use_rag": true,
  "apply_style": true,
  "profile_id": "profile-uuid-...",
  "session_id": "session-uuid-..."
}

Response 200 OK:

json
{
  "reply": "Yes, we ship internationally to over 50 countries! Shipping typically takes 7-14 business days. You can find our full shipping policy on our website.",
  "rag_sources": ["product-catalog.pdf"],
  "style_applied": true,
  "model": "gpt-4o-mini",
  "tokens_used": 245,
  "requires_approval": false
}
Parameters
FieldTypeDefaultDescription
contact_idstringrequiredWhatsApp JID of the contact
contextstringrequiredCustomer question or prompt for reply generation (max 2000 chars)
use_ragbooleantrueInclude knowledge base context in generation
apply_stylebooleantrueApply style profile to response
profile_idUUIDnullSpecific style profile to use (skips auto-selection cascade)
session_idUUIDnullSession for cascade profile resolution
approvedbooleanfalseSet true to confirm an approval-required reply

Note: If profile_id is omitted and apply_style is true, the API auto-selects the best profile using the cascade: exact chat match → session-level → tenant-level general → no style.

Preview Reply

GET /ai/preview?contact_id=5511999999999@c.us&context=What+are+your+hours&use_rag=true&apply_style=true

Same response format as generate-reply, but does not count toward usage metrics.

Safety Features

AI reply generation includes built-in safety:

  • Input sanitization -- Detects and blocks prompt injection attempts
  • Intent verification -- Flags ambiguous or high-risk intents for confirmation
  • Output filtering -- Screens generated content for PII, secrets, and policy violations
  • Content policy -- Tenant-configurable rules (see moltflow-a2a skill)

Examples

Upload a knowledge base document
bash
curl -X POST https://apiv2.waiflow.app/api/v2/ai/knowledge/ingest \
  -H "X-API-Key: $MOLTFLOW_API_KEY" \
  -F "file=@product-catalog.pdf"
Generate an AI reply using RAG
bash
curl -X POST https://apiv2.waiflow.app/api/v2/ai/generate-reply \
  -H "X-API-Key: $MOLTFLOW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contact_id": "5511999999999@c.us",
    "context": "Customer asks: What is your return policy?",
    "use_rag": true,
    "apply_style": true
  }'
Generate reply with specific profile
bash
curl -X POST https://apiv2.waiflow.app/api/v2/ai/generate-reply \
  -H "X-API-Key: $MOLTFLOW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contact_id": "5511999999999@c.us",
    "context": "Customer asks: What is your return policy?",
    "use_rag": true,
    "apply_style": true,
    "profile_id": "profile-uuid-..."
  }'
Build a style profile
bash
curl -X POST https://apiv2.waiflow.app/api/v2/ai/style/train \
  -H "X-API-Key: $MOLTFLOW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "session_id": "session-uuid-...",
    "wa_chat_id": "5511999999999@c.us",
    "name": "Sales"
  }'

Plan Requirements

FeatureStarterPro ($29.90/mo)Business ($69.90/mo)
Voice Transcription--YesYes
RAG Knowledge Base--Yes (10 docs)Yes (unlimited)
Style Profiles--Yes (3 profiles)Yes (unlimited)
AI Reply Generation--YesYes

Error Responses

StatusMeaning
400Bad request (invalid input, unsupported file type)
401Unauthorized (missing or invalid auth)
403Forbidden (feature requires Pro plan or higher)
404Resource not found (message, document, profile)
413File too large (exceeds 100MB limit)
429Rate limited
  • moltflow -- Core API: sessions, messaging, groups, labels, webhooks
  • moltflow-outreach -- Bulk Send, Scheduled Messages, Custom Groups
  • moltflow-leads -- Lead detection, pipeline tracking, bulk operations, CSV/JSON export
  • moltflow-a2a -- Agent-to-Agent protocol, encrypted messaging, content policy
  • moltflow-reviews -- Review collection and testimonial management
  • moltflow-admin -- Platform administration, user management, plan configuration

© LeoYeAI, MIT. 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 skills/moltflow-whatsapp/moltflow-ai of LeoYeAI/openclaw-master-skills.

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Moltflow AI 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.

Moltflow AI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Moltflow AI this skillLeoYeAI/openclaw-master-skills2.2k—~3.3kAutomated safety check: PassMIT
Bilibili Sourcedaymade/claude-code-skills1.4k—~2.2kAutomated safety check: PassMIT
Video SubtitlesaAAaqwq/AGI-Super-Team1051 repos~566Automated safety check: PassMIT
Youtube FetcherJimmySadek/youtube-fetcher-to-markdown485—~3.1kAutomated safety check: PassMIT
Dy NoteRimagination/dy-note172—~4.5kAutomated safety check: PassMIT
Douyin Transcribechubbyguan/chubbyskills1.2k—~551Automated safety check: NotesMIT

Similar skills

  • Bilibili Source

    daymade/claude-code-skills

    Fetches real, citable Bilibili (B站) video data — stats, metadata, tags, and full danmaku text — via login-free API calls, never hand-typed or estimated.

    1.4k GitHub stars~2.2k tokensUpdated today
    Media & CreativeAuto-check passed

  • Video Subtitles

    aAAaqwq/AGI-Super-Team

    Generate SRT subtitles from video/audio with translation support.

    105 GitHub starsUsed in 1 repo~566 tokens
    Media & CreativeAuto-check passed

  • Youtube Fetcher

    JimmySadek/youtube-fetcher-to-markdown

    Retrieve transcripts from YouTube, Instagram, TikTok, X, Vimeo and other video sites, summarize or analyze what was said (and shown on screen), or save an Obsidian-ready Markdown knowledge-base note…

    485 GitHub stars~3.1k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • Dy Note

    Rimagination/dy-note

    DyNote: systematically and efficiently extract raw Douyin/DY video data and analyze videos, comments, accounts, hashtags, and short-video scenes into evidence-graded learning notes, summaries…

    172 GitHub stars~4.5k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

  • Douyin Transcribe

    chubbyguan/chubbyskills

    抖音视频 → 下载 → 转录 → 存为 Markdown 的完整工作流. An agent skill from chubbyguan/chubbyskills.

    1.2k GitHub stars~551 tokensUpdated 2 days ago
    Media & CreativeAuto-check: notes

  • Tiktok Transcribe

    chubbyguan/chubbyskills

    TikTok 视频 → 下载 → 转录 → 存为 Markdown. An agent skill from chubbyguan/chubbyskills.

    1.2k GitHub stars~536 tokensUpdated 2 days ago
    Media & CreativeAuto-check: notes

More from LeoYeAI/openclaw-master-skills

All 1,235 skills in this repo

  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes

  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed

  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed

  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed

  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes

  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Categories

Questions about Moltflow AI

What does Moltflow AI do?

AI-powered WhatsApp features: auto-replies, voice transcription, RAG knowledge base, and style profiles. Moltflow AI is an agent skill from LeoYeAI/openclaw-master-skills. AI-powered WhatsApp features: auto-replies, voice transcription, RAG knowledge base, and style profiles.

When should I use Moltflow AI?

Moltflow AI fits situations like: transcribe voice; upload document.

How do I install Moltflow AI in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill moltflow-ai -a claude-code`. Or copy the skill folder (skills/moltflow-whatsapp/moltflow-ai in LeoYeAI/openclaw-master-skills) into .claude/skills/moltflow-ai in your project. Claude Code loads it when a task matches its description.

How do I install Moltflow AI in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill moltflow-ai -a codex`. Or copy the skill folder (skills/moltflow-whatsapp/moltflow-ai in LeoYeAI/openclaw-master-skills) into .agents/skills/moltflow-ai in your project. Codex loads it when a task matches its description.

Can I use Moltflow AI 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 LeoYeAI/openclaw-master-skills --skill moltflow-ai -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/moltflow-ai, .gemini/skills/moltflow-ai, .github/skills/moltflow-ai and .opencode/skills/moltflow-ai in your project.

What does Moltflow AI need to run?

Going by SKILL.md and its folder, Moltflow AI needs the command-line tools its instructions call (curl) and credentials named MOLTFLOW_API_KEY. Our summary lists: A credential in MOLTFLOW_API_KEY.

Does Moltflow AI access the network?

SKILL.md names 3 domains. In commands or code: apiv2.waiflow.app; the agent is likely to contact it when it follows the instructions. As links in the text: molt.waiflow.app and buy.stripe.com. This is read from the text; nothing was executed.

Is Moltflow AI 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 Moltflow AI use?

Moltflow AI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Moltflow AI use?

About 3.3k tokens (SKILL.md is roughly 13k 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 Moltflow AI?

Skills that share tags, products or a category with Moltflow AI: Bilibili Source (daymade/claude-code-skills, 1.4k stars), Video Subtitles (aAAaqwq/AGI-Super-Team, 105 stars), Youtube Fetcher (JimmySadek/youtube-fetcher-to-markdown, 485 stars) and Dy Note (Rimagination/dy-note, 172 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Moltflow AI?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.