opencode-skills-collection 2.0.81 → 2.0.82

package/bundled-skills/.antigravity-install-manifest.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "updatedAt": "2026-04-14T17:10:47.719Z",
+  "updatedAt": "2026-04-14T19:18:15.869Z",
   "entries": [
     "00-andruia-consultant",
     "007",
@@ -846,6 +846,7 @@
     "ml-engineer",
     "ml-pipeline-workflow",
     "mlops-engineer",
+    "mmx-cli",
     "mobile-design",
     "mobile-developer",
     "mobile-security-coder",

package/bundled-skills/docs/contributors/skill-anatomy.md

@@ -113,6 +113,18 @@ tools: [claude, cursor, gemini]
 ---
 ```
 
+#### `license` *(optional)*
+- **What it is:** SPDX license identifier for the upstream source material
+- **Format:** A valid SPDX expression (e.g. `MIT`, `Apache-2.0`, `CC-BY-4.0`)
+- **Example:** `license: MIT`
+- **When to use:** Declare when `source_repo` points to material under a known license. Omitting it signals "license not verified" to downstream tooling.
+
+#### `license_source` *(optional)*
+- **What it is:** Direct URL to the upstream license file
+- **Format:** Full URL string
+- **Example:** `license_source: "https://github.com/owner/repo/blob/main/LICENSE"`
+- **When to use:** Include alongside `license:` so automated tooling can verify the claim. If the upstream repo has no LICENSE file, omit this field.
+
 ### Source-credit contract
 
 - External GitHub-derived skills should declare both `source_repo` and `source_type`.

package/bundled-skills/docs/contributors/skill-template.md

@@ -10,6 +10,9 @@ date_added: "YYYY-MM-DD"
 author: your-name-or-handle
 tags: [tag-one, tag-two]
 tools: [claude, cursor, gemini]
+# Optional: declare the upstream license if source_repo is set
+# license: "MIT"
+# license_source: "https://github.com/owner/repo/blob/main/LICENSE"
 ---
 
 # Skill Title

package/bundled-skills/docs/integrations/jetski-cortex.md

@@ -1,9 +1,9 @@
 ---
 title: Jetski/Cortex + Gemini Integration Guide
-description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1.409+ skills."
+description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1.410+ skills."
 ---
 
-# Jetski/Cortex + Gemini: safe integration with 1,1.409+ skills
+# Jetski/Cortex + Gemini: safe integration with 1,1.410+ skills
 
 This guide shows how to integrate the `antigravity-awesome-skills` repository with an agent based on **Jetski/Cortex + Gemini** (or similar frameworks) **without exceeding the model context window**.
 
@@ -23,7 +23,7 @@ Never do:
 - concatenate all `SKILL.md` content into a single system prompt;
 - re-inject the entire library for **every** request.
 
-With over 1,1.409 skills, this approach fills the context window before user messages are even added, causing truncation.
+With over 1,1.410 skills, this approach fills the context window before user messages are even added, causing truncation.
 
 ---
 

package/bundled-skills/docs/integrations/jetski-gemini-loader/README.md

@@ -20,7 +20,7 @@ This example shows one way to integrate **antigravity-awesome-skills** with a Je
 - How to enforce a **maximum number of skills per turn** via `maxSkillsPerTurn`.
 - How to choose whether to **truncate or error** when too many skills are requested via `overflowBehavior`.
 
-This pattern avoids context overflow when you have 1,409+ skills installed.
+This pattern avoids context overflow when you have 1,410+ skills installed.
 
 ---
 

package/bundled-skills/docs/maintainers/repo-growth-seo.md

@@ -6,7 +6,7 @@ This document keeps the repository's GitHub-facing discovery copy aligned with t
 
 Preferred positioning:
 
-> Installable GitHub library of 1,409+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
+> Installable GitHub library of 1,410+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
 
 Key framing:
 
@@ -20,7 +20,7 @@ Key framing:
 
 Preferred description:
 
-> Installable GitHub library of 1,409+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
+> Installable GitHub library of 1,410+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
 
 Preferred homepage:
 
@@ -28,7 +28,7 @@ Preferred homepage:
 
 Preferred social preview:
 
-- use a clean preview image that says `1,409+ Agentic Skills`;
+- use a clean preview image that says `1,410+ Agentic Skills`;
 - mention Claude Code, Cursor, Codex CLI, and Gemini CLI;
 - avoid dense text and tiny logos that disappear in social cards.
 

package/bundled-skills/docs/maintainers/skills-update-guide.md

@@ -69,7 +69,7 @@ For manual updates, you need:
 The update process refreshes:
 - Skills index (`skills_index.json`)
 - Web app skills data (`apps\web-app\public\skills.json`)
-- All 1,409+ skills from the skills directory
+- All 1,410+ skills from the skills directory
 
 ## When to Update
 

package/bundled-skills/docs/users/bundles.md

@@ -673,4 +673,4 @@ Found a skill that should be in a bundle? Or want to create a new bundle? [Open
 
 ---
 
-_Last updated: March 2026 | Total Skills: 1,409+ | Total Bundles: 37_
+_Last updated: March 2026 | Total Skills: 1,410+ | Total Bundles: 37_

package/bundled-skills/docs/users/claude-code-skills.md

@@ -12,7 +12,7 @@ Install the library into Claude Code, then invoke focused skills directly in the
 
 ## Why use this repo for Claude Code
 
-- It includes 1,409+ skills instead of a narrow single-domain starter pack.
+- It includes 1,410+ skills instead of a narrow single-domain starter pack.
 - It supports the standard `.claude/skills/` path and the Claude Code plugin marketplace flow.
 - It also ships generated bundle plugins so teams can install focused packs like `Essentials` or `Security Developer` from the marketplace metadata.
 - It includes onboarding docs, bundles, and workflows so new users do not need to guess where to begin.

package/bundled-skills/docs/users/gemini-cli-skills.md

@@ -12,7 +12,7 @@ Install into the Gemini skills path, then ask Gemini to apply one skill at a tim
 
 - It installs directly into the expected Gemini skills path.
 - It includes both core software engineering skills and deeper agent/LLM-oriented skills.
-- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,409+ files.
+- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,410+ files.
 - It is useful whether you want a broad internal skill library or a single repo to test many workflows quickly.
 
 ## Install Gemini CLI Skills

package/bundled-skills/docs/users/getting-started.md

@@ -1,4 +1,4 @@
-# Getting Started with Antigravity Awesome Skills (V10.0.0)
+# Getting Started with Antigravity Awesome Skills (V10.1.0)
 
 **New here? This guide will help you supercharge your AI Agent in 5 minutes.**
 

package/bundled-skills/docs/users/kiro-integration.md

@@ -18,7 +18,7 @@ Kiro is AWS's agentic AI IDE that combines:
 
 Kiro's agentic capabilities are enhanced by skills that provide:
 
-- **Domain expertise** across 1,409+ specialized areas
+- **Domain expertise** across 1,410+ specialized areas
 - **Best practices** from Anthropic, OpenAI, Google, Microsoft, and AWS
 - **Workflow automation** for common development tasks
 - **AWS-specific patterns** for serverless, infrastructure, and cloud architecture

package/bundled-skills/docs/users/usage.md

@@ -14,7 +14,7 @@ If you came in through a **Claude Code** or **Codex** plugin instead of a full l
 
 When you ran `npx antigravity-awesome-skills` or cloned the repository, you:
 
-✅ **Downloaded 1,409+ skill files** to your computer (default: `~/.gemini/antigravity/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)  
+✅ **Downloaded 1,410+ skill files** to your computer (default: `~/.gemini/antigravity/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)  
 ✅ **Made them available** to your AI assistant  
 ❌ **Did NOT enable them all automatically** (they're just sitting there, waiting)
 
@@ -34,7 +34,7 @@ Bundles are **curated groups** of skills organized by role. They help you decide
 
 **Analogy:**
 
-- You installed a toolbox with 1,409+ tools (✅ done)
+- You installed a toolbox with 1,410+ tools (✅ done)
 - Bundles are like **labeled organizer trays** saying: "If you're a carpenter, start with these 10 tools"
 - You can either **pick skills from the tray** or install that tray as a focused marketplace bundle plugin
 
@@ -212,7 +212,7 @@ Let's actually use a skill right now. Follow these steps:
 
 ## Step 5: Picking Your First Skills (Practical Advice)
 
-Don't try to use all 1,409+ skills at once. Here's a sensible approach:
+Don't try to use all 1,410+ skills at once. Here's a sensible approach:
 
 If you want a tool-specific starting point before choosing skills, use:
 
@@ -343,7 +343,7 @@ Usually no, but if your AI doesn't recognize a skill:
 
 ### "Can I load all skills into the model at once?"
 
-No. Even though you have 1,409+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
+No. Even though you have 1,410+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
 
 The intended pattern is:
 

package/bundled-skills/docs/users/visual-guide.md

@@ -34,7 +34,7 @@ antigravity-awesome-skills/
 ├── 📄 CONTRIBUTING.md                  ← Contributor workflow
 ├── 📄 CATALOG.md                       ← Full generated catalog
 │
-├── 📁 skills/                          ← 1,409+ skills live here
+├── 📁 skills/                          ← 1,410+ skills live here
 │   │
 │   ├── 📁 brainstorming/
 │   │   └── 📄 SKILL.md                 ← Skill definition
@@ -47,7 +47,7 @@ antigravity-awesome-skills/
 │   │   └── 📁 2d-games/
 │   │       └── 📄 SKILL.md             ← Nested skills also supported
 │   │
-│   └── ... (1,409+ total)
+│   └── ... (1,410+ total)
 │
 ├── 📁 apps/
 │   └── 📁 web-app/                     ← Interactive browser
@@ -100,7 +100,7 @@ antigravity-awesome-skills/
 
 ```
                     ┌─────────────────────────┐
-                    │  1,409+ SKILLS          │
+                    │  1,410+ SKILLS          │
                     └────────────┬────────────┘
                                  │
         ┌────────────────────────┼────────────────────────┐
@@ -201,7 +201,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
 │   ├── 📁 brainstorming/                 │
 │   ├── 📁 stripe-integration/            │
 │   ├── 📁 react-best-practices/          │
-│   └── ... (1,409+ total)                │
+│   └── ... (1,410+ total)                │
 └─────────────────────────────────────────┘
 ```
 

package/bundled-skills/mmx-cli/SKILL.md

@@ -0,0 +1,193 @@
+---
+name: mmx-cli
+description: "Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform. Use when the user wants to create media content, chat with MiniMax models, perform web search, or manage MiniMax API resources from the terminal."
+risk: safe
+source: "https://github.com/MiniMax-AI/cli"
+date_added: "2026-04-14"
+---
+
+# MiniMax CLI — Agent Skill Guide
+
+Use `mmx` to generate text, images, video, speech, music, and perform web search via the MiniMax AI platform.
+
+## Prerequisites
+
+```bash
+# Install
+npm install -g mmx-cli
+
+# Auth (OAuth persists to ~/.mmx/credentials.json, API key persists to ~/.mmx/config.json)
+mmx auth login --api-key sk-xxxxx
+
+# Verify active auth source
+mmx auth status
+
+# Or pass per-call
+mmx text chat --api-key sk-xxxxx --message "Hello"
+```
+
+Region is auto-detected. Override with `--region global` or `--region cn`.
+
+---
+
+## Agent Flags
+
+Always use these flags in non-interactive (agent/CI) contexts:
+
+| Flag | Purpose |
+|---|---|
+| `--non-interactive` | Fail fast on missing args instead of prompting |
+| `--quiet` | Suppress spinners/progress; stdout is pure data |
+| `--output json` | Machine-readable JSON output |
+| `--async` | Return task ID immediately (video generation) |
+| `--dry-run` | Preview the API request without executing |
+| `--yes` | Skip confirmation prompts |
+
+---
+
+## Commands
+
+### text chat
+
+Chat completion. Default model: `MiniMax-M2.7`.
+
+```bash
+mmx text chat --message <text> [flags]
+```
+
+```bash
+# Single message
+mmx text chat --message "user:What is MiniMax?" --output json --quiet
+
+# Multi-turn with system prompt
+mmx text chat \
+  --system "You are a coding assistant." \
+  --message "user:Write fizzbuzz in Python" \
+  --output json
+
+# From file
+cat conversation.json | mmx text chat --messages-file - --output json
+```
+
+---
+
+### image generate
+
+Generate images. Model: `image-01`.
+
+```bash
+mmx image generate --prompt <text> [flags]
+```
+
+```bash
+mmx image generate --prompt "A cat in a spacesuit" --output json --quiet
+mmx image generate --prompt "Logo" --n 3 --out-dir ./gen/ --quiet
+```
+
+---
+
+### video generate
+
+Generate video. Default model: `MiniMax-Hailuo-2.3`. Async task — polls until completion by default.
+
+```bash
+mmx video generate --prompt <text> [flags]
+```
+
+```bash
+# Non-blocking: get task ID
+mmx video generate --prompt "A robot." --async --quiet
+
+# Blocking: wait and save file
+mmx video generate --prompt "Ocean waves." --download ocean.mp4 --quiet
+```
+
+---
+
+### speech synthesize
+
+Text-to-speech. Default model: `speech-2.8-hd`. Max 10k chars.
+
+```bash
+mmx speech synthesize --text <text> [flags]
+```
+
+```bash
+mmx speech synthesize --text "Hello world" --out hello.mp3 --quiet
+echo "Breaking news." | mmx speech synthesize --text-file - --out news.mp3
+```
+
+---
+
+### music generate
+
+Generate music. Model: `music-2.6-free`.
+
+```bash
+mmx music generate --prompt <text> [--lyrics <text>] [flags]
+```
+
+```bash
+# Instrumental
+mmx music generate --prompt "Cinematic orchestral, building tension" --instrumental --out bgm.mp3 --quiet
+
+# With auto-generated lyrics
+mmx music generate --prompt "Upbeat pop about summer" --lyrics-optimizer --out summer.mp3 --quiet
+```
+
+---
+
+### search query
+
+Web search via MiniMax.
+
+```bash
+mmx search query --q "MiniMax AI" --output json --quiet
+```
+
+---
+
+### vision describe
+
+Image understanding via VLM.
+
+```bash
+mmx vision describe --image photo.jpg --prompt "What breed?" --output json
+```
+
+---
+
+## Piping Patterns
+
+```bash
+# Chain: generate image → describe it
+URL=$(mmx image generate --prompt "A sunset" --quiet)
+mmx vision describe --image "$URL" --quiet
+
+# Async video workflow
+TASK=$(mmx video generate --prompt "A robot" --async --quiet | jq -r '.taskId')
+mmx video task get --task-id "$TASK" --output json
+mmx video download --task-id "$TASK" --out robot.mp4
+```
+
+---
+
+## Exit Codes
+
+| Code | Meaning |
+|---|---|
+| 0 | Success |
+| 1 | General error |
+| 2 | Usage error |
+| 3 | Authentication error |
+| 4 | Quota exceeded |
+| 5 | Timeout |
+| 10 | Content filter triggered |
+
+---
+
+## Limitations
+
+- Requires a configured MiniMax account and valid authentication before any API-backed command will work.
+- Media-generation tasks can be async, quota-limited, or region-constrained; agents should handle delayed completion and provider-side failures explicitly.
+- This skill documents CLI usage only and does not replace provider policy review, content-safety checks, or downstream file validation.

package/bundled-skills/zipai-optimizer/SKILL.md

@@ -1,44 +1,83 @@
 ---
 id: zipai-optimizer
 name: zipai-optimizer
-description: "Behavioral protocol engineered for extreme AI agent token optimization, eliminating I/O noise via context-aware truncation and strict conciseness."
+version: "11.0"
+description: "Adaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware."
 category: agent-behavior
 risk: safe
-version: "5.0"
 ---
 
 # ZipAI: Context & Token Optimizer
 
 <rules>
-  <rule id="1" name="Contextual Conciseness">
-    <description>Adapt output verbosity to the type of task.</description>
+  <rule id="1" name="Adaptive Verbosity">
     <instruction>
-      - **Operations & Code Fixes:** Eliminate all conversational filler, pleasantries, and meta-commentary. Output ONLY the technical analysis, code delta, or command. Use terse `<thought>` blocks.
-      - **Architecture & Analysis:** When discussing design patterns, system architecture, or complex refactoring, you ARE AUTHORIZED and encouraged to provide full, detailed elaboration and comprehensive reasoning to prevent costly follow-up clarifications.
+      - **Ops/Fixes:** technical content only. No filler, no echo, no meta.
+      - **Architecture/Analysis:** full reasoning authorized and encouraged.
+      - **Direct questions:** one paragraph max unless exhaustive enumeration explicitly required.
+      - **Long sessions:** never re-summarize prior context. Assume developer retains full thread memory.
     </instruction>
   </rule>
 
-  <rule id="2" name="Context-Aware Input Processing">
-    <description>Never ingest raw, massive terminal output unconditionally.</description>
+  <rule id="2" name="Ambiguity-First Execution">
     <instruction>
-      Before piping terminal commands, identify the output type:
-      - **Builds/Installs (npm, pip, make):** You MUST pipe the command to truncate noise (e.g., `| tail -n 30`).
-      - **Errors/Stacktraces (tests, crashes):** You MUST NOT blind-truncate. Use intelligent execution: Pipe through dynamic grep filters (e.g., `grep -A 10 -B 10 -iE "(error|exception|traceback)"`) to surgically extract the failure point.
+      Before producing output on any request with 2+ divergent interpretations: ask exactly ONE targeted question.
+      Never ask about obvious intent. Never stack multiple questions.
+      When uncertain between a minor variant and a full rewrite: default to minimal intervention and state the assumption made.
     </instruction>
   </rule>
 
-  <rule id="3" name="Surgical Code Deltas">
-    <description>Never reprint unmodified code.</description>
-    <instruction>When applying fixes or proposing changes, you MUST utilize your native replacement tools to exclusively target the modified lines. Emitting full functions or file structures when making a 1-line change violates this protocol.</instruction>
+  <rule id="3" name="Intelligent Input Filtering">
+    <instruction>
+      Classify before ingesting — never read raw:
+
+      - **Builds/Installs (pip, npm, make, docker):** `grep -A 10 -B 10 -iE "(error|fail|warn|fatal)"`
+      - **Errors/Stacktraces (pytest, crashes, stderr):** `grep -A 10 -B 5 -iE "(error|exception|traceback|failed|assert)"`
+      - **Large source files (>300 lines):** locate with `grep -n "def \|class "`, read with `view_range`.
+      - **JSON/YAML payloads:** `jq 'keys'` or `head -n 40` before committing to full read.
+      - **Files already read this session:** use cached in-context version. Do not re-read unless explicitly modified.
+      - **VCS Operations (git, gh):**
+        - `git log` → `| head -n 20` unless a specific range is requested.
+        - `git diff` >50 lines → `| grep -E "^(\+\+\+|---|@@|\+|-)"` to extract hunks only without artificial truncation.
+        - `git status` → read as-is.
+        - `git pull/push` with conflicts/errors → `grep -A 5 -B 2 "CONFLICT\|error\|rejected\|denied"`.
+        - `git log --graph` → `| head -n 40`.
+      - **Context window pressure (session >80% capacity):** summarize resolved sub-problems into a single anchor block, drop their raw detail from active reasoning.
+    </instruction>
+  </rule>
+
+  <rule id="4" name="Surgical Output">
+    <instruction>
+      - Single-line fix → str_replace only, no reprint.
+      - Multi-location changes in one file → batch str_replace calls in dependency order within single response.
+      - Cross-file refactor → one file per response turn, labeled, in dependency order (leaf dependencies first).
+      - Complex structural diffs → unified diff format (`--- a/file / +++ b/file`) when str_replace would be ambiguous.
+      - Never silently bundle unrelated changes.
+    </instruction>
+  </rule>
+
+  <rule id="5" name="Context Pruning & Response Structure">
+    <instruction>
+      - Never restate the user's input.
+      - Lead with conclusion, follow with reasoning (inverted pyramid).
+      - Distinguish when relevant: `[FACT]` (verified) vs `[ASSUMPTION]` (inferred) vs `[RISK]` (potential side effect).
+      - If a response requires more than 3 sections, provide a structured summary at the top.
+    </instruction>
   </rule>
 </rules>
 
 <negative_constraints>
-  - DO NOT say "Here is the updated code", "I understand", "Let me help", or any variation of filler.
-  - DO NOT blind-truncate error logs or stacktraces.
+  - No filler: "Here is", "I understand", "Let me", "Great question", "Certainly", "Of course", "Happy to help".
+  - No blind truncation of stacktraces or error logs.
+  - No full-file reads when targeted grep/view_range suffices.
+  - No re-reading files already in context.
+  - No multi-question clarification dumps.
+  - No silent bundling of unrelated changes.
+  - No full git diff ingestion on large changesets — extract hunks only.
+  - No git log beyond 20 entries unless a specific range is requested.
 </negative_constraints>
 
 ## Limitations
-- Use this skill only when the task clearly matches the scope described above.
-- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
-- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
+- **Ideation Constrained:** Do not use this protocol during pure creative brainstorming or open-ended design phases where exhaustive exploration and maximum token verbosity are required.
+- **Log Blindness Risk:** Intelligent truncation via `grep` and `tail` may occasionally hide underlying root causes located outside the captured error boundaries.
+- **Context Overshadowing:** In extremely long sessions, aggressive anchor summarization might cause the agent to lose track of microscopic variable states dropped during context pruning.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-skills-collection",
-  "version": "2.0.81",
+  "version": "2.0.82",
   "description": "OpenCode CLI plugin that automatically downloads and keeps skills up to date.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

package/skills_index.json

@@ -18521,6 +18521,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "mmx-cli",
+    "path": "skills/mmx-cli",
+    "category": "uncategorized",
+    "name": "mmx-cli",
+    "description": "Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform. Use when the user wants to create media content, chat with MiniMax models, perform web search, or manage MiniMax API resources from the terminal.",
+    "risk": "safe",
+    "source": "https://github.com/MiniMax-AI/cli",
+    "date_added": "2026-04-14",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "mobile-design",
     "path": "skills/mobile-design",
@@ -30959,7 +30981,7 @@
     "path": "skills/zipai-optimizer",
     "category": "agent-behavior",
     "name": "zipai-optimizer",
-    "description": "Behavioral protocol engineered for extreme AI agent token optimization, eliminating I/O noise via context-aware truncation and strict conciseness.",
+    "description": "Adaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware.",
     "risk": "safe",
     "source": "unknown",
     "date_added": null,