opencode-skills-collection 3.0.33 → 3.0.35

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

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "updatedAt": "2026-06-01T02:30:46.952Z",
+  "updatedAt": "2026-06-03T02:36:10.080Z",
   "entries": [
     "00-andruia-consultant",
     "007",
@@ -1399,6 +1399,7 @@
     "unsplash-integration",
     "upgrading-expo",
     "upstash-qstash",
+    "user-thoughts",
     "using-git-worktrees",
     "using-neon",
     "using-superpowers",

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 1,493+ skills."
+description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1,494+ skills."
 ---
 
-# Jetski/Cortex + Gemini: safe integration with 1,493+ skills
+# Jetski/Cortex + Gemini: safe integration with 1,494+ 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 1,493+ skills, this approach fills the context window before user messages are even added, causing truncation.
+With 1,494+ 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

@@ -21,7 +21,7 @@ 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 1,493+ skills installed.
+This pattern avoids context overflow when you have 1,494+ skills installed.
 
 Manifest contract references:
 

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 1,493+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
+> Installable GitHub library of 1,494+ 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 1,493+ 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 1,494+ 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 `1,493+ Agentic Skills`;
+- use a clean preview image that says `1,494+ 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

@@ -72,7 +72,7 @@ The update process refreshes:
 - Canonical skills index (`skills_index.json`)
 - Compatibility mirror (`data/skills_index.json`)
 - Web app skills data (`apps\web-app\public\skills.json`)
-- All 1,493+ skills from the skills directory
+- All 1,494+ 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: 1,493+ | Total Bundles: 37_
+_Last updated: March 2026 | Total Skills: 1,494+ | 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 1,493+ skills instead of a narrow single-domain starter pack.
+- It includes 1,494+ 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 1,493+ files.
+- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,494+ 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 (V11.10.0)
+# Getting Started with Antigravity Awesome Skills (V11.11.0)
 
 **New here? This guide will help you supercharge your AI Agent in 5 minutes.**
 
@@ -106,7 +106,7 @@ Once installed, just talk to your AI naturally.
 | **Kiro CLI**    | ✅ Full Support | Global: `~/.kiro/skills/` · Workspace: `.kiro/skills/`                |
 | **Kiro IDE**    | ✅ Full Support | Global: `~/.kiro/skills/` · Workspace: `.kiro/skills/`                |
 | **Antigravity** | ✅ Native       | Global: `~/.agents/skills/` · Workspace: `.agent/skills/` |
-| **Antigravity CLI (`agy`)** | ✅ Full Support | Global slash-command files: `~/.gemini/antigravity-cli/skills/` |
+| **Antigravity CLI (`agy`)** | ✅ Full Support | Global slash-command directories: `~/.gemini/antigravity-cli/skills/<skill>/SKILL.md` |
 | **Cursor**      | ✅ Native       | `.cursor/skills/`                                                     |
 | **OpenCode**    | ✅ Full Support | `.agents/skills/` (prefer reduced installs with `--risk`, `--category`, or `--tags`) |
 | **AdaL CLI**    | ✅ Full Support | `.adal/skills/`                                                       |
@@ -156,7 +156,7 @@ A: Follow the recovery steps in [windows-truncation-recovery.md](windows-truncat
 A: Use the activation flow in [agent-overload-recovery.md](agent-overload-recovery.md). It shows how to run `scripts/activate-skills.sh` from a cloned repo so you can keep the full library archived and activate only the bundles or skills you need in the live Antigravity directory.
 
 **Q: What if `agy` does not show installed skills when I type `/`?**
-A: The Antigravity CLI reads flat markdown skills from `~/.gemini/antigravity-cli/skills/`. Run `npx antigravity-awesome-skills --agy`, restart `agy`, then open `/skills` or type a specific slash command such as `/brainstorming`.
+A: The Antigravity CLI reads skill directories from `~/.gemini/antigravity-cli/skills/<skill>/SKILL.md`. Run `npx antigravity-awesome-skills --agy`, restart `agy`, then open `/skills` or type a specific slash command such as `/brainstorming`.
 
 **Q: What if OpenCode or another `.agents/skills` host becomes unstable with a full install?**
 A: Start with a reduced install instead of copying the whole library. For example: `npx antigravity-awesome-skills --path .agents/skills --category development,backend --risk safe,none`. You can narrow further with `--tags` and use a trailing `-` to exclude values such as `typescript-`.

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 1,493+ specialized areas
+- **Domain expertise** across 1,494+ 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 1,493+ skill files** to your computer (default: `~/.agents/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
+✅ **Downloaded 1,494+ skill files** to your computer (default: `~/.agents/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 1,493+ tools (✅ done)
+- You installed a toolbox with 1,494+ 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 1,493+ skills at once. Here's a sensible approach:
+Don't try to use all 1,494+ 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 1,493+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
+No. Even though you have 1,494+ 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/                          ← 1,493+ skills live here
+├── 📁 skills/                          ← 1,494+ skills live here
 │   │
 │   ├── 📁 brainstorming/
 │   │   └── 📄 SKILL.md                 ← Skill definition
@@ -47,7 +47,7 @@ antigravity-awesome-skills/
 │   │   └── 📁 2d-games/
 │   │       └── 📄 SKILL.md             ← Nested skills also supported
 │   │
-│   └── ... (1,493+ total)
+│   └── ... (1,494+ total)
 │
 ├── 📁 apps/
 │   └── 📁 web-app/                     ← Interactive browser
@@ -100,7 +100,7 @@ antigravity-awesome-skills/
 
 ```
                     ┌─────────────────────────┐
-                    │  1,493+ SKILLS          │
+                    │  1,494+ SKILLS          │
                     └────────────┬────────────┘
                                  │
         ┌────────────────────────┼────────────────────────┐
@@ -201,7 +201,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
 │   ├── 📁 brainstorming/                 │
 │   ├── 📁 stripe-integration/            │
 │   ├── 📁 react-best-practices/          │
-│   └── ... (1,493+ total)                │
+│   └── ... (1,494+ total)                │
 └─────────────────────────────────────────┘
 ```
 

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

@@ -53,14 +53,14 @@ Always use these flags in non-interactive (agent/CI) contexts:
 
 ### text chat
 
-Chat completion. Default model: `MiniMax-M2.7`.
+Chat completion. Default model: `MiniMax-M3`. Pass `--model MiniMax-M2.7` for the previous-generation default when reproducing older outputs.
 
 ```bash
 mmx text chat --message <text> [flags]
 ```
 
 ```bash
-# Single message
+# Single message (uses MiniMax-M3 by default)
 mmx text chat --message "user:What is MiniMax?" --output json --quiet
 
 # Multi-turn with system prompt
@@ -69,6 +69,9 @@ mmx text chat \
   --message "user:Write fizzbuzz in Python" \
   --output json
 
+# Pin to the previous-generation model
+mmx text chat --model MiniMax-M2.7 --message "user:Hello" --output json
+
 # From file
 cat conversation.json | mmx text chat --messages-file - --output json
 ```

package/bundled-skills/nextjs-seo-indexing/SKILL.md

@@ -85,7 +85,7 @@ Find pages that are accidentally noindexed:
 
 ```bash
 # Search for noindex in metadata
-grep -r "noindex\|robots.*noindex" --include="*.{js,ts,jsx,tsx}" app/ pages/ -l
+rg -n --glob '*.{js,ts,jsx,tsx}' 'noindex|robots.*noindex' app pages
 
 # Check layout.js — a noindex here affects ALL pages
 grep -n "robots" app/layout.js
@@ -156,7 +156,7 @@ Pages must be statically generated (or SSR with metadata in HTML) for Google to
 npm run build 2>&1 | grep -E "○|●|λ|/blog|/tools"
 ```
 
-```
+```text
 ○  /about             (static)
 ●  /blog/[slug]       (SSG)  ← good
 λ  /api/data          (serverless) ← expected for APIs
@@ -221,7 +221,7 @@ async redirects() {
 curl -s https://www.yourdomain.com/robots.txt
 ```
 
-```
+```text
 # ✓ Good
 User-agent: *
 Allow: /

package/bundled-skills/schema-markup-generator/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: schema-markup-generator
-description: "Generate and implement JSON-LD structured data for web apps, tool pages, blogs, FAQs, and SaaS sites. Supports WebSite, SoftwareApplication, BlogPosting, FAQPage, HowTo, BreadcrumbList, and Organization schemas."
+description: "Generate and implement JSON-LD structured data for web apps, blogs, FAQs, and SaaS sites. Supports WebSite, SoftwareApplication, BlogPosting, FAQPage, HowTo, and more."
 category: seo
 risk: safe
 source: self

package/bundled-skills/social-metadata-hardening/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: social-metadata-hardening
-description: "Fix social sharing previews so URLs render as rich cards on Facebook, LinkedIn, X/Twitter, WhatsApp, Telegram, Slack, and Discord. Covers OG tags, Twitter cards, absolute image URLs, and metadata debugging."
+description: "Fix social sharing previews so URLs render as rich cards on Facebook, LinkedIn, X/Twitter, WhatsApp, Telegram, and more. Covers OG tags, Twitter cards, absolute image URLs, and debugging."
 category: seo
 risk: safe
 source: self
@@ -141,7 +141,7 @@ export const metadata = {
 };
 ```
 
-> ⚠️ **`metadataBase` is critical.** Without it, Next.js generates relative OG image URLs that every platform rejects.
+> ⚠️ **Set `metadataBase` when using relative metadata URLs.** If your helper already outputs absolute canonical/OG URLs, previews can still work without it.
 
 ---
 
@@ -198,6 +198,7 @@ curl -s https://www.yourdomain.com/blog/my-post | grep -i "og:\|twitter:"
 If tags don't appear → they're being added by JavaScript (not crawlable). Fix: move to `export const metadata` or `generateMetadata`.
 
 ### 2. Validate with platform tools
+
 | Platform | Tool |
 |----------|------|
 | Facebook | https://developers.facebook.com/tools/debug/ |
@@ -226,5 +227,5 @@ After deploying fixes, paste the URL into each platform's debugger and click "Fe
 ## Limitations
 
 - Cannot force immediate cache refresh on every social platform; some previews may remain stale after a correct fix.
-- Requires deployed, publicly reachable URLs for reliable validation with platform debuggers.
+- Requires publicly reachable deployed URLs for reliable validation with platform debuggers.
 - Does not replace brand, accessibility, or legal review of image text, alt text, and preview copy.

package/bundled-skills/social-post-writer-seo/SKILL.md

@@ -93,6 +93,25 @@ Check the link in bio to pre-order!
 - ❌ Avoid using more than 10 hashtags; it can look like spam.
 - ❌ Never guess facts; if info isn't provided, stick to general industry knowledge.
 
+## Examples
+
+### Example: New Product Launch
+- **Topic**: Solar Powered Coffee Mug
+- **Keyword**: eco-friendly coffee
+- **Target**: Commuters
+- **Platform**: Instagram
+- **Tone**: Insightful
+
+**Output**:
+☕️ Your morning coffee just got a clean energy upgrade! 
+Your commute just got smarter and greener. 
+The SolMug keeps your brew hot using only sunlight. 
+A small change for your bag, a big win for the planet. 
+Check the link in bio to pre-order! 
+#ecofriendly #coffee #sustainability #tech #morningroutine
+
+---
+
 ## Limitations
 - This skill does not generate image or video assets.
 - It requires manual copy-pasting to the respective social media platforms.

package/bundled-skills/user-thoughts/SKILL.md

@@ -0,0 +1,236 @@
+---
+name: user-thoughts
+description: >-
+  Persist user decisions and project constraints to mdbase across sessions.
+  Trigger on /user-thoughts or /ustht, or when the user discusses architecture,
+  tech stack, rules, UI/UX, or project memory.
+license: MIT
+source: "https://github.com/JularDepick/user-thoughts.SKILL"
+source_repo: JularDepick/user-thoughts.SKILL
+source_type: community
+date_added: "2026-05-31"
+author: JularDepick
+tags: [userthoughts, documentation, project-management, mdbase]
+tools: [claude, cursor, gemini]
+risk: safe
+allowed-tools: read write bash
+metadata:
+  author: JularDepick
+  category: productivity
+  supported_agents: "[claude, cursor, gemini]"
+---
+
+# user-thoughts.SKILL
+
+## Overview
+
+Across sessions and across agents, project decisions and user constraints are easy to lose. `user-thoughts` persists those decisions into a project-local `mdbase` so any future agent can recover the user's intent without re-deriving it from scratch.
+
+The skill records user intent. It does not replace normal task execution. If the user says, "make the button red," the agent should both make the change and record the preference when persistent project memory is useful.
+
+## When to Use
+
+Use this skill when the user states or revises:
+
+- Project rules, constraints, preferences, or requirements.
+- Architecture, tech-stack, data-model, deployment, or workflow decisions.
+- UI/UX direction, copy standards, visual preferences, or design rationale.
+- Backlog items, planned work, rejected options, or decisions that future agents should inherit.
+- A direct command beginning with `/user-thoughts` or `/ustht`.
+
+Do not use it for unrelated small talk, transient chatter, or content the user explicitly asks to ignore.
+
+## Language Policy
+
+- All bundled skill files, scripts, templates, and reference docs are written in English.
+- Agent-facing command output should follow the user's current conversation language when the agent can reasonably do so.
+- Raw user thoughts should preserve the user's original wording. Do not translate, summarize, or clean the user's intent unless the user asks for that.
+
+## Core Workflow
+
+```text
+User message -> Agent identifies persistent project intent -> write to #raw/
+             -> /ustht sortin groups raw entries into #mdbase/
+             -> /ustht mdbase show exposes the organized memory base
+```
+
+## Runtime Modes
+
+- Passive mode: `INSTANT_STATUS=off`; only explicit skill commands run.
+- Instant mode: `INSTANT_STATUS=on` and `SKILL_STATUS=on`; project-relevant user thoughts are written to `#raw/` as they appear.
+- Ignore mode: `ignore start` and `ignore end` mark a temporary interval that should not be recorded.
+- Read-only mode: if required read/write/bash tools are unavailable, show commands can still work but write commands should explain that the environment cannot persist data.
+
+`SKILL_STATUS=off` pauses instant capture even when `INSTANT_STATUS=on`. Ignore intervals are context-local and do not persist across sessions.
+
+## Path Definitions
+
+- `@/`: the installed `user-thoughts/` skill directory.
+- `~/`: the current project working directory.
+- `#ustht/`: `~/.ustht/`.
+- `#mdbase/`: `~/.ustht/mdbase/`.
+- `#ignored/`: `~/.ustht/ignored/`.
+- `#raw/`: `~/.ustht/raw/`.
+- `#export/`: `~/.ustht/export/`.
+
+## Runtime Directory Layout
+
+```text
+.ustht/
+├── define.ini
+├── README.ai.md
+├── raw/
+│   └── yyyy-mm-dd.md
+├── ignored/
+│   └── yyyy-mm-dd.md
+├── mdbase/
+│   ├── backlog.md
+│   ├── README.ai.md
+│   └── details/
+│       ├── rules.md
+│       ├── plans.md
+│       ├── ui/
+│       │   ├── outline.md
+│       │   └── details.md
+│       ├── dev-stack.md
+│       └── general.md
+└── export/
+```
+
+## Tools and Environment
+
+Required tools:
+
+- read/write: read and update files under `#ustht/`.
+- bash: create directories and run bundled scripts.
+
+Optional tool:
+
+- SubAgent: when available, use it for semantic `sortin` or `resort` maintenance that spans many files. Use the main agent directly only when subagents are unavailable.
+
+## Bundled Scripts
+
+The `scripts/` directory provides small Python helpers for mechanical operations:
+
+| Script | Purpose | Example |
+|---|---|---|
+| `common.py` | Shared helpers | Imported by other scripts |
+| `status.py` | Show current runtime state | `python @/scripts/status.py` |
+| `init.py` | Initialize `.ustht/` | `python @/scripts/init.py` |
+| `show_raw.py` | Show unprocessed raw entries | `python @/scripts/show_raw.py` |
+| `show_mdbase.py` | Show mdbase index or a dimension | `python @/scripts/show_mdbase.py show --all` |
+| `sortin.py` | Soft-maintain raw entries into mdbase | `python @/scripts/sortin.py --dry` |
+| `write_raw.py` | Append one raw thought | `python @/scripts/write_raw.py "Use REST APIs" --dim dev-stack` |
+| `toggle.py` | Toggle skill or instant mode | `python @/scripts/toggle.py instant on` |
+| `ignore_ops.py` | Manage ignored entries | `python @/scripts/ignore_ops.py show` |
+
+`resort` has no standalone script because it requires semantic review, deduplication, and restructuring by an agent.
+
+## define.ini
+
+`define.ini` stores simple key/value runtime state:
+
+| Key | Value | Meaning |
+|---|---|---|
+| `SKILL_STATUS` | `on` or `off` | Whether the skill accepts write operations |
+| `INSTANT_STATUS` | `on` or `off` | Whether instant capture is enabled |
+| `LAST_SORTIN` | `yyyy-mm-dd HH:MM` or empty | Last soft-maintenance time |
+
+Write the file atomically by replacing its complete contents. Do not append partial key/value fragments.
+
+## Commands
+
+Commands may use either `/user-thoughts` or `/ustht`.
+
+### Status and Toggles
+
+- `/ustht init`: create `.ustht/` and copy templates.
+- `/ustht status`: show status, raw counts, and dimension counts.
+- `/ustht skill`: show skill status.
+- `/ustht skill on|off`: enable or disable writes.
+- `/ustht instant`: show instant-capture status.
+- `/ustht instant on|off`: enable or disable instant capture.
+
+### Maintenance
+
+- `/ustht sortin [--dry]`: append unprocessed raw entries into mdbase.
+- `/ustht resort [--dry]`: semantically review and reorganize all mdbase content.
+
+### Ignore Management
+
+- `/ustht ignore start|end`: start or end an ignore interval.
+- `/ustht ignore --last`: remove the last raw entry and record it in `#ignored/`.
+- `/ustht ignore`: same as `--last` when used as a standalone command.
+- `/ustht ignore show`: list ignored entries.
+- Any message ending in `/ustht ignore` or `/user-thoughts ignore`: ignore that message.
+
+### Content Review and Export
+
+- `/ustht raw`: show unprocessed raw entries.
+- `/ustht mdbase show [--all|--dimension]`: show the index, all dimensions, or one dimension.
+- `/ustht mdbase export [--all|--dimension]`: export mdbase content to `#export/`.
+- `/ustht import <path>`: scan markdown files under a safe project-local path and merge project-relevant decisions into mdbase.
+
+Chain commands with `&&`, for example `/ustht skill on && instant on`.
+
+## Instant Capture
+
+When instant mode is active:
+
+1. Decide whether the user message contains project-relevant intent.
+2. Write one raw line per independent thought using `- [HH:MM] original text | suggested-dim:dimension`.
+3. Do not update mdbase directly; wait for `sortin`.
+4. Skip ignored messages and ignore intervals.
+5. Keep normal user work moving. Recording should not block task execution.
+6. If one day accumulates more than five raw entries, suggest `/ustht sortin`.
+
+## Sortin and Resort
+
+`sortin` is soft maintenance:
+
+1. Read unprocessed `#raw/*.md` files.
+2. Parse entries and their suggested dimensions.
+3. Append them to matching `#mdbase/` files grouped by date.
+4. Mark processed raw files with `<!-- processed -->` on the first line.
+5. Update `LAST_SORTIN` and the mdbase index.
+
+`resort` is hard maintenance:
+
+1. Review all mdbase files.
+2. Deduplicate overlapping records.
+3. Move entries into better dimensions when justified by the user's own wording.
+4. Mark deprecated dimensions instead of deleting them unless the user explicitly requests deletion.
+5. Preserve provenance and user wording.
+
+## Best Practices
+
+- Record explicit user decisions faithfully.
+- Do not over-infer. Store only what the user said or what follows directly from it.
+- Preserve original wording, including negations, numbers, links, constraints, and tradeoffs.
+- Split one message into multiple records when it contains independent decisions.
+- Resolve conflicts by treating the newest user statement as current while preserving the older record as historical context.
+- Put unmatched project-relevant items in `general.md` instead of inventing too many dimensions.
+- Do not record unrelated conversation.
+
+## Limitations
+
+- The skill records intent; it does not validate whether the user's idea is correct, feasible, secure, or internally consistent.
+- Dimension assignment depends on agent judgment and may need user correction through `resort`.
+- Ignore intervals are context-local and do not persist across sessions.
+- `.ustht/` can contain sensitive information. The skill does not redact content; users must use ignore commands or repository hygiene to manage sensitive data.
+- The workflow is not file-lock based. In multi-agent environments, agents must coordinate to avoid conflicting writes.
+
+## Safety Rules
+
+- Keep all runtime writes inside `#ustht/`.
+- Validate dimension names: lowercase letters, digits, hyphens, and `/` subdirectories only; no `..`, backslashes, spaces, absolute paths, or reserved names.
+- Do not execute user-provided shell commands.
+- Do not recursively copy directories with shell commands during initialization; copy known template files safely.
+- Treat `<!-- processed -->` as meaningful only when it is the first line of a raw file.
+- Never silently delete dimension files; mark deprecated content unless the user explicitly asks for deletion.
+
+More detail is available in `references/safety.md`, `references/sortin.md`, `references/commands.md`, and `references/edge-cases.md`.
+
+## Related Skills
+
+None. This skill is intentionally focused on project-local user intent persistence.

package/bundled-skills/user-thoughts/assets/Runtime-Template/README.ai.md

@@ -0,0 +1,13 @@
+# user-thoughts Runtime Directory
+
+This directory stores project-local user intent captured by `user-thoughts`.
+
+## Contents
+
+- `define.ini`: runtime state for the skill.
+- `raw/`: unprocessed user thoughts captured by date.
+- `ignored/`: entries the user explicitly chose not to record.
+- `mdbase/`: organized project memory grouped by dimension.
+- `export/`: exported mdbase content.
+
+Do not delete this directory unless the user explicitly wants to discard project memory.

package/bundled-skills/user-thoughts/assets/Runtime-Template/define.ini

@@ -0,0 +1,3 @@
+SKILL_STATUS=on
+INSTANT_STATUS=off
+LAST_SORTIN=

package/bundled-skills/user-thoughts/assets/Runtime-Template/mdbase/README.ai.md

@@ -0,0 +1,25 @@
+# user-thoughts mdbase Index
+
+This directory stores user-provided project decisions, constraints, preferences, and plans. Keep the user's original intent intact.
+
+Last updated: never
+
+## Maintenance Rules
+
+- Preserve details from user wording. Do not simplify away constraints, numbers, negations, or examples.
+- Classify entries by dimension so future agents can find them quickly.
+- Prefer existing dimensions. Create a new dimension only when the user's thought clearly needs one.
+- Append new records by date under `## yyyy-mm-dd` headings.
+- Do not delete historical content unless the user explicitly asks for deletion.
+
+## Document Index
+
+| File | Dimension | Entries |
+|------|-----------|---------|
+| [backlog.md](backlog.md) | backlog | 0 |
+| [details/rules.md](details/rules.md) | rules | 0 |
+| [details/plans.md](details/plans.md) | plans | 0 |
+| [details/dev-stack.md](details/dev-stack.md) | dev-stack | 0 |
+| [details/ui/outline.md](details/ui/outline.md) | ui/outline | 0 |
+| [details/ui/details.md](details/ui/details.md) | ui/details | 0 |
+| [details/general.md](details/general.md) | general | 0 |

package/bundled-skills/user-thoughts/assets/Runtime-Template/mdbase/backlog.md

@@ -0,0 +1,19 @@
+# Backlog
+
+> User plans, pending tasks, and work that has been requested but not started.
+
+## Pending
+
+<!-- Items explicitly requested by the user but not started yet. -->
+
+## In Progress
+
+<!-- Items that have started but are not complete. -->
+
+## Done
+
+<!-- Completed items retained for traceability. -->
+
+## Notes
+
+Record the date each item was raised. When an item is completed, move it to Done and include the completion date when known.

package/bundled-skills/user-thoughts/assets/Runtime-Template/mdbase/details/dev-stack.md

@@ -0,0 +1,7 @@
+# Development Stack Decisions
+
+> Frameworks, libraries, services, deployment choices, data stores, APIs, and other technical stack decisions.
+
+## Current Decisions
+
+<!-- Append dated user decisions here. -->