user-thoughts
Helps your agent remember project decisions and rules. This is useful for maintaining consistency in future conversations.
What it does
This tool helps save important project decisions. It stores what you decide about rules, technologies, or appearance, so you or other AIs can remember it later without having to ask again.
When to use it
- ✓When you define project rules.
- ✓When choosing the technologies to be used.
- ✓When deciding how the project should look or function.
Example of what to ask your AI
“Remember that the main button should be blue.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
When you say something important about the project, the AI saves that information. Later, it organizes everything so it can be easily found and used in other conversations or by other AIs.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add sickn33/agentic-awesome-skills --skill user-thoughtsOr download just the file:
curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/plugins/agentic-awesome-skills-claude/skills/user-thoughts/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
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-thoughtsor/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
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=onandSKILL_STATUS=on; project-relevant user thoughts are written to#raw/as they appear. - Ignore mode:
ignore startandignore endmark 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 installeduser-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
.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
sortinorresortmaintenance 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 |
|---|
…
FAQ
What happens if I say something I don't want saved?
You can say "/ustht ignore start" before and "/ustht ignore end" after to prevent that part of the conversation from being saved.
How do I see what has been saved?
You can use commands like "/ustht raw" to see what was recently noted or "/ustht mdbase show" to see the organized decisions.
Will the AI change what I said?
No, the AI saves your decisions exactly as you said them, unless you ask it to summarize or organize.
Details
Original description by the author
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.
Popularity
- GitHub stars
- 48k
- Ranking position
- #4464
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
00-andruia-consultant
Helps your agent start or improve AI projects. It analyzes code, suggests tools, and creates action plans in Spanish.
sickn33/agentic-awesome-skills
007
Lets your agent perform security audits and threat modeling. It's useful for protecting projects against attacks and vulnerabilities.
sickn33/agentic-awesome-skills
10-andruia-skill-smith
Helps your agent create or improve AI tools. It defines how tools work, writes documentation, and validates the structure.
sickn33/agentic-awesome-skills
20-andruia-niche-intelligence
Lets your agent create a summary about a specific industry. It's useful for understanding the context, rules, usage patterns, and risks of a project, using reliable sources.
sickn33/agentic-awesome-skills
Similar skills
agent-architecture-audit
Makes your agent check if everything is working correctly. It finds and fixes problems in AI systems, ensuring they perform as expected.
affaan-m/ECC
agent-eval
Helps your agent compare different AI coding tools. It measures which one is faster, cheaper, and more reliable for specific tasks.
affaan-m/ECC
agent-harness-construction
Makes your agent better understand how to perform tasks. It optimizes the tools and instructions the agent uses to increase its chances of success.
affaan-m/ECC