← Back to Skills Marketplace
Amm
by
bytesagain1
· GitHub ↗
· v1.0.0
· MIT-0
159
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install amm
Description
Analyze amm operations. Use when you need to understand amm mechanisms, evaluate protocol security, or reference on-chain concepts.
README (SKILL.md)
Amm
Analyze amm operations. Use when you need to understand amm mechanisms, evaluate protocol security, or reference on-chain concepts.
When to Use
- status: Show current status
- add: Add new entry
- list: List all entries
- search: Search entries
- remove: Remove entry by number
- export: Export data to file
- stats: Show statistics
- config: View or set config
Commands
status
scripts/script.sh status
Show current status
add
scripts/script.sh add
Add new entry
list
scripts/script.sh list
List all entries
search
scripts/script.sh search
Search entries
remove
scripts/script.sh remove
Remove entry by number
export
scripts/script.sh export
Export data to file
stats
scripts/script.sh stats
Show statistics
config
scripts/script.sh config
View or set config
help
scripts/script.sh help
version
scripts/script.sh version
Configuration
Use scripts/script.sh config \x3Ckey> \x3Cvalue> to customize behavior.
| Variable | Description |
|---|---|
AMM_DIR |
Data directory (default: ~/.amm/) |
Powered by BytesAgain | bytesagain.com | [email protected]
Usage Guidance
This is a small local CLI that stores its data under ~/.amm by default (or a directory you set via the AMM_DIR environment variable). There are no network calls or credential requests. Before installing/running: (1) review the script (scripts/script.sh) yourself — it will create and write files in your home directory; (2) if you want data elsewhere, set AMM_DIR in your environment before running (the tool's config command cannot change which DATA_DIR is used); (3) be aware entries are appended as simple JSONL — input is not strongly escaped, so avoid storing secrets you don't want in plain text; (4) run with normal caution for any shell script provided by third parties.
Capability Analysis
Type: OpenClaw Skill
Name: amm
Version: 1.0.0
The 'amm' skill is a basic local data management tool for logging and searching strings related to blockchain AMM operations. The script (scripts/script.sh) implements simple CRUD functionality (add, list, search, remove, export) targeting a local directory (~/.amm/) and contains no evidence of data exfiltration, remote code execution, or malicious intent.
Capability Assessment
Purpose & Capability
Name/description (analyzing AMM operations) match the included shell script and SKILL.md: the tool is a local note/entry manager for AMM analysis. There are no unrelated credentials, network endpoints, or surprising dependencies. One small documentation mismatch: SKILL.md documents AMM_DIR as a configurable variable but implies use via the 'config' command; in reality AMM_DIR must be set as an environment variable before running (the config command writes to DATA_DIR, so it cannot change which DATA_DIR is used).
Instruction Scope
Runtime instructions call scripts/script.sh with specific commands (status, add, list, search, etc.). The script only reads/writes files under DATA_DIR (default ~/.amm) and prints local stats. It does not call external network services, read arbitrary system files, or access unrelated environment variables. The only scope concern is the SKILL.md wording around configuring AMM_DIR (see purpose_capability note).
Install Mechanism
No install spec; this is instruction-only with a bundled shell script. No downloads, installers, or external packages are fetched. Risk is limited to executing the provided script; review before running as with any script.
Credentials
No required credentials or secret environment variables. The only optional env var is AMM_DIR to change the data directory, which is reasonable and minimal for a local data tool.
Persistence & Privilege
The skill does not request permanent/autonomous privileges (always:false) and does not modify other skills or system-wide agent settings. It persists only its own data under the user's DATA_DIR.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install amm - After installation, invoke the skill by name or use
/amm - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
publish v1.0.0
Metadata
Frequently Asked Questions
What is Amm?
Analyze amm operations. Use when you need to understand amm mechanisms, evaluate protocol security, or reference on-chain concepts. It is an AI Agent Skill for Claude Code / OpenClaw, with 159 downloads so far.
How do I install Amm?
Run "/install amm" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Amm free?
Yes, Amm is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Amm support?
Amm is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Amm?
It is built and maintained by bytesagain1 (@bytesagain1); the current version is v1.0.0.
More Skills