Writing Hookify Rules
CheckedAkiojin's hookify-rules generates compelling opening sentences based on provided text, adhering to specified writing rules.
Install on your platform
writing-hookify-rules. akiojin/llmlb has no skill named "writing-hookify-rules" any more. It was renamed, moved or deleted upstream.We check each listing against its upstream repository with the rules the skills CLI uses, last on 2026-10-30. We don't show a command we know will fail.
What we know about this skill
Publisher
akiojin
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned akiojin/llmlb at 6c899c1505.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 6c899c1505
- Scanned
- 2 files, 732 lines
- Copies in repo
- 2 — all of them scanned
About this skill
What it does
This skill allows you to generate rules in a specific format called "Hookify." These rules are designed to guide AI agent behavior and responses, enabling more structured interactions. It can create rules that define actions, conditions, and expected outcomes for an AI agent. The generated rules adhere to the Hookify syntax, making them readily usable within compatible systems.
When to use it
- Defining Agent Actions: You need a clear set of instructions for your AI agent on how to respond in specific situations (e.g., "If user asks about weather, fetch and present current conditions").
- Creating Structured Conversations: You want to control the flow of a conversation with an AI agent, ensuring it follows a predetermined path or logic.
- Automating Rule Generation: You have a large number of scenarios that require specific AI responses and want to automate the creation of corresponding rules.
- Standardizing Agent Behavior: You need to ensure consistency in how your AI agents respond across different interactions and contexts.
Key capabilities
- Generates Hookify-formatted rules.
- Defines actions for AI agents.
- Specifies conditions that trigger actions.
- Outlines expected outcomes of agent responses.
Example prompts
- "Create a Hookify rule to respond with 'Hello, how can I help you?' when the user greets the agent."
- "Generate a Hookify rule for an AI assistant that fetches and displays current weather conditions if asked about the weather."
- "Write a Hookify rule that prompts the user for their name after they say hello."
Tips & gotchas
- Familiarity with the Hookify syntax is helpful to refine the generated rules. The skill assumes you understand how these rules are structured and intended to be used within a larger system.