skill-with-hooks
Skill8 starsChanged 10 months agoMITView on GitHub
Example skill demonstrating embedded hooks for validation and logging
In this repository3 other files it gives its agents.
- amplifier-philosophySkill
- module-developmentSkill
- python-standardsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
When this skill is loaded, its hooks become active for the session:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill With Hooks Example
This is an example skill that demonstrates how to embed Claude Code-compatible hooks directly in a skill's frontmatter.
Purpose
When this skill is loaded, its hooks become active for the session:
- PreToolUse (Bash): Validates bash commands before execution
- PreToolUse (all tools): Logs all tool invocations
- PostToolUse (all tools): Logs tool results
Hook Scripts
The hooks reference scripts in the ./hooks/ directory relative to this skill:
validate-bash.sh- Checks bash commands for dangerous patternslog-tool-use.sh- Logs tool name and parameterslog-tool-result.sh- Logs tool execution results
Usage
Load this skill to activate its hooks:
load_skill(skill_name="skill-with-hooks")The hooks will remain active until the session ends.
Testing
This skill is used to validate the skill-scoped hooks integration between
amplifier-module-tool-skills and amplifier-module-hooks-shell.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.