SkillCheatSheet
crush-hooks
An AI agent skill from charmbracelet/crush, scored 74 out of 100 by code.
Code score by group
It loses the most points in Description (9), the group that checks whether the description says what the skill does and when to use it.
What the author says it does
Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.
This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.
- Repository
- charmbracelet/crush
- Folder
- internal/skills/builtin/crush-hooks
- License
- Not identified by GitHub
- GitHub stars
- 29,057
- SKILL.md lines
- 246
- Other files
- 0
Add crush-hooks to your agent
npx skills add charmbracelet/crush --skill crush-hooksThe command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored. GitHub identifies no license for this repository, so check its terms before you use it.
Labelled for
More skills from charmbracelet/crush
-
builtin-skills
Use when creating a new builtin skill for Crush, editing an existing builtin skill (internal/skills/builtin/), or when the user needs to understand how the embedded skill system w…
59C -
shell-builtins
Use when creating a new shell builtin command for Crush (internal/shell/), editing an existing one, or when the user needs to understand how commands are intercepted in Crush's em…
58C -
crush-config
Use when the user needs help configuring Crush — writing crushrc (the Bash config format) or crush.json, setting up providers, models, LSPs, MCP servers, hooks, skills, permission…
57C -
jq
Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when he…
54D
All skills in charmbracelet/crush
Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.