Filter CLI output through a declarative YAML DSL.
npx skills add https://github.com/edouard-claude/snip --skill tool-subcommand
Please help me install this Agent Skill. Skill: tool-subcommand Source: https://github.com/edouard-claude/snip/tree/main Command: npx skills add https://github.com/edouard-claude/snip --skill tool-subcommand
Snip users often contend with noisy, verbose CLI output that blooms the AI context. This Skill provides a declarative YAML DSL to filter and condense command output so you can focus on signal.
Create a new YAML filter under filters/your-tool.yaml and run snip with your command to apply it.
High-intent search queries and answers about installing and using this skill.
You can reduce token usage by applying declarative YAML filters to CLI output, condensing command results to focus on signal. This Skill uses a 19-action DSL to keep, remove, transform, and extract relevant lines before they enter the context window.
To create a YAML filter, define your desired transformations using the 19-action DSL in a new file under filters/your-tool.yaml. Running the CLI command through the snip tool then automatically applies these declarative filtering rules to the output.
A declarative DSL for CLI filtering uses a 19-action vocabulary to specify deterministic pipelines that keep, remove, or transform lines. It processes command output safely with built-in fallbacks to preserve original exit codes and prevent data loss.
Yes, you can customize CLI output filters by placing YAML files in per-project directories or user-level paths like ~/.config/snip/filters. The system also loads built-in filters embedded directly in the binary for flexible workflow customization.
Yes, the YAML filtering Skill requires a SKILL.md frontmatter containing a name and description to function properly. This metadata ensures the 19-action DSL pipelines execute with deterministic behavior and safe fallbacks.
Filtering CLI output through YAML preserves the original command exit codes by utilizing safe, deterministic pipelines with built-in fallbacks. This error handling ensures that condensing output for token savings does not result in data loss or failed executions.
Bitterbot-AIList, configure, authenticate, and call MCP servers and tools via CLI.
SamuelSahaReduce AI token consumption via shallow skill loading, context pruning, and output compression.
MuhammadUsmanGMExecute MCP calls in external scripts to minimize agent context tokens.
GrupoUSProvide Bash and Linux terminal commands for file, process, and text management.
