feat(skills): add smart-bash context-compressing bash proxy#14
Open
rrp-bot wants to merge 1 commit into
Open
Conversation
Introduces .claude/skills/smart-bash.md — a Claude Code skill that runs bash commands via the Bash tool and returns a concise 2-5 sentence synthesis rather than raw output. Uses context: fork to avoid polluting the calling context. Explains failures with a suggested fix. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a new Claude Code skill at
.claude/skills/smart-bash.md— a context-compressing bash proxy that runs shell commands and returns a concise 2–5 sentence synthesis rather than raw output.What the skill does
$ARGUMENTScontaining a bash command, with an optional embedded plain-English question or intentWhy
context: forkmattersThe skill uses
context: forkin its frontmatter. This causes Claude to execute the skill in a forked context, meaning the raw command output and intermediate reasoning are discarded after the skill returns. Only the 2–5 sentence synthesis propagates back to the calling context, preventing large terminal outputs from bloating the main conversation thread during long agentic sessions.Failure handling
When a command exits non-zero or produces error output, the skill explains what failed and provides one specific, actionable fix — rather than quoting the raw error.
Files changed
.claude/skills/smart-bash.md(new file) — the skill definition withcontext: forkfrontmatterWork item
SKILL-SMART-BASH
Generated by spec-to-pr