boundary-bbcr-fallback
Execute automatic BBCR (Collapse-Rebirth Correction) when knowledge boundaries are exceeded or reasoning fails.
Create Linear tasks from pull requests
$ npx -y skills add qdhenry/Claude-Command-Suite --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/task-from-prContext preview
What this command does when you run it.
Create Linear tasks from pull requests
Create Linear tasks from pull requests
This command analyzes GitHub pull requests and creates corresponding Linear tasks, automatically extracting key information like title, description, labels, and assignees. It helps maintain synchronization between GitHub development workflow and Linear project management.
# Convert a specific PR to a Linear task claude "Convert PR #123 to a Linear task" # Convert multiple PRs from a repository claude "Convert all open PRs to Linear tasks for repo owner/repo" # Convert PR with custom mapping claude "Create Linear task from PR #456 and assign to team 'Engineering'"
First, use GitHub CLI to fetch PR details:
# Get PR information gh pr view <PR_NUMBER> --json title,body,labels,assignees,state,url,createdAt,updatedAt,milestone # List all open PRs gh pr list --json number,title,labels,assignees --limit 100
Extract structured information from the PR body:
Common label mappings:
Generate Linear task structure:
{
title: `[PR #${prNumber}] ${prTitle}`,
description: `
**GitHub PR:** ${prUrl}
## Summary
${extractedSummary}
## Changes
${bulletPoints}
## Acceptance Criteria
${checklistItems}
## Technical Details
${codeSnippets}
`,
priority: mapPriorityFromLabels(labels),
labels: mapLabelsToLinear(labels),
estimate: estimateFromPRSize(additions, deletions),
assignee: mapGitHubUserToLinear(assignees[0])
}Calculate estimates based on PR metrics:
- Tiny (1 point): < 10 lines changed - Small (2 points): 10-50 lines changed - Medium (3 points): 50-250 lines changed - Large (5 points): 250-500 lines changed - X-Large (8 points): > 500 lines changed Adjust based on: - Number of files changed (multiply by 1.2 if > 10 files) - Presence of tests (multiply by 0.8 if tests included) - Documentation changes (multiply by 0.7 if only docs)
Use Linear MCP to create the task:
// Example Linear task creation
const task = await linear.createTask({
title: taskTitle,
description: taskDescription,
teamId: getTeamId(),
priority: priority,
estimate: estimate,
labels: labelIds,
assigneeId: assigneeId
});
// Link back to GitHub PR
await linear.createComment({
issueId: task.id,
body: `Linked to GitHub PR: ${prUrl}`
});Handle common scenarios:
// Check for Linear MCP availability
if (!linear.available) {
console.error("Linear MCP tool not available. Please ensure it's configured.");
return;
}
// Check for GitHub CLI
try {
await exec('gh --version');
} catch (error) {
console.error("GitHub CLI not installed. Please install: https://cli.github.com/");
return;
}
// Handle duplicate tasks
const existingTask = await linear.searchTasks(`PR #${prNumber}`);
if (existingTask) {
console.log(`Task already exists for PR #${prNumber}: ${existingTask.url}`);
return;
}Converting PR #123 to Linear task... Fetched PR details: - Title: Add user authentication middleware - Author: @johndoe - Labels: feature, backend, security - Size: 234 lines changed across 8 files Parsed description: - Summary: Implements JWT-based authentication - Has 5 checklist items (3 completed) - References issues: #98, #102 Creating Linear task... ✓ Task created: LIN-456 Title: [PR #123] Add user authentication middleware Team: Backend Priority: High (due to security label) Estimate: 3 points Labels: Feature, Backend, Security Assignee: John Doe Task URL: https://linear.app/yourteam/issue/LIN-456
Convert multiple PRs:
# Convert all PRs with specific label
gh pr list --label "needs-task" --json number | \
jq -r '.[].number' | \
xargs -I {} claude "Convert PR #{} to Linear task"Map PR metadata to Linear custom fields:
Set up webhook to automatically create tasks when PRs are opened:
// Webhook handler
on('pull_request.opened', async (event) => {
await createLinearTaskFromPR(event.pull_request);
});A comprehensive development toolkit designed following Anthropic's Claude Code Best Practices for AI-assisted software development.
Repo: qdhenry/Claude-Command-Suite
Execute automatic BBCR (Collapse-Rebirth Correction) when knowledge boundaries are exceeded or reasoning fails.
Analyze semantic position relative to knowledge boundaries to prevent hallucination and identify uncertainty zones.
Generate a visual heatmap of knowledge boundaries showing safe zones, risk areas, and semantic coverage.
Evaluate the current risk level and provide detailed analysis of potential hallucination or reasoning failure.
Find and construct semantic bridges to safely navigate from current position to target concept without crossing dangerous boundaries.
Takes an input prompt and returns ONLY a token-optimized version that preserves meaning while minimizing token count. Based on LLM tokenization principles:…