brainstorming
Structured design dialogue that validates ideas before implementation begins.
coalesce
Combine multiple related articles into one unified piece. Archives originals to preserve URLs.
Full skill instructions
Merge multiple related articles into a single unified piece, archiving the originals to preserve their URLs for external links.
/coalesceProvide as space-separated arguments or answer when prompted:
obsidian/concepts/article-1.md,obsidian/concepts/article-2.mdobsidian/topics/new-unified-article.mdExample: /coalesce obsidian/concepts/a.md,obsidian/concepts/b.md obsidian/topics/combined.md
Verify all source files exist and target location is valid:
If arguments are not provided, search for articles that exhibit overlap and duplication, or are strong candidates for merging. Choose the most promisng two or more for candidates merging, If there are no good candidates, abandon the attempt and do not merge anything.
Read all source articles and identify:
Also search for external references to these articles:
grep -r "[[source-slug" obsidian/
If you selected aricles automaticall but find that the articles ar well-differntiated and should not be merged, search again. If after five iterations there are still no strong candiates, abaon the attempt and do not merge anything.
Create a mental outline:
Create the new article at the target location.
Frontmatter:
---
title: "[Unified Title]"
created: [earliest source created date]
modified: [today's date]
human_modified: [latest human_modified from sources, or null]
ai_modified: [current timestamp]
draft: false
topics: [merge from sources, deduplicate]
concepts: [merge from sources, deduplicate]
related_articles: [merge from sources, remove self-references, deduplicate]
ai_contribution: [calculate: if all sources were AI, use 100; if mixed, estimate]
author: [preserve if any human-authored sources]
ai_system: [current model]
ai_generated_date: [today]
last_curated: null
coalesced_from:
- "/[section]/[source-1-slug]/"
- "/[section]/[source-2-slug]/"
---
Content guidelines:
For each source article:
Calculate archive path: archive/[original-section]/[slug].md
obsidian/concepts/old-article.md → archive/concepts/old-article.mdMove file to archive directory (preserving content)
Update frontmatter with archive metadata:
archived: true
archived_date: [current ISO timestamp]
superseded_by: "/[target-section]/[target-slug]/"
archive_reason: "Coalesced into [new article title]"
original_path: "/[original-section]/[original-slug]/"
The original content remains intact below the frontmatter. The archive notice will be displayed by Hugo templates.
Search for wikilinks to the archived articles in active content:
grep -r "\[\[source-slug" obsidian/
For each reference found:
If this was a todo item, mark it complete.
If references were found to archived articles, create a follow-up task:
### P2: Update references to coalesced articles
- **Type**: other
- **Notes**: Coalesce created [new-article]. The following files reference archived articles and may need review: [list files]
- **Source**: coalesce
- **Generated**: [today]
Append to obsidian/workflow/changelog.md:
### HH:MM - coalesce
- **Status**: Success
- **Sources**: [list of source files]
- **Target**: [new article path]
- **Archived**: [list of archive paths]
- **References to review**: [count or "none"]
Create a git commit:
feat(content): coalesce [N] articles into [new-article-slug]
Merged:
- [source-1] → archive/[section]/[slug].md
- [source-2] → archive/[section]/[slug].md
New article: [target-path]
Structured design dialogue that validates ideas before implementation begins.
Comprehensive design intelligence for web and mobile UI/UX across 10 technology stacks.
Comprehensive implementation plans for multi-step tasks, breaking down specs into bite-sized, testable steps.
Introduction to the obra skills system with mandatory skill invocation rules and best practices.
Execute a written implementation plan with critical review and task checkpoints.
Delegate independent tasks to specialized agents working concurrently with isolated context.
Isolated git worktrees with smart directory selection and safety verification.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Plan searchable and shareable content that drives traffic, builds authority, and generates leads.
README-first repository scanner that extracts commands and classifies reproduction candidates without executing them.
Brainstorm and prioritize marketing strategies tailored to your SaaS stage, budget, and goals.
Plan and optimize your website's page hierarchy, navigation, URL structure, and internal linking.
The world's fastest calendar for remote work
Capture, organize, and utilize your knowledge effortlessly.
Instant Summaries of Audio & Video Interviews with AnySummary
Transform PDFs into engaging mind maps.
Chat with any PDF instantly
Create an optimal daily plan using your voice
A productivity platform to centralize organizational knowledge and workflows with contextual AI assistance.
AskYourPDF Pricing Plans: Tailored to Your Needs