add-highlight

Add an item to the highlights page. Max 1 per day.

181 stars

Best use case

add-highlight is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Add an item to the highlights page. Max 1 per day.

Teams using add-highlight should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/add-highlight/SKILL.md --create-dirs "https://raw.githubusercontent.com/majiayu000/claude-skill-registry/main/skills/data/add-highlight/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/add-highlight/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How add-highlight Compares

Feature / Agentadd-highlightStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Add an item to the highlights page. Max 1 per day.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Add Highlight

Add a notable item to the public highlights (What's New) page.

## When to Use

- After writing a new article worth sharing
- When research reveals something interesting
- When a review finds a significant insight
- Any time something is worth publicising
- Manual invocation: `/add-highlight [topic]`

## Instructions

### 1. Check Rate Limit

Use the CLI to check if we can add today:

```bash
uv run python scripts/highlights.py check
```

Only 1 highlight per day is allowed. If already added today, skip silently and note in output that a highlight was already added.

### 2. Compose Highlight

Determine the content:

- **Title**: Short, engaging (5-10 words). Should make someone want to click.
- **Description**: 1-2 sentences explaining what's new or interesting. Max 280 characters (Twitter-ready).
- **Type**: One of:
  - `new-article` - A new piece of content was created
  - `insight` - An interesting finding from review or analysis
  - `research` - Research notes or discoveries
  - `refinement` - Significant improvement to existing content
- **Link**: Wikilink to the relevant content (e.g., `[[hard-problem-of-consciousness]]`)

### 3. Add via CLI

```bash
uv run python scripts/highlights.py add "Title Here" "Description of what's interesting, max 280 chars." --type new-article --link "[[article-name]]"
```

### 4. Post to Twitter (Optional)

If Twitter is configured (credentials in `.env`), add the `--tweet` flag:

```bash
uv run python scripts/highlights.py add "Title" "Description" --type new-article --link "[[article]]" --tweet
```

To test formatting without posting:

```bash
uv run python scripts/highlights.py add "Title" "Description" --type new-article --link "[[article]]" --tweet --dry-run
```

**Note:** Twitter posting is optional. If credentials aren't configured, the highlight is added and a warning is logged. Twitter failures never block highlight creation.

### 5. Verify Addition

The CLI will confirm success or report rate limiting.

## Content Guidelines

**Good highlights are:**
- Genuinely interesting to a general audience
- Understandable without deep context
- Engaging enough to click through
- Connected to The Unfinishable Map's philosophical mission

**Skip these (not highlight-worthy):**
- Routine maintenance (validate-all, check-links)
- Minor refinements with no new insight
- Failed or blocked tasks
- Internal workflow changes

## Examples

### New Article
```bash
uv run python scripts/highlights.py add \
  "Why Materialism Can't Explain Consciousness" \
  "New article argues that all forms of materialism fail to account for subjective experience. The hard problem isn't just unsolved—it may be unsolvable in principle." \
  --type new-article \
  --link "[[materialism]]"
```

### Research Insight
```bash
uv run python scripts/highlights.py add \
  "Buddhist Perspectives Challenge Western Assumptions" \
  "Research into Buddhist philosophy reveals that the self-consciousness problem looks different from a tradition that questions the self's existence entirely." \
  --type research \
  --link "[[buddhist-perspectives-meaning]]"
```

### Review Finding
```bash
uv run python scripts/highlights.py add \
  "Decoherence Timescales Present Real Challenge" \
  "Pessimistic review identified that quantum decoherence in warm brains happens in femtoseconds—nine orders of magnitude faster than neural processes." \
  --type insight \
  --link "[[consciousness-selecting-neural-patterns]]"
```

## Automated Invocation (from evolve_loop)

The evolution loop automatically invokes this skill at **8am UTC daily** when there's highlight-worthy work from today's successful tasks. It passes task context via `--from-task`.

### When invoked with `--from-task`

Parse the task info and compose an appropriate highlight:

1. **Parse the context** (e.g., `expand-topic: concepts/qualia.md`)
2. **Read the relevant file** to understand what was created/changed
3. **Compose an engaging highlight**:
   - **Title**: 5-10 words, engaging, makes people want to click
   - **Description**: 1-2 sentences, max 280 chars
   - **Type**: new-article, insight, research, or refinement
   - **Link**: wikilink to the content
4. **Call the CLI** with `--tweet` flag

### Example

Input: `--from-task 'expand-topic: concepts/quantum-timing.md' --tweet`

Steps:
1. Read `obsidian/concepts/quantum-timing.md`
2. Understand the article's thesis
3. Compose highlight and run:

```bash
uv run python scripts/highlights.py add \
  "Quantum Timing: When Mind Meets Matter" \
  "New article maps timescales from femtosecond decoherence to 300ms decisions, showing how quantum effects must operate within neural constraints." \
  --type new-article \
  --link "[[quantum-timing]]" \
  --tweet
```

The `--tweet` flag triggers the full chain: **add → commit → push → wait for deployment → tweet**.

### Task type to highlight type mapping

| Task Type | Highlight Type |
|-----------|---------------|
| expand-topic | new-article |
| research-topic | research |
| research-voids | research |
| deep-review | insight |
| coalesce | new-article |
| apex-evolve | new-article |
| backlog | (infer from content - see below) |

### Handling backlog content

When invoked with `--from-task 'backlog: obsidian/path/to/file.md'`, this means we're highlighting existing content that hasn't been featured in the last 90 days. This is NOT necessarily new work—it's content worth sharing that hasn't had recent attention.

1. **Read the file** at the given path
2. **Determine highlight type** from the file's directory:
   - `obsidian/topics/` → new-article (even if old, it's an article)
   - `obsidian/concepts/` → new-article
   - `obsidian/apex/` → new-article
   - `obsidian/voids/` → insight (these explore cognitive limits)
3. **Compose an engaging highlight**:
   - The title and description should present the content as interesting/worth reading
   - Don't frame it as "new" if it's older content—just make it sound appealing
   - Focus on the most compelling aspect of the article
4. **Call the CLI** with appropriate flags

## Important

- **Max 280 characters** for descriptions (Twitter-ready for future integration)
- **Max 1 highlight per day** (enforced by the manager)
- **Always use wikilinks** for the link field
- **Skip routine maintenance** - only highlight interesting work
- The highlights page auto-trims to 20 items

Related Skills

adding-markdown-highlighted-comments

181
from majiayu000/claude-skill-registry

Use when adding responses to markdown documents with user-highlighted comments, encountering markup errors, or unsure about mark tag placement - ensures proper model-highlight formatting with required attributes and correct placement within markdown elements

vly-money

159
from majiayu000/claude-skill-registry

Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.

Fintech & CryptoClaude

ontopo

159
from majiayu000/claude-skill-registry

An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.

General Utilities

whisper-transcribe

159
from majiayu000/claude-skill-registry

Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.

Media Processing

chrome-debug

159
from majiayu000/claude-skill-registry

This skill empowers AI agents to debug web applications and inspect browser behavior using the Chrome DevTools Protocol (CDP), offering both collaborative (headful) and automated (headless) modes.

Coding & DevelopmentClaude

modal-deployment

159
from majiayu000/claude-skill-registry

Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.

DevOps & Infrastructure

astro

159
from majiayu000/claude-skill-registry

This skill provides essential Astro framework patterns, focusing on server-side rendering (SSR), static site generation (SSG), middleware, and TypeScript best practices. It helps AI agents implement secure authentication, manage API routes, and debug rendering behaviors within Astro projects.

Coding & Development

thor-skills

159
from majiayu000/claude-skill-registry

An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.

SecurityClaude

ux

159
from majiayu000/claude-skill-registry

This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.

UX Design & StrategyClaude

lets-go-rss

159
from majiayu000/claude-skill-registry

A lightweight, full-platform RSS subscription manager that aggregates content from YouTube, Vimeo, Behance, Twitter/X, and Chinese platforms like Bilibili, Weibo, and Douyin, featuring deduplication and AI smart classification.

Content & Documentation

tech-blog

159
from majiayu000/claude-skill-registry

Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.

Content & DocumentationClaude

grail-miner

159
from majiayu000/claude-skill-registry

This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.

DevOps & Infrastructure