Discovery Brief Window — Development skill for Claude Code
Discovery Brief — Window Over Recent Scan Output.
How to install Discovery Brief Window
Installs to ~/.claude/skills/dzivkovi-video-intel-discovery-brief-window/SKILL.md
mkdir -p ~/.claude/skills/dzivkovi-video-intel-discovery-brief-window && curl -fsSL https://raw.githubusercontent.com/dzivkovi/video-intel/HEAD/prompts/discovery-brief-window.md -o ~/.claude/skills/dzivkovi-video-intel-discovery-brief-window/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Discovery Brief Window does
Discovery Brief — Window Over Recent Scan Output
Role
Act as a corpus analyst standing over a freshly scanned set of video artifacts. You have direct file access to a video-intel `output_dir/`. Your job is to write a 1-page "state of the corpus" briefing that surfaces signal a person would NOT catch from scan logs alone.
Scan logs say *"scanned N videos, M new concepts."* A good brief says *"Channels X, Y, Z all converged on concept Q this week; concept R has gone silent after being week
Alternatives in Development
- Review Claudemd — Review recent conversations to find improvements for CLAUDE.md files 6.5k ★
- Recent Memories — Display the most recent memories and activity from Claude's persistent storage 332 ★
- Obsidian Emerge — Surface unnamed patterns from your recent notes — recurring themes, hidden connections, and conclusions you ha 277 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Mt Cancel
Cancel your most recent trade (5-minute window)
Promote Patterns
Scan recent craft notes for clusters that meet pattern-promotion criteria, and promote them to craft/patterns/
Job Scan
Scan Simplify Jobs' New-Grad or Internship board for recent postings, filtered interactively by category and r
Brain Brief
Load a quick session-start orientation - who you are, your North Star, recent activity, and what is open. Read
Toonify MCP
Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, an
Hoangsa
HOANGSA is a context engineering system for Claude, Codex. It solves a fundamental problem: Claude's output qu
Related Agents
Tp Incident Timeline
PROACTIVELY use this when the user reports a production incident and asks "what changed before this", "what wa
Cross Linker
Scan recent or specified notes for missing wikilinks. Finds mentions of people, projects, teams, competencies,
Staging Log Verifier
Use this agent to fetch staging service logs for a deploy window, scan them for errors, warnings, and stack tr