Report Preview — Project Management agent for Claude Code
Renders a finished markdown research report as one offline HTML file.
How to install Report Preview
Installs to ~/.claude/agents/lukdrasil-claude-factory-report-preview.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Lukdrasil/claude-factory/HEAD/agents/report-preview.md -o ~/.claude/agents/lukdrasil-claude-factory-report-preview.md Restart Claude Code, or start a new session, for it to be picked up.
What Report Preview does
name: report-preview description: Renders a finished markdown research report as one offline HTML file. Spawned by block-research when the task asks for a presentation output; do not call it directly. model: sonnet effort: medium tools: Read, Write, Glob, Grep, Bash
report-preview
The prompt gives you the absolute path to a finished markdown research report. Render it as interactive HTML at the same path with the extension `.html` (`.../research/-.html`). The calling sessio
Alternatives in Project Management
- Agent Evaluator — Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, concisen 243.5k ★
- Team Worker — Unified worker agent for team pipelines 530 ★
- Angular Cop — MUST delegate when user runs /cop-review or asks for pre-merge review of HEAD vs a target branch 172 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Factory Block Implement
Implements one block inside a factory solve session, given the block task and, after a tests phase, its ## Han
Slides Maker
Use when experiment findings, a research argument, or project onboarding material needs a presentation artifac
Kss Reviewer
KSS reviewer — opus, high effort, read-only. Reviews one finished ticket's diff and report against the project
Notion Publisher
Mirrors a markdown source-of-truth file to Notion as a child page under the right project parent, with consist
Factory Block Implement Medium
Implements one high complexity block inside a factory solve session, given the block task and, after a tests p
Grainulator
Autonomous research sprint subagent. Executes multi-pass research, adds claims, compiles, and generates output
Related Skills
Lwc In Chat
Turn a Figma design into a Lightning Web Component that renders inside an Agentforce chat bubble. Guided walkt
Lectern
Visual drag-and-drop editor for AI-generated slide decks. Ask Claude, ChatGPT or any coding agent for a presen
Stepwarden
Every tool call your agent makes, checked before it runs. A Claude Code plugin that uses TypeSafe AI's Jev to