team-ultra-analyze
Deep collaborative analysis pipeline. Multi-perspective exploration, deep analysis, user-driven discussion loops, and cross-perspective synthesis. Supports Quick, Standard, and Deep pipeline modes.
Profile →npx skills add majiayu000/claude-skill-registry --skill team-ultra-analyze-catlog22-claude-code-workflow --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Coordinates a deep collaborative analysis pipeline that runs multiple perspectives in parallel, with user-driven discussion loops and cross-perspective synthesis. Supports Quick, Standard, and Deep pipeline modes.
How it works
- Uses a topic-driven pre-wave phase to determine pipeline mode, perspectives, and dimensions (Phase 0: Pre-Wave Interactive).
- Phase 1 builds tasks.csv and classifies tasks as csv-wave or interactive, based on the chosen pipeline mode and perspectives.
- For each wave, spawns agents to perform exploration and analysis in parallel via wave-specific CSV inputs, then merges results into the master tasks.csv.
- Phase 3 enables a post-discussion interactive loop driven by user feedback, potentially creating dynamic DISCUSS-N and ANALYZE-fix-N tasks.
- Phase 4 aggregates results into results.csv and context.md, providing a complete execution report.
When to use it
Use when you need multi-perspective, collaborative analysis with structured wave-pipeline execution and optional user-driven discussion loops. Choose mode quick, standard, or deep to control depth and rounds.
What it can touch
- spawn_agents_on_csv
- spawn_agent
- wait
- send_input
- close_agent
- Read
- Write
- Edit
- Bash
- Glob
- Grep
- AskUserQuestion
Caveats
- Output directories and filenames follow the specified workflow layout (e.g.,
.workflow/.csv-wave/{session-id}/,tasks.csv,results.csv,discoveries.ndjson,context.md). - User interaction gates exist after discussion rounds; some paths create dynamic tasks (e.g., DISCUSS-N, ANALYZE-fix-N).
- Requires explicit mode and concurrency handling as per flags; auto mode skips interactive validation.
## Auto Mode When `--yes` or `-y`: Auto-confirm task decomposition, skip interactive validation, use defaults. # Team Ultra Analyze ## Usage ```bash $team-ultra-analyze "Analyze authentication module architecture and security" $team-ultra-analyze -c 4 --mode deep "Deep analysis of payment processing pipeline" $team-ultra-analyze -y --mode quick "Quick overview of API endpoint structure" $team-ultra-analyze --continue "uan-auth-analysis-20260308" ``` **Flags**: - `-y, --yes`: Skip all confirmations (auto mode) - `-c, --concurrency N`: Max concurrent agents within each wave (default: 3) - `--mode`: Pipeline mode override (quick|standard|deep) - `--continue`: Resume existing session **Output Directory**: `.workflow/.csv-wave/{session-id}/` **Core Output**: `tasks.csv` (master state) + `results.csv` (final) + `discoveries.ndjson` (shared exploration) + `context.md` (human-readable report) --- ## Overview Deep collaborative analysis with multi-perspective exploration, deep analysis, user-driven discussion loops, and cross-perspective synthesis. Each perspective gets its own explorer and analyst, working in parallel. Discussion rounds allow the user to steer analysis depth and direction.
- Auto Mode
- Usage
- Overview
- Task Classification Rules
- CSV Schema
- tasks.csv (Master State)
- Per-Wave CSV (Temporary)
- Agent Registry (Interactive Agents)
- Output Artifacts
- Session Structure
- Implementation
- Session Initialization
- Phase 0: Pre-Wave Interactive
- Phase 1: Requirement → CSV + Classification
What does the team-ultra-analyze skill do?
Deep collaborative analysis pipeline. Multi-perspective exploration, deep analysis, user-driven discussion loops, and cross-perspective synthesis. Supports Quick, Standard, and Deep pipeline modes.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill team-ultra-analyze-catlog22-claude-code-workflow --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.