daaf-orchestrator
Operational framework for the DAAF orchestrator. Defines engagement modes, confirmation protocol, subagent dispatch, context budget, and reference-loading. Loaded exclusively by the orchestrator — not for subagents or user questions.
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill daaf-orchestrator --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
Operational framework for the DAAF orchestrator agent. Defines the eight engagement modes and their confirmation protocol, subagent dispatch patterns, context budget rules, communication standards, and progressive reference-loading decision tree. Loaded exclusively by the orchestrator agent to govern its own execution — not a general-purpose orchestration reference and should not be loaded by subagents or in response to user questions about pipeline coordination.
How it works
- Establishes Identity & Mission for an Analytical Research Orchestrator powering the Data Analyst Augmentation Framework (DAAF).
- Sets execution philosophy, code style, safety boundaries, and project conventions to be followed universally by the orchestrator and subagents.
- When writing code directly as the orchestrator, requires reading the mandatory file-first execution protocol described in agent_reference/SCRIPT_EXECUTION_REFERENCE.md.
- Provides Tone & Voice guidelines for user-facing communication and a Welcome Preamble with onboarding and escalation behavior.
- Details Eight engagement modes and a Mode Decision Framework to route requests into Data Onboarding, Data Lookup, Data Discovery, Ad Hoc Collaboration, Full Pipeline, Revision and Extension, Reproducibility Verification, or Framework Development. Each mode has corresponding trigger logic and outputs.
- Introduces a Mode Confirmation Gate (HARD GATE) that mandates explicit user approval before any mode execution, including a structured confirmation message with reasoning, what to expect, deliverables, and a closing confirmation question.
- Defines mode-specific escalation paths and a set of example confirmation templates for each mode.
When to use it
Use this framework whenever coordinating DAAF-driven analyses or framework modifications. It applies to orchestrator-level decision-making and governs how modes are selected, confirmed, and executed. It is not intended for subagents or user questions about pipeline coordination.
What it can touch
- Tools: claude-code
Caveats
- License: NOASSERTION
- This framework is designed to govern orchestrator execution and not to be loaded by subagents or in response to user questions about pipeline coordination.
- All mode activations require explicit user confirmation per the Mode Confirmation Gate before proceeding.
# DAAF Orchestrator Framework Operational framework for the DAAF orchestrator agent. Defines the eight engagement modes and their confirmation protocol, subagent dispatch patterns, context budget rules, communication standards, and progressive reference-loading decision tree. Loaded exclusively by the orchestrator agent to govern its own execution — not a general-purpose orchestration reference an
What does the daaf-orchestrator skill do?
Operational framework for the DAAF orchestrator. Defines engagement modes, confirmation protocol, subagent dispatch, context budget, and reference-loading. Loaded exclusively by the orchestrator — not for subagents or user questions.
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill daaf-orchestrator --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 brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 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.