Orchestrate trace and interview phases to identify root causes and generate specifications.
npx skills add https://github.com/Pryma-Tech/iris --skill deep-dive-pryma-tech
Please help me install this Agent Skill. Skill: deep-dive Source: https://github.com/Pryma-Tech/iris/tree/main/cli/skills/deep-dive Command: npx skills add https://github.com/Pryma-Tech/iris --skill deep-dive-pryma-tech
Deep Dive orchestrates a 2-stage pipeline that first investigates WHY something happened (trace) then precisely defines WHAT to do about it (deep-interview). The trace stage runs 3 parallel causal investigation lanes, and its findings feed into the interview stage via a 3-point injection mechanism — enriching the starting point, providing system context, and seeding initial questions. The result is a crystal-clear spec grounded in evidence, not assumptions.
Invoke /deep-dive with your problem statement to start a five-phase investigation and spec crystallization flow.
High-intent search queries and answers about installing and using this skill.
To crystallize software requirements, you orchestrate a structured investigation that traces root causes across parallel causal lanes, then injects those findings into a deep-interview phase to produce evidence-based formal specifications.
The best way to investigate root causes is running a 2-stage pipeline with parallel trace lanes to find why something happened, then using a 3-point injection to feed that context into a deep-interview for precise specification generation.
To start a deep-dive investigation, you invoke the command with your problem statement to initialize a five-phase flow that handles lane confirmation, autonomous tracing, trace-to-interview injection, and spec generation.
Yes, autonomous tracing applies to greenfield projects needing structured investigation by running parallel causal lanes to gather evidence, which then seeds targeted questions for the downstream interview phase.
Trace-to-interview injection works by transferring trace findings into interview initialization through a 3-point mechanism, enriching the starting point, providing system context, and seeding initial questions to reduce context switching.
When a root cause trace returns low confidence results, the investigation pipeline provides graceful handling and fallback options to ensure the downstream deep-interview still receives viable context for spec generation.
officechbusinessservices-creatorCoordinate competing hypotheses with evidence collection and ranked synthesis.
withkynamCreate and validate 9-field provisional goal blocks for Autopilot sessions.
INNERJOINTTrace causal observations to rank competing explanations for system behavior.
dropsyoonTrace root causes across three parallel lanes and crystallize evidence-grounded requirements.
