Coordinate a trace and interview workflow to generate evidence-based specs.
npx skills add https://github.com/atmigtnca/sidep-ops --skill deep-dive-atmigtnca
Please help me install this Agent Skill. Skill: deep-dive Source: https://github.com/atmigtnca/sidep-ops/tree/main/skills/deep-dive Command: npx skills add https://github.com/atmigtnca/sidep-ops --skill deep-dive-atmigtnca
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 to start the trace-interview pipeline and generate a crystallized spec.
High-intent search queries and answers about installing and using this skill.
To crystallize requirements when root causes are unclear, you can run a 2-stage trace and interview pipeline that investigates why something happened and then precisely defines what to do about it.
The best way to investigate root causes before generating a specification is to run 3 parallel causal investigation lanes, then feed those trace findings into a structured interview via a 3-point injection mechanism.
A trace-injected interview workflow improves requirement gathering by using a 3-point injection mechanism to enrich the starting point, provide system context, and seed initial questions with evidence from prior causal investigations.
You need an evidence-based spec over a standard requirement document when applying workflows to complex problems where root causes are unclear and downstream planning and execution skills require a grounded, crystal-clear specification.
Yes, you can hand off a crystallized spec directly to downstream planning and execution skills because the pipeline provides end-to-end orchestration and state persistence with an explicit spec_path for seamless downstream handoff.
kwt00Orchestrate a two-stage pipeline for causal investigation and requirements crystallization.
jmylchreestGenerate technical design specifications with interfaces, data flow, and acceptance criteria.
incidentfoxRun DataPrime queries on Coralogix logs and traces for investigation.
angryconsultantGenerate GitHub issues for unmet requirements extracted from specification files.
