Agent-Skills.md

Agent Skills: Deep Research

Extended investigation for technology evaluation, competitive analysis, architectural exploration, and best practices research. Unlike spike (time-boxed hours), deep-research supports multi-day comprehensive investigation producing reports for major decisions. Triggers on "research X solutions", "compare frameworks for our use case", "evaluate vendors for X", "what are best practices for Y", "how do competitors handle Z", or any investigation requiring comprehensive analysis across multiple sources.

UncategorizedID: srstomp/pokayokay/deep-research

Repository

srstomp/pokayokay
srstomp
2

Install this agent skill to your local

pnpm dlx add-skill https://github.com/srstomp/pokayokay/tree/HEAD/plugins/pokayokay/skills/deep-research

Skill Files

Browse the full folder contents for deep-research.

Download Skill

Loading file tree…

plugins/pokayokay/skills/deep-research/SKILL.md

Skill Metadata

Name
deep-research
Description
Use for multi-day technology evaluations, competitive analysis, architectural exploration, best practices research, or major strategic decisions requiring comprehensive investigation and stakeholder reports. Unlike spike (time-boxed hours), supports extended multi-day investigation.

Deep Research

Comprehensive investigation that informs major decisions. Produces structured reports for stakeholders.

Deep Research vs Spike

| | Spike | Deep Research | |-|-------|---------------| | Duration | Hours | Days | | Scope | Single question | Multiple questions | | Output | GO/NO-GO decision | Comprehensive report | | Depth | Proof of concept | Full evaluation |

When NOT to Use

  • Single focused question answerable in hours — Use spike for quick GO/NO-GO decisions
  • Reviewing existing code/architecture — Use architecture-review for structural analysis of what's already built
  • Known technology, just need implementation guidance — Read docs or use relevant skill directly

Key Principles

  • Define research questions and success criteria upfront
  • Evaluate multiple options against consistent criteria
  • Synthesize findings into actionable recommendations
  • Track progress through ohno for multi-session continuity

Quick Start Checklist

  1. Define research questions (what decisions need data?)
  2. Set evaluation criteria (what matters for comparison?)
  3. Gather sources (docs, benchmarks, case studies, experiments)
  4. Compare options against criteria systematically
  5. Synthesize findings and form recommendations
  6. Present report with clear decision guidance

References

| Reference | Description | |-----------|-------------| | research-types.md | Technology evaluation, competitive analysis, best practices | | source-quality.md | Evaluating source reliability and relevance | | synthesis-patterns.md | Comparison matrices, decision frameworks | | research-report-template.md | Template for comprehensive research reports | | comparison-matrix-template.md | Template for multi-option comparison scoring |