Favicon of parallax-investigation

parallax-investigation Skill

AI Agent SkillPythonOpen source

Use when you need true understanding of a complex system — not a quick answer. Parallax Discovery is a multi-agent, multi-pass investigation methodology that combines three perspectives (code tracing, behavior observation, integration mapping) to produce verified, evidence-backed findings. Published by microsoft in amplifier-bundle-dot-graph.

What is parallax-investigation Skill?

Use when you need true understanding of a complex system — not a quick answer. Parallax Discovery is a multi-agent, multi-pass investigation methodology that combines three perspectives (code tracing, behavior observation, integration mapping) to produce verified, evidence-backed findings. Published by microsoft in amplifier-bundle-dot-graph. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.

Trust signal
95/100
Maintenance signal
90/100
Adoption signal
11/100

Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.

Key capabilities

  • Includes SKILL.md support
  • Reusable instructions support
  • Security review
  • Security review use cases

Technical details

Copy skill directory
  • Install or run with Copy skill directory

When to use parallax-investigation Skill

  • Use it for security review.

Built with

PythonCopy skill directory

Editorial notes

Source

  • Creator: microsoft
  • Repository: microsoft/amplifier-bundle-dot-graph
  • Skill file: skills/parallax-investigation/SKILL.md

What it does

Use when you need true understanding of a complex system — not a quick answer. Parallax Discovery is a multi-agent, multi-pass investigation methodology that combines three perspectives (code tracing, behavior observation, integration mapping) to produce verified, evidence-backed findings.

Skill instructions

Parallax Discovery Methodology Overview Parallax Discovery is a multi-agent, multi-pass investigation methodology named after astronomical parallax — just as astronomers triangulate depth by observing stars from multiple positions, this methodology triangulates truth by examining code from multiple perspectives. Use Parallax Discovery when you need true understanding, not a quick answer: - Unfamiliar or complex codebases - Debugging subtle, intermittent, or cross-cutting issues - Architecture review before major refactoring - Onboarding investigation to map system structure - Security audits requiring evidence-backed findings A single agent reading code produces a single perspective. Parallax produces three, then reconciles them. --- The Three-Perspective Model Each perspective is a distinct agent role. Together they form a triplicate team. All agents in a team run with fresh context (contextdepth='none') — this is non-negotiable. Prior session state contaminates findings. Agent 1: Cod

Explore related resources

Frequently asked questions

What is parallax-investigation?

parallax-investigation is a open-source AI agent skill with Copy skill directory. Use when you need true understanding of a complex system — not a quick answer.

Who is parallax-investigation best for?

parallax-investigation is best for reusing agent instructions, scripts, and references, security review workflows.

How do I install parallax-investigation?

Install or run parallax-investigation using Copy skill directory. Check parallax-investigation for the latest setup command.

Is parallax-investigation actively maintained?

parallax-investigation may need a closer maintenance check before production use.

Share:

Stars
2
Forks
4
Last commit
2 months ago
Repository age
4 months
License
MIT

Auto-fetched from GitHub.

Ad
Favicon

 

  
 

Similar to parallax-investigation