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.
Decision snapshot
Is this a fit?
Security review, Includes SKILL.md, Reusable instructions
Compatibility not yet detected.
Permission behavior not yet detected.
Copy skill directory
4 months ago · MIT license
No specific cautions were detected. Review the source and requested permissions before installing.
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.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement. See how SkillIndex evaluates profiles.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Security review
- Security review use cases
Declared skill metadata
- Source file: skills/parallax-investigation/SKILL.md
These fields retain source and confidence evidence from the indexed SKILL.md.
Compatibility and setup
- Install or run with Copy skill directory
When to use parallax-investigation Skill
- Use it for security review.
Built with
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
Verified compatibility and discovery
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.
Project health auto-fetched from the source repository.
Maintain this resource?
Review this source-backed profile, send a correction with evidence, or link to it from your documentation. Claims verify your relationship to the project; profile facts still require source evidence and editorial review.
