@firstpick/pi-skill-research-orchestration

Agents should invoke this skill for broad multi-claim research projects needing planning, parallel investigation, source merging, gap closure, citation audit, and final synthesis when narrower research skills are insufficient.

Packages

Package details

skill

Install @firstpick/pi-skill-research-orchestration from npm and Pi will load the resources declared by the package manifest.

npm report
$ pi install npm:@firstpick/pi-skill-research-orchestration
Package
@firstpick/pi-skill-research-orchestration
Version
0.1.2
Published
May 18, 2026
Downloads
not available
Author
firstpick
License
MIT
Types
skill
Size
30.6 KB
Dependencies
0 dependencies · 0 peers
Pi manifest JSON
{
  "skills": [
    "./skills"
  ]
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

@firstpick/pi-skill-research-orchestration

A Pi skill for broad multi-claim research projects needing planning, parallel investigation, source merging, gap closure, citation audit, and final synthesis when narrower research skills are insufficient.

What it does

  • Adds the research-orchestration skill to Pi's skill library.
  • Guides agents to invoke the skill for broad multi-claim research projects needing planning, parallel investigation, source merging, gap closure, citation audit, and final synthesis when narrower research skills are insufficient.
  • Bundles skills/research-orchestration/SKILL.md plus any supporting references, scripts, tests, fixtures, or assets used by the skill.

Install

pi install npm:@firstpick/pi-skill-research-orchestration

Configuration

No required configuration.

Bundled helper scripts

This package ships the research-orchestration skill plus its scout helper scripts:

skills/research-orchestration/
  SKILL.md
  scripts/
    README.md
    policy.json
    scout_query_plan.py
    scout_normalize_sources.py
    scout_evidence_bundle.py
    scout_citation_audit.py
    _lib/
      normalize.py

Run helpers from skills/research-orchestration/ or use absolute paths. By default, scripts read ./scripts/policy.json; pass --policy /path/to/policy.json to override.

Examples:

python3 ./scripts/scout_query_plan.py --topic "local-first AI notes" --task-class standard -o query-plan.json
python3 ./scripts/scout_normalize_sources.py --input sources.json -o normalized-sources.json
python3 ./scripts/scout_evidence_bundle.py --input fetch-records.jsonl -o evidence_bundle.json
python3 ./scripts/scout_citation_audit.py --report final-report.json

Commands

None.

Tools

None.

Example view

User: Review this change for the concerns covered by `research-orchestration`.
Agent: Invokes the `research-orchestration` skill, follows its workflow, and reports the result.