repo-scanner

name	repo_scanner
display_name	Repo Scanner
description	Meta-specialist that auto-discovers and scaffolds new specialists from trending GitHub repos
version	1.0.0
source_repo	jeremylongshore/oss-agent-lab
license	MIT
tier	core
capabilities	["auto_scaffold","repo_analysis","specialist_generation"]
allowed_tools	["scan_repo","scaffold_specialist","evaluate_score"]
output_formats	["python_api","cli","mcp_server","agent_skill","rest_api"]

Repo Scanner Specialist

Overview

A meta-specialist that IS the OSS Agent Lab repository acting on itself. It consumes the Capability Scoring Engine's signal pipeline to evaluate whether a candidate GitHub repo is worth wrapping as a new specialist, then auto-scaffolds the directory skeleton when the score crosses the threshold.

Wraps jeremylongshore/oss-agent-lab.

Capabilities

• auto_scaffold: Materialise a new specialist directory from the _template skeleton when a repo's composite score reaches >= 80.
• repo_analysis: Analyse structural signals (Python presence, tests, README, licence) and infer likely capabilities from repo naming conventions.
• specialist_generation: Orchestrate the full scan → score → scaffold pipeline and surface a unified result with provenance metadata.

Tools

Tool	Description	Side Effects
scan_repo	Structural analysis: name suggestion, detected capabilities, has_python/tests/readme, recommendation	None
evaluate_score	Composite capability score (0-100) with action and signal breakdown	None
scaffold_specialist	Copy _template/ into agents/specialists/<name>/	Creates files on disk

Parameters

All parameters are passed via request.intent.parameters:

Parameter	Type	Default	Description
repo	str	(query text)	GitHub repo in owner/name format
name	str	(from scan)	Override for the scaffolded specialist directory name

Usage

Python API

from agents.specialists.repo_scanner.agent import RepoScannerSpecialist
 oss_agent_lab.contracts  Intent, Query, SpecialistRequest

specialist = RepoScannerSpecialist()

request = SpecialistRequest(
    intent=Intent(
        action=,
        domain=,
        confidence=,
        parameters={: },
    ),
    query=Query(user_input=),
    specialist_name=,
)

response =  specialist.execute(request)
(response.result[][])   
(response.result.get())