Repo Profiler — Testing & QA agent for Claude Code
Analyzes the last 10-20 merged PRs of a target repo to extract contribution conventions (commit format, PR body structure, test runner, lint commands, reviewer norms).
How to install Repo Profiler
Installs to ~/.claude/agents/gaurav0107-superhuman-repo-profiler.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/gaurav0107/superhuman/HEAD/agents/repo-profiler.md -o ~/.claude/agents/gaurav0107-superhuman-repo-profiler.md Restart Claude Code, or start a new session, for it to be picked up.
What Repo Profiler does
name: repo-profiler description: Analyzes the last 10-20 merged PRs of a target repo to extract contribution conventions (commit format, PR body structure, test runner, lint commands, reviewer norms). Parses .github/workflows/*.yml to classify CI commands into a safe allowlist. Writes repo_profile.json, ci_commands.json, and seeds allowed_commands.json. tools: ["Read", "Write", "Bash", "Grep", "Glob"] model: opus
You profile a target open-source repository so other agents can contribute
Alternatives in Testing & QA
- Distill — Extract an Allium specification from an existing codebase 474 ★
- Review Test Structure — Reviews test code for isolation, independence, readability, documentation quality, and proper setup/teardown 432 ★
- Checklist Generator — Use when an orchestrator needs to enumerate every verifiable claim in a code diff (dependency interactions, te 115 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Sequant Testgen
Test stub generator for sequant /testgen phase. Parses verification criteria from /spec comments and generates
Bank Extract
Structuring stage of bank onboarding. Reads the ingested raw sources (resumes, notes) listed in the bank's .in
Cleanup Phase 4 Impl
Executes phase 4 of a codebase cleanup — the tier A reshaping operations the survey cleared, plus the one tier
Flutter Pro
Implements or refactors Flutter/Dart against the repo's conventions, verifying with its codegen/format/analyze
Karr Worker
Default App::karr worker — implement, refactor, debug, and test code in this distribution. Pre-loaded with kar
Deep Reviewer
Use this agent when performing the AI Deep Review stage (Stage 5) of the contribution test phase. This agent a
Related Skills
OSS
Orchestrate an OSS-contribution task — find issues, research status, draft questions/feedback/new issues, lear
Researcher Writing Profiler
A Claude Code skill that analyzes a researcher's publication record and writing style from Google Scholar, pro
OSS Autopilot
Open source contribution manager — tracks PRs across repos, discovers issues, diagnoses CI failures, drafts ma