01 · Roasts
The 40-Minute Founder
jammed-claw: 3 commits in 40 minutes, 3 stars, done. pocketcode: created in literally 2 seconds of git history. You're not shipping — you're time-trialing.
91% Python, 0% Tests
Python is 91% of your codebase but your ML/AI repos have zero test coverage across the board. 'AI training arc' apparently doesn't include training yourself to write tests.
The Cheese Profile
Your profile README says 'I love cheese.' That's it. That's the whole README. 4KB. No code. This is your public face to the world and you went with dairy enthusiasm.
Hackathon Graveyard
haist (5 weeks old, 2/30 commit days), clod-voice (5 weeks, 3/30 days), diff-review (lifespan: 36 minutes) — you sprint hard and ghost harder. CI would at least leave a paper trail.
20 PRs, 0 Issues
You opened 20 PRs this year but filed exactly zero issues. Either every codebase you touch is perfect, or you're too polite to complain. Neither is a great look for an engineer.
Built using
Zoral
Shadows one worker for a week, then takes over their job with zero extra setup. Behaves exactly like the original.
zoral.ai
02 · Category breakdown
- Impact25% weight48D
- Consistency20% weight35F
- Quality20% weight57D
- Depth15% weight35F
- Breadth10% weight55D
- Community10% weight40D
03 · Stats
365-day commit heatmap
166 active days
Language distribution
- Python91%
- TypeScript6%
- Jupyter Notebook1%
- C++1%
- Swift1%
- JavaScript1%
04 · Numbers
Owned repos
non-fork
24
Commits
last 12 months
167
Followers
16
Joined GitHub
Jan 2024
05 · Top repos
KNQuoc /
jammed-claw
TypeScript workflow automation library integrating jam-nodes with OpenClaw for AI-driven task orchestration. Early-stage project with typed code, tests, and solid architecture but nascent adoption (3 stars, 3 commits in 40 minutes).
KNQuoc /
clod-voice
Early-stage TypeScript Discord voice bot integrating OpenAI Realtime API with Claude tools. Functional but experimental with 41KB codebase, no tests/CI, minimal commit history over ~5 weeks.
KNQuoc /
haist
TypeScript workflow editor with monorepo structure, React Flow canvas, AI assistant integration, and Composio tool support. No README, no tests/CI, but 824KB codebase with structured types and documentation in source files shows meaningful scope.
KNQuoc /
tool-discovery
Early-stage tool for extracting API endpoints from docs (OpenAPI, MCP, HTML) using AI. Has a working CLI (discover.mjs, pipeline.mjs) with structured extraction logic, but unpolished and incomplete implementation with hardcoded configs and partial code.
KNQuoc /
jam-nodes-docs-mcp
Brand-new MCP server integrating jam-nodes documentation into AI agents via typed TypeScript, with 5 documented tools and bundled guides, but zero commits depth and minimal adoption footprint.
KNQuoc /
pocketcode
Brand-new TypeScript monorepo (38kb, created 2 days ago) providing a PWA dashboard for controlling AI coding agents. Typed, documented, and structured (cli/server/web/shared packages) but single commit push with no adoption or test coverage yet.
KNQuoc /
diff-review
Single-day experimental OpenClaw skill for Discord-based diff review with minimal code, no tests, no CI, no license, and no type safety. Shows promise in concept but lacks production polish.
KNQuoc /
KNQuoc
Minimal experimental repo with placeholder README ("I love cheese"), 4KB total, no code files, no tests/CI/license. Created recently with sparse commits.
06 · Timeline
- Jan 10, 2024Joined GitHub
- Jul 3, 2025Created KNQuoc
- Feb 9, 2026Created clod-voice — Discord voice bot — OpenAI Realtime API with Claude/OpenClaw integration
- Feb 15, 2026Created jam-nodes-docs-mcp — MCP server for jam-nodes documentation
- Feb 19, 2026Created jammed-claw — Visual workflow automation for OpenClaw — powered by jam-nodes
- Feb 21, 2026Created haist — haist
- Feb 23, 2026Created diff-review — OpenClaw skill for interactive code diff review in Discord with reaction-based pagination
- Feb 23, 2026Created pocketcode — Control your AI coding agents from anywhere. Open source alternative to Omnara.
- Feb 24, 2026Created tool-discovery — Extract API tools/endpoints from any docs URL — OpenAPI, MCP, or HTML docs
- Mar 28, 2026Most recent push to haist
07 · Compare
08 · Rubric
How this score was produced
Overall = Σ (category × weight) + gentle top-end curve
Tier thresholds
▸ How the pipeline works
- 01Scrape.Pull every non-fork repo pushed in the last 90 days, plus your contribution calendar, followers, and language byte counts — straight from GitHub's REST & GraphQL APIs.
- 02Triage.A small model reads every repo's file tree + README and picks the 20 files per repo that actually reveal how you code.
- 03Grade each repo. All repos run in parallel through a fast scoring model that reads the picked files and rates each one independently on Impact, Quality, and Depth — with evidence citations.
- 04Aggregate. A larger reasoning model combines the per-repo scores with server-computed stats (heatmap, commit cadence, language entropy, follower count) to produce the 6-dimension profile score + roasts.
- 05Correct.Deterministic server-side checks enforce anchor-scale floors (e.g. a profile with 2,000+ public commits can't score 30 Consistency) and recompute the final verdict.
~90 seconds per profile, ~$0.25 in compute. Total of ~240 files read across your top-12 repos. One rating per GitHub account per day.
▸ Data sources & caveats
- Heatmap & commit totals: GitHub GraphQL
contributionsCollection— covers the last 365 days, includes private repos when the user has opted in (default). - Language %: byte totals across the top 30 owned non-fork repos.
- Curve: a small upward nudge centered on raw score ≈ 70, capping at 100. Prevents specialists from being unfairly penalised for narrow breadth.
- Anchor corrections: when server-measured signals (e.g. privateWorkLikely, multiRepoVolume, follower count) mandate a minimum category score, the aggregation step enforces it. These are signal-conditional, not identity-based floors.