Curated knowledge repository — reusable methods, patterns, and techniques contributed by the community
The curated knowledge repository for StatsClaw. This repo contains validated, privacy-scrubbed knowledge entries contributed by the StatsClaw community.
When StatsClaw users opt into Brain mode, their agents can read knowledge entries from this repo to enhance their capabilities — better math formulations, coding patterns, validation strategies, simulation designs, and more. Every entry here has been:
- Extracted from a real workflow by the distiller agent
- Privacy-scrubbed (no repo names, file paths, usernames, or proprietary code)
- Approved by the contributing user
- Reviewed and curated by admin
StatsClaw agents read from this repo automatically when Brain mode is enabled. You can also browse entries directly:
planner/— Mathematical methods, statistical techniques, spec patternsbuilder/— Language-specific coding patterns, numerical stability, API designtester/— Validation strategies, tolerance calibration, benchmark patternssimulator/— DGP patterns, harness designs, convergence diagnosticsscriber/— Architecture patterns, documentation stylesreviewer/— Convergence failure patterns, quality checksgeneral/— Cross-agent knowledge, language guides, debugging patterns
See index.md for a searchable index of all entries.
Do NOT create PRs directly to this repo. Contributions flow through statsclaw/brain-seedbank:
Automatic — Use StatsClaw with Brain mode enabled. After noteworthy workflows, the distiller agent extracts knowledge automatically.
Manual — Run the /contribute command at any time during a session. It summarizes what you learned — what worked, what required manual intervention, and what domain-specific patterns emerged — and submits a structured report.
Either way:
- The distiller agent extracts reusable knowledge
- You review and approve the extracted entries — nothing is shared without your explicit consent
- Your contribution is submitted as a PR to
statsclaw/brain-seedbank - Admin reviews, then transfers accepted entries here
See CONTRIBUTING.md for quality standards.
See CONTRIBUTORS.md for the badge leaderboard.
If you use StatsClaw or benefit from the shared brain in your research, please cite:
Qin, Tianzhu and Yiqing Xu. 2026. "StatsClaw: An AI-Collaborative Workflow for Statistical Software Development."
@misc{qinxu2026statsclaw,
title={StatsClaw: An AI-Collaborative Workflow for Statistical Software Development},
author={Qin, Tianzhu and Xu, Yiqing},
year={2026},
howpublished = {Mimeo, Stanford University},
url={https://bit.ly/statsclaw}
}Knowledge entries are shared under CC BY 4.0. The StatsClaw framework itself is released under the MIT License.