multi-reviewer-patterns
wshobson
Parallel code reviews, one prioritized report.
Code review
wshobson
GitHub publisher184 Skills2.3M installs
Person · Seth Hobson · major7apps.com · On GitHub since 2011
- 9.3k
- 9.1k
team-communication-protocols
wshobsonKeep agent teammates coordinated through handoffs.
Agent coordination
- 9.1k
team-composition-patterns
wshobsonRight-sized agent teams for your coding work.
Agent orchestration
- 6.6k
evaluation-methodology
wshobsonUnderstand what your PluginEval score really means.
Quality evaluation
- 6k
hads
wshobsonMake technical docs efficient for people and AI.
Technical documentation
- 6k
block-no-verify-hook
wshobsonKeep commit safeguards from being bypassed.
Commit safeguards
- 5.4k
protect-mcp-setup
wshobsonGive every tool call a policy gate and signed receipt.
Agent governance
- 5.3k
signed-audit-trails-recipe
wshobsonAdd verifiable audit logs to Claude Code.
Agent audit trails
+1 - 4.7k
review-agent-setup
wshobsonPut agent PR actions behind human approval.
Agent governance
- 4.1k
scan
wshobsonKeep your codebase docs in step with its changes.
Project documentation
- 3.7k
recsys-pipeline-architect
wshobsonBuild ranking pipelines with runnable scaffolds.
Recommendation systems
- 3.1k
social-publishing
wshobsonPublish every campaign across your connected channels.
Social media publishing
SO - 2.5k
before-you-build
wshobsonFind the riskiest assumption before you build.
Product strategy
- 2.5k
file-conversion
wshobsonConvert your files without uploading them.
File conversion
- 2.3k
ai-debt-detector
wshobsonCatch hidden debt before AI-written code ships.
Code review
- 2.3k
visual-edit-precision
wshobsonChange the UI you point at, not everything around it.
Frontend development
- 2.3k
session-guard
wshobsonKeep long sessions aligned with your rules.
Agent workflow
- 2.2k
hermes-tweet
wshobsonResearch X/Twitter with approval before account actions.
Social media research
+1 - 2.1k
dataset-curation
wshobsonTurn raw examples into training-ready datasets.
Training data curation
- 2.1k
eval-harness-first
wshobsonKnow what improves before you fine-tune.
Model evaluation
- 2.1k
lora-qlora-recipes
wshobsonGet an adapter configuration ready for training.
Model fine-tuning
- 2.1k
finetuning-method-selection
wshobsonChoose whether to train, and which method fits.
Model fine-tuning
- 2.1k
preference-optimization
wshobsonTurn preference feedback into a concrete training config.
Model fine-tuning
- 2.1k
quantized-export
wshobsonYour promoted model, exported and smoke-tested.
Model deployment