← Back to open source9 articles·≈ 27 minutes
HumanLayer Skills: instruction preservation and reviewable control loops
Nine source-backed chapters on conditional guidance, live type contracts, loop design, iteration routing, review capacity and explicit authority.
Latest article
Map the set point, sensor, controller and actuator, then examine where persistent feedback actually enters the documented workflow.
HumanLayer control-loop architecture: measurement, selection, action and feedbackHumanLayer Skillshumanlayer/skills
Start reading →By publication date
01 → 09
01·3 min read·Search intent: Learning
Map the set point, sensor, controller and actuator, then examine where persistent feedback actually enters the documented workflow.
HumanLayer control-loop architecture: measurement, selection, action and feedbackHumanLayer Skillshumanlayer/skills
·3 min read·Search intent: Learning
Decide when instruction cleanup, live-call-site type analysis or a recurring agent loop is appropriate, without treating automation as the default.
Choose HumanLayer skills, deterministic checks or manual review by the taskHumanLayer Skillshumanlayer/skills
·3 min read·Search intent: Learning
Separate installing a skill from implementing a loop, review template assumptions and use GitHub’s actual workflow_dispatch prerequisites.
Deploying a HumanLayer control loop: replace placeholders before enabling CIHumanLayer Skillshumanlayer/skills
·3 min read·Search intent: Learning
Evaluate a proposed CLAUDE.md rewrite using synthetic input, preserved commands and explicit safety constraints before changing future agent guidance.
Try HumanLayer instruction cleanup with a protected-command worksheetHumanLayer Skillshumanlayer/skills
·3 min read·Search intent: Learning
Model review capacity, exact iteration commands and missing policy without creating PRs or granting a learning prototype real write access.
Build a synthetic admission simulator before scheduling a maintenance agentHumanLayer Skillshumanlayer/skills
·3 min read·Search intent: Learning
Understand the five skills, their different modification scopes and why the collection is not a ready-made autonomous maintenance service.
HumanLayer Skills explained: repository guidance and reviewable agent loopsHumanLayer Skillshumanlayer/skills
·3 min read·Search intent: Learning
Measure accepted improvements, open-PR age, retries and human effort before increasing the cadence or batch size of a maintenance agent.
HumanLayer loop throughput: size work to review capacity, not the clockHumanLayer Skillshumanlayer/skills
·3 min read·Search intent: Learning
Review persistent guidance and CI credentials as consequential changes, not harmless text, and preserve task scope through iteration and recovery.
HumanLayer Skills operations: protect instruction files, branch trust and durable memoryHumanLayer Skillshumanlayer/skills
·3 min read·Search intent: Learning
Trace the workflow preflight and Bun prompt helper while distinguishing a routing marker from authentication and commentary from trusted instructions.
Read HumanLayer /iterate routing: role checks, PR markers and raw contextHumanLayer Skillshumanlayer/skills
