agentic-review
Use when reviewing current branch for bugs before pushing or merging, when wanting a thorough multi-agent review of local changes, or when preparing work for human review
Use when reviewing current branch for bugs before pushing or merging, when wanting a thorough multi-agent review of local changes, or when preparing work for human review
Investigate homelab infrastructure health using VictoriaMetrics and VictoriaLogs. Use for node health, pod issues, storage, network, and security investigation.
Record field scouting observations, track pest and disease pressure, and manage spray application records. Use when asked to log a new pest sighting, check which fields have high pressure, find all codling moth observations, view spray history for a field, or check if a pre-harvest interval has cleared. Triggers include "log observation", "scouting report", "pest pressure", "disease found", "field scouting", "spray record", "PHI", "pre-harvest interval", "observation history", "high pressure fields", or any task involving pest or disease tracking.
Record soil test results, track nutrient levels over time, and log soil amendments. Use when asked to add a soil test, check which nutrients are deficient, view field nutrient history, record a lime or fertilizer application, or compare field health across tests. Triggers include "soil test", "soil pH", "nutrient deficiency", "add lime", "compost application", "phosphorus low", "organic matter", "amendment record", or any task involving soil chemistry tracking.
Use when creating, editing, validating, or enforcing glossary-driven terminology.
Configure camera, LIDAR, IMU, and contact sensors on simulated robots in Gazebo
Verify artifact quality by running coherence lenses (logical consistency) and factual verification tracks (external accuracy). Designed to be loaded by a freshly spawned subagent or nested Claude instance that reads the artifact cold. Produces a findings file — does not fix issues. Use when: after completing a research report, after spec scope freeze, on-demand quality check, verify claims, fact-check, review accuracy, cross-check assertions, post-completion verification for any artifact with evidence-backed claims.
Instrument web applications to send telemetry data to Azure Application Insights for observability and monitoring. USE FOR: instrument app with app insights, add appinsights instrumentation, configure application insights, set up telemetry monitoring, enable app insights auto-instrumentation, add observability to azure web app, instrument webapp to send data to app insights, configure telemetry for app service. DO NOT USE FOR: non-Azure monitoring (use CloudWatch for AWS, Datadog for third-party), log analysis (use azure-kusto), cost monitoring (use azure-cost-optimization), security monitoring (use azure-security).
Validate a research idea BEFORE implementation. Tests core assumptions with minimal experiments. Kills bad ideas in hours, not weeks. MANDATORY before any implementation work begins.
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
Use when a task mentions IPG, CarMaker, IPGControl, Movie NX, Instrument Designer, or IPGGraph and you need to route the question to the right product, manual, example set, or companion tool.
Personal device and appliance manager with error code lookup and troubleshooting. Tracks all your devices (appliances, electronics, software) with model numbers, manuals, and warranty info. When something breaks, tell it the error code and get instant solutions. Use when: device shows error, need manual, warranty check, adding new device, maintenance reminder. Triggers: /device, /geräte, 'mein Geschirrspüler', 'Fehler E24', 'Fehlermeldung', device problems, appliance issues.
Track elapsed time from a set epoch with tamper-evident locking. Like an analog Hobbs meter but digital. Use for tracking uptime, service hours, time since events, sobriety counters, project duration, equipment runtime. Supports create, lock (seal), check, verify against external hash, list, and export operations.
Monitor and control Snapmaker 3D printers (U1 with Moonraker/Klipper). Use when checking print status, temperatures, progress, or controlling prints (pause/resume/cancel). Triggers on "printer", "3D print", "Snapmaker", "print status", "nozzle temp", "bed temp".
Retest remediated findings, detect regressions, and generate remediation status and certification artifacts.
Conflict detection and error monitoring for AI agents. The 'something's off' detector. Part of the AI Brain series.
A product photo of running shoes on white marble in a minimalist studio, shot with natural lighting and shallow depth of field.
Operate and troubleshoot BambuLab printers with the bambu-cli (status/watch, print start/pause/resume/stop, files, camera, gcode, AMS, calibration, motion, fans, light, config, doctor). Use when a user asks to control or monitor a BambuLab printer, set up profiles or access codes, or translate a task into safe bambu-cli commands with correct flags, output format, and confirmations.