observability-instrumentation
Instrument agents with structured traces, events, metrics, and execution-phase diagnostics for production debugging.
Instrument agents with structured traces, events, metrics, and execution-phase diagnostics for production debugging.
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 PR/MR already exists and needs to be driven to merge — monitors CI/CD, handles multi-round code review, responds to and resolves reviewer comments, and loops until all merge requirements are met.
Moves an object to one of two destination containers based on a numeric threshold check. Trigger after a measurement (e.g., temperature) is taken. Place object in 'green' box if value > threshold, or 'blue' box if value < threshold.
Audit logging for compliance and security. Structured audit events, immutable logs, user action tracking, database change tracking, and regulatory compliance (SOC2, HIPAA, GDPR). USE WHEN: user mentions "audit log", "audit trail", "activity log", "change tracking", "compliance logging", "who changed what", "SOC2 logging" DO NOT USE FOR: application logging - use logging skills; error tracking - use observability skills
ISA-5.1 tag naming, ISA-88 batch control, ISA-95 enterprise integration, ISA-18.2 alarm management, and ISA-101 HMI standards reference. Use when working with instrument tags, naming conventions, or plant hierarchy.
Extracts learnings from completed work, feedback, or failures. Updates a persistent learnings file with capped entries. Use after receiving feedback, fixing bugs, or completing complex tasks.
Lameness grading (AAHA scale), joint assessment (drawer sign/tibial thrust for CCL, Ortolani for hip dysplasia), patellar luxation grading I-IV, OFA scoring, breed predispositions, common conditions by species.
Schirmer tear test values and interpretation, fluorescein staining, tonometry with normal IOP ranges, common conditions by species (KCS, glaucoma, cataracts, ulcers, entropion, cherry eye), breed predispositions.
Veterinary cardiac examination and diagnostic workup including murmur grading (I-VI), arrhythmia classification, echocardiography indications, and ACVIM staging for MMVD and DCM.
Species-specific interpretation of veterinary laboratory results including CBC, chemistry, urinalysis, and endocrine panels. Reference ranges differ dramatically by species. Use when interpreting bloodwork for animals.
OpenTelemetry best practices for manual instrumentation. Use when adding, changing, or reviewing OpenTelemetry instrumentation in code. Guidance to choose runtime boundaries, choose signals, apply semantic conventions, handle propagation, control cardinality, and verify the result.
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
Acquire and analyze mobile device data using Cellebrite UFED and open-source tools to extract communications, location data, and application artifacts.
Inspect and edit Jupyter notebook (.ipynb) listing, reading, updating, deleting, and inserting cells. Use whenever an agent must analyze or modify notebook cell content (e.g., reviewing markdown, tweaking code) with precise, per-cell control.
Synchronizes issue and PR labels (kind, priority, status, changes) using repo rules and observes CI-managed size labels; use when triaging, implementing, or preparing review.
Deep competitive intelligence combining web scraping, LinkedIn data, social media monitoring, leadership analysis, GitHub activity, Glassdoor sentiment, and community insights. Analyzes founders/C-level profiles, tracks real-time signals vs quarterly reports, and creates comprehensive competitor profiles. Use when asked to analyze competitors, research leadership teams, investigate market positioning, compare products/pricing, assess strategic threats, or gather intelligence on founders and key executives.
Deep analytical investigation mode using Bayesian reasoning, superforecasting techniques, and rigorous hypothesis testing. Combines methods from Kahneman, Tetlock, Peirce, and Feynman. Use when user invokes /investigate or asks for thorough analysis.
Computational mathematics expert for numerical solutions, approximations, error analysis, and scientific computing
Detect anomalies and outliers in datasets using statistical and ML methods. Use for data cleaning, fraud detection, or quality control analysis.