“observability”

Observe and troubleshoot WhatsApp in Kapso: search Logs across API, Meta webhook, workflow, and webhook-delivery events; debug message delivery; inspect…

Make every skill/agent/eval execution observable through a structured, queryable run log so the framework can answer "why did the agent do X, and did it…

Wires Sentry crash reporting behind a port: start on consent, PII scrubbing, releases, source maps per build and update.

Observe and troubleshoot Campfire WhatsApp: message delivery timeline by Meta wamid, partner logs, installation health, webhook/transport failures…

Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram…

Use Langfuse for LLM observability and evaluation and look up Langfuse documentation.

Mac fleet inventory and upkeep with full/worker profiles: collect installed apps and packages, compare desired versus observed state, audit local-account…

Decide which bounded personal observations warrant attention, then return a source-bound private briefing intent and next-check proposal.

Umbrella skill for integrating an agent with Mission Control, the orchestration and observability control plane.

Refine a GitHub issue into a proper engineering spec — a short, clear description plus well-defined acceptance criteria (AC) written as observable, external…

Improve code structure while preserving observable behavior.

Configure, observe, and recover Discord AI jobs from the ADK workspace with Codex, Claude, OpenCode, or Grok.

Read-only observability map of the running agent — live topology, sessions, telemetry, and container health.

Enhanced agentic loop with planning, parallel execution, confidence gates, semantic error recovery, and observable state machine.

Audit installed skills for observed usage, explicit-only invocation controls, duplicate discovery, and global-versus-project scope.

Agent memory system with memory graph, context profiles, checkpoint/recover, structured storage, semantic search, observational memory, task tracking, canvas…

QA a change in the running program, the way its user meets it: drive a CLI or terminal UI through tmux, a web app through a browser, and check every requested…

Maintain and validate the Learn hypothesis ledger (specs/learn/hypotheses.md): add Open hypotheses, list reviews and feature deletions that are due, compute a…

Gates analytics on opt-in consent: no SDK before a yes, typed events without personal data, ATT.

Change or review NewHeap Platform libraries while keeping public APIs, behavior, provider support, executable samples, consumer guidance and distributable…

Answers why code is shaped as it is with an evidence-rated report, tagging each claim [Direct], [Supported], [Inferred], or [Speculative] and closing with a…

Route design work to systems, graphics, prototypes, or critique.

Reviews — and, when asked, sets up — a project's autonomous, scheduled loop — the routine that wakes on a cadence (cron, launchd, a /loop interval, a cloud…

CMO-style autonomous content agent.