41 tagged reliability, measured the same way as everything else here.
Browse within: sre 8observability 6
Skill Claude CodeCodex
Guide for job queue patterns in multi-agent coordination. Use when deciding between background jobs vs inline execution, submitting long-running tasks, monitoring job progress, and handling failures. Covers when to queue, job priority, retry strategies, and monitoring patterns.
Skill Claude CodeCodex
Diagnose gateway failures by reading daemon logs, session transcripts, Redis state, and OTEL telemetry. Full Telegram path triage: daemon process → Redis channel → command queue → pi session → model API → Telegram delivery. Use when: 'gateway broken', 'telegram not working', 'why is gateway down', 'gateway not…
Skill Claude CodeCodex
Design recovery mechanisms for a software system or component: select the right rollback control strategy from a three-mechanism decision framework (key rotation, deny list, and minimum acceptable security version number / downgrade prevention), set rate-of-change policy that decouples rollout velocity from rollout…
Skill Claude CodeCodex
Review a system design for security and reliability tradeoffs before implementation begins. Use when: evaluating an architecture proposal or design document and need to identify where security and reliability requirements conflict with feature or cost requirements; auditing a proposed design to determine whether…
Skill Claude CodeCodex
Safety, privacy, cost management, and frank advice for building always-on AI agents with episodic memory. Covers data hygiene, privacy risk surfaces, runaway cost prevention, scope creep, psychological effects of persistent AI companions, and responsible deployment patterns. This is the skill that tells you what can…
Skill Claude CodeCodex
Writes a blameless incident postmortem document from an incident timeline or Slack thread.
Skill Claude CodeCodex
Operate terminal coding agents by voice. Reads and every send go through the local yapitalism MCP server, which returns receipts; the superset MCP server is used for workspaces, projects, and creating agents. Designed for ChatGPT Voice and Remote operation of the Mac Studio Superset instance. Trigger whenever the user…
Skill Claude CodeCodex
Post-edit verification that prevents silent edit failures. After every Write, Edit, or MultiEdit, re-reads files to confirm changes actually saved to disk across all call sites. Assigns a 0-100 trust score per edit. Catches: silent failures (tool reports success but file unchanged), partial application (some call…
Skill Claude CodeCodexCursor
High-precision reliability engineer focusing on failure handling, circuit breakers, retry strategies, and graceful degradation under high-pressure conditions.
Skill Claude CodeCodex
Verified, sourced facts about real-world entities and how they connect — companies, people, investors, funding rounds, M&A, laws, regulations, sanctions, countries and places, industries, products, financial metrics, macro indicators, FX rates. Every value carries a source and date. Use when a task needs to: filter or…
christopherlhammer11-ai/tool-use-guardian
Skill Claude CodeCodex
The Tool Use Guardian ensures reliable tool operations by monitoring and retrying calls, handling errors such as timeouts and rate limits, and learning from past failures. It is crucial for maintaining operation consistency and reliability across various AI functionalities.
Skill Claude CodeCodex
Invariants for the ledger-era fleet — merge never rebase, ownership by authorship, unknown is not broken, verify the artifact.