⚡ SOTA agent skills for OpenClaw — observability, security, code quality, incident response, and more. Built by Anvil AI.
cacheforge-ai/cacheforge-skills
Skill Claude Code
Production-grade agent DevOps toolkit — Docker, process management, log analysis, and health monitoring. Built by engineers who run production.
cacheforge-ai/cacheforge-skills
Skill Claude Code
Context window optimizer — analyze, audit, and optimize your agent's context utilization. Know exactly where your tokens go before they're sent.
cacheforge-ai/cacheforge-skills
Skill Claude Code
OpenClaw continuity kernel for fail-open llminput injection, deterministic runtime contracts, and shadow-mode eval receipts.
cacheforge-ai/cacheforge-skills
Skill Claude CodeCodex
Audit your information diet across HN and RSS feeds — beautiful reports with category breakdowns, ASCII charts, and personalized recommendations.
cacheforge-ai/cacheforge-skills
Skill Claude CodeCodex
Kubernetes Cluster Triage & Diagnostics — instant AI-powered incident triage via kubectl.
cacheforge-ai/cacheforge-skills
Skill Claude CodeCodex
Unified log search across Loki, Elasticsearch, and CloudWatch. Natural language queries translated to LogQL, ES DSL, or CloudWatch filter patterns. Read-only. Never modifies or deletes logs.
cacheforge-ai/cacheforge-skills
Skill Claude CodeCodex
Turn meeting transcripts into operational outputs — action items, decisions, follow-up email drafts, and ticket drafts. Not a summarizer. An operator. Accepts VTT, SRT, or plain text. Multi-pass LLM extraction.
cacheforge-ai/cacheforge-skills
Skill Claude CodeCodex
AI-powered incident triage for PagerDuty. List active incidents, deep-dive with timeline and alert correlation, check on-call schedules, acknowledge, resolve, and annotate — all from your agent. Read-only by default; write operations require explicit --confirm.
cacheforge-ai/cacheforge-skills
Skill Claude CodeCodex
Prometheus Metrics Query & Alert Interpreter — query metrics, interpret timeseries, triage alerts.
cacheforge-ai/cacheforge-skills
Skill Claude CodeCodex
Solana token rug-pull risk analysis. 10-point on-chain check with visual report. Zero API keys. Read-only. Not financial advice.
cacheforge-ai/cacheforge-skills
Skill Claude Code
Swarm reliability watchdog for OpenClaw — validates gateway/channel and every lane, performs bounded recovery, and emits auditable receipts.
cacheforge-ai/cacheforge-skills
Skill Claude CodeCodex
Analyze Terraform plans for risk before you apply. Classifies every change as safe, moderate, dangerous, or critical. Detects destroys, IAM changes, data-loss risks, and blast radius. Entirely read-only — never runs apply.
cacheforge-ai/cacheforge-skills
Skill Claude CodeCodex
Audit code for "vibe coding sins" — patterns that indicate AI-generated code was accepted without proper review. Produces a scored report card with fix suggestions.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: