Agent skills for Claude Desktop

Manage Telegram channel access — approve pairings, edit allowlists, set DM/group policy.

Use Miðeind's Málfríður API to fix or check Icelandic grammar.

Configuring or debugging Malga webhooks (v1.1).

Use when analyzing suspected malware through static, dynamic, and behavioral techniques, including IOC extraction, YARA or Sigma rules…

Interact with Mamo DeFi yield strategies on Base (Moonwell).

Push/pull Copilot Studio agent content via the VS Code extension's LanguageServerHost LSP binary.

Finds oversized files, binary bloat, and accidental artifact commits in a repo — large files currently tracked, large blobs hiding in git…

Find, review, and update customers in a Clara account through Clara's authenticated MCP.

Operate a Kube-DC Managed Cluster: download its external kubeconfig, scale or autoscale worker pools, perform supported upgrades, and…

Cross-cutting reference manager for medical manuscripts.

Coordinate implementation waves through separate OpenCode TUI workers in isolated git worktrees and cmux workspaces.

Assembles, structures, and audits empirical data and code replication packages compliant with Management World (《管理世界》) publication…

Structures digital wallet analysis with stored value, regulatory classification, and risk assessment.

Use when working with Posthog — postHog analytics management — monitor events, feature flags, experiments, session recordings, and…

Define behavioral contracts, run adversarial tests, and detect regressions for AI agents — invariants, edge cases, statistical analysis…

Full deprecation lifecycle for APIs, features, or internal code — Hyrum's Law analysis, deprecation notices, migration path design, and…

Spawn a fresh adversarial reviewer mid-implementation for any non-trivial decision — branching logic, cross-module boundaries…

Relentlessly interview the user about a plan or design, walking down every branch of the decision tree one question at a time until…

Structured production incident workflow — gather symptoms, run diagnostics, correlate recent deploys, draft a timeline and incident report

Extract requirements one targeted question at a time before any plan or code starts — hypothesizes user intent, scores confidence, and…

Instrument code with structured logging, metrics, and OpenTelemetry tracing — define the on-call questions first, then work backward to…