sprites.dev CLI + API runbook for AgentSmith — ephemeral fly-machine workloads. Service create/update, file uploads (with the compress-over-~20MB rule), checkpoints, URL auth. Headless-Linux only; Windows/Git-Bash path-mangling material from the upstream spindev version is deliberately out of scope.
Plugin agentsmith-sprites-dev from marketplace agentsmith-plugins in SmithFamilyPlayground/agentsmith-plugins. Commands read from the repo's manifest — 1 month ago.
sprites-devUse when a Smith-family agent runs `sprite` CLI commands or calls the sprites.dev API for ephemeral fly-machine workloads — service create/update, file uploads (with the compress-over-~20MB rule), checkpoints, URL auth. Triggers on `sprite exec`, `sprite api`, `sprite console`, `sprite checkpoint`,
GitHub CLI runbook for AgentSmith and the SmithFamilyPlayground org — PR conventions, auto-review + daily-rollup workflow expectations, ruleset awareness, Actions triage. Bundles the `clean-gone` skill for pruning local branches whose remotes are deleted.
2 skills
AgentSmith family API plugin — owns vault-IO, the Memory.* contract surface, the Dispatch.Agent surface, routes-cache, and the subagent-tools (ex-lifecycle) hook surface for sub-agents. Phase-2 MVP: bundled `memory.sh` and `vault-commit.sh` CLIs implementing the Memory.* contract against the AgentSmith vault (~/.secondbrain today-branch) plus a local-mode passthrough; `routes.sh` with bundled fallbacks for svc-unreachable; `dispatch.sh` as a filesystem-queue rendezvous for closed-set fix concerns; defensive + always-on subagent hooks shipped alongside the plugin. svc is a graceful fallback path, not a hard dependency. MCP server, HTTP round-trip to svc, and Haiku PII/secrets scan are deferred to Phase-2b.
1 skill
Lifecycle channel for AgentSmith — push-only Claude Code channel plugin (declares claude/channel only; no tools, no permission relay). Reads NDJSON over a Unix domain socket from a local supervisor process and emits operational nudges (idle_check, context_pressure, health_pulse, external_event) as <channel source="agentsmith-comms"> notifications. Companion to the existing telegram channel — user-facing comms stay on telegram, lifecycle nudges are isolated here.
1 MCP server
Fly.io runbook for the `tod-smith` deployment — app anatomy, the always-on attachable invariant, persistence layout, Tailscale (userspace) topology, secrets rotation (incl. the VAULT_* reserved-name gotcha and Telegram bot uniqueness across fly + home box), deploy/rollback, and a triage playbook.
1 skill
How agents write to ~/.secondbrain: vault-commit.sh, frontmatter schema, daily-branch lifecycle, raw/ immutability.
1 skill
Continuity-of-self memory for persistent-identity Claude Code agents. Phase-1a MVP — ships a bundled `local-vault` CLI implementing the Memory.* contract (store/recall/update/list/config) against a local project vault at `<project>/.claude-persistent-memory/`, so the plugin works standalone on any project from day one (no AgentSmith / no svc / no api dependency). Phase-1b will add the dreaming-model hooks (state.md @-import + recall + consolidate-and-restart + context-pressure); phase-1c will add auto-detect-and-route to an `agentsmith-api` backend when present.
1 skill
Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.
44 skills · 1 MCP server
CI/CD pipeline configuration, GitHub Actions/GitLab CI workflow setup, and automated deployment pipeline orchestration
4 skills · 1 command · 5 agents
Plan, build, and debug Zoom integrations across REST APIs, Meeting SDK, Video SDK, webhooks, bots, and MCP workflows. Search meetings, retrieve recordings, access transcripts, and design AI-powered Zoom experiences.
44 skills · 3 MCP servers
Build, launch, grade, and schedule Claude Managed Agents (CMA) in your own Anthropic account — a plugin re-implementation of Anthropic's launch-your-agent reference skill (Apache-2.0; independent, not a fork). Every session starts with a goal (./my-agent/goal.json, opt-in SessionStart hook, driven by /cs-goal); loop_compiler.py compiles it into a bounded grade->iterate loop (max_iterations 1..20), a recurring cron scheduled-deployment loop, or a single-pass interview->stage->launch workflow. 6 skills: orchestrator (context: fork goal router) + interview + stage-launch + grade-iterate + run-without-you + wrap-up. 18 stdlib-only deterministic scaffolders (no network/API calls; live launches emitted as BYOK curl that never prints the key), 4 agents, 8 commands, hooks, 5 references, 4 assets. Validators enforce CMA limits. Distinct from engineering/agent-harness (generic domain loop) and write-a-skill (authors Claude Code skills, not CMAs).
6 skills · 8 commands · 4 agents · hooks
DevOps, cloud, and deployment specialists - Kubernetes, Terraform, AWS, Azure, GCP, and SRE
Production LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.
98 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.