tommywagz

@tommywagz source repo

27 skills
0 followers
10 hours ago last updated

▌
Google Agents CLI Adk Code · tommywagz bundle
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management", or needs ADK (Agent Development Kit) Python API patterns and code examples. Part of the Google ADK skills suite. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

0 installs
▌
Find Skill · tommywagz bundle
Finds and safely installs existing Agent Skills, MCP servers, or Composio integrations. TRIGGER for "find a skill", "find an MCP server", registry searches, awesome-agent-skills, or Composio integrations. DO NOT TRIGGER for writing a new skill, evaluating an existing skill, or ordinary web/docs research.

0 installs
▌
Write Skill · tommywagz bundle
Creates or restructures an Agent Skill package with SKILL.md, scripts, references, and assets. TRIGGER for "create/write/scaffold a skill", a SKILL.md, or fixing a skill's description, token budget, or layout. DO NOT TRIGGER for ordinary documentation, general code, or evaluating a skill.

0 installs
▌
A2a Workflows · tommywagz bundle
Skill for authoring A2A (Agent2Agent) multi-agent workflows, featuring host-agent orchestration and sub-agent communication. TRIGGER when: 'A2A workflow', 'A2A multi-agent', 'A2A host', 'A2A sub-agent', 'Agent2Agent collaboration', 'AgentCard', 'agent-card.json', 'A2ACardResolver'. DO NOT TRIGGER when: normal ADK workflows without A2A (use google-agents-cli-adk-code).

0 installs
▌
Evaluate Skill · tommywagz bundle
Evaluates an existing Agent Skill for routing accuracy, task performance, or security. TRIGGER for "evaluate/test/benchmark a skill", trigger precision/recall, red-team/security review, or an eval suite. DO NOT TRIGGER for authoring a new skill, general application tests, or generic statistics.

0 installs
▌
Integrate Repo · tommywagz bundle
Audits an unintegrated file, folder, or vendored dependency against the host repository's real quality gates, then emits an ordered remediation script and a local CI pre-flight runner. TRIGGER when the user says 'integrate repo', 'make this folder compliant', 'match the repo style', 'align external code with our conventions', 'remediate to match CONTRIBUTING.md', 'make it pass CI locally', 'why does CI fail but lint passes locally', or drops vendored/generated/AI-authored code into a repo and asks to bring it up to standard. DO NOT TRIGGER for scaffolding a brand-new repository or service (use a project-scaffolding skill), for resolving git merge conflicts, for refactoring business logic or fixing test failures unrelated to repo standards, or for authoring the CI pipeline itself rather than conforming to it.

0 installs
▌
Model Governance · tommywagz bundle
Profiles an agent prompt, workflow step, or task spec for cognitive/token complexity, resolves the optimal LLM provider and model tier against a governed catalog, and emits the exact opencode run --model provider/model launch command plus opencode.json agent.<name>.model config patches. TRIGGER when the user asks to 'assign a model for this prompt', 'select the optimal model/tier', 'configure opencode model governance', wants a --model provider/model launch command, needs to reconcile ~/.config/opencode/opencode.json against a project opencode.json, or asks to optimize model choice for cost vs. intelligence (result_maximized, cost_optimized, balanced). DO NOT TRIGGER for rewriting or improving prompt wording (prompt engineering), provisioning API keys/credentials, or running live model benchmarks/evals.

0 installs
▌
Find Skill 2 · tommywagz bundle
Searches external Agent Skill, MCP server, and SaaS-tool registries to find an existing skill or integration matching a requested capability, screens every candidate for prompt injection and other security risks before its content is read as instructions, and installs only vetted results into the local project. TRIGGER when the user asks to find, search for, or discover an existing skill, MCP server, or tool integration — e.g. "is there a skill for X", "find an MCP server for Slack", "search awesome-agent-skills", "add a Composio integration for Y". DO NOT TRIGGER for authoring a brand-new skill from scratch with no external source in mind (use a skill-writing skill), scoring/auditing a skill already in this project (use a skill-evaluation skill), or a generic web/documentation search with no skill, MCP-server, or tool-registry angle (e.g. library docs, release notes).

0 installs
▌
Ap2 Agent Payments · tommywagz bundle
Builds and audits AP2 (Agent Payments Protocol) payment agents: Checkout and Payment Mandates as SD-JWT verifiable credentials, human-present vs. human-not-present flows, role sub-agents, x402 crypto rails, and authorization/dispute audits. TRIGGER when the user mentions AP2, ap2-protocol.org, 'mandate.checkout.1', 'mandate.payment.1', Checkout Mandate, Payment Mandate, open vs. closed mandate, Credentials Provider or Merchant Payment Processor agents, x402 settlement, google-agentic-commerce/AP2, or asks to let an agent pay, delegate autonomous spend under signed constraints, or prove after the fact who authorized a purchase. DO NOT TRIGGER for UCP cart/catalog/checkout-session work with no payment settlement (use ucp-merchant-servers or ucp-consumer-surface), or for wiring a non-agentic payment gateway SDK (Stripe, PayPal, Adyen) with no verifiable mandate credential.

0 installs
▌
GCP Cost Optimizer · tommywagz bundle
Analyzes a normalized Google Cloud resource inventory (idle Compute Engine instances, unattached persistent disks/static IPs, under-utilized BigQuery flat-rate slots, unexpiring BigQuery datasets, over-provisioned Cloud Run min_instances/concurrency) and generates prescriptive recommendations plus reviewable Terraform remediation snippets to cut spend. TRIGGER when the user asks to "reduce GCP costs", "find idle Google Cloud resources", "optimize BigQuery slot utilization", "run a GCP spend/FinOps audit", or provides a GCP billing/inventory export. DO NOT TRIGGER for general Terraform authoring unrelated to cost, AWS/Azure cost optimization, or security/compliance scanning of GCP resources (use the gcp-terraform-security-policy skill for that).

0 installs
▌
Write Skill 2 · tommywagz bundle
Creates, formats, and scaffolds new Agent Skills using the standard SKILL.md + scripts/ + references/ + assets/ architecture. TRIGGER when the user asks to "create a skill", "write a skill", "make an agent skill", "package this as a skill/SKILL.md", "scaffold a skill folder", wants a Trigger/Do-Not-Trigger description written, or wants a workflow, runbook, API doc, or set of scripts turned into a reusable Claude Code or Claude Agent SDK skill. Also trigger to audit, restructure, or fix an existing skill's SKILL.md format, description, token budget, or folder layout. DO NOT TRIGGER for general documentation requests with no skill-authoring intent (e.g. a README or product doc); for general-purpose code, scripts, or tests with no skill-packaging intent; for simply invoking/running an already-installed skill; or for scoring, testing, or security-reviewing an existing skill with no restructure or fix requested (use a skill-evaluation skill instead).

0 installs
▌
Ucp Consumer Surface · tommywagz bundle
Skill for building the client / consumer surface of a Universal Commerce Protocol (UCP) integration: a shopping agent or platform that negotiates capabilities against a business's discovery profile, searches/looks up catalog items, builds carts, drives native or embedded checkout to completion, and tracks orders via webhook. TRIGGER when: 'UCP shopping agent', 'UCP consumer client', 'UCP platform integration', 'buy/book/order X through UCP', 'negotiate UCP capabilities', 'UCP checkout client', 'UCP-Agent header'. DO NOT TRIGGER when: building the server/business side of UCP (use ucp-merchant-servers), authoring new UCP extensions/schemas, or wiring AP2 payment mandates beyond submitting a basic payment instrument (use an AP2-specific skill).

0 installs
▌
Ucp Merchant Servers · tommywagz bundle
Skill for standing up and implementing a UCP (Universal Commerce Protocol) compliant Merchant or Business Server. TRIGGER when: 'UCP merchant server', 'UCP business server', 'UCP server integration', 'UCP shopping service', 'UCP capability profile'. DO NOT TRIGGER when: client-side shopping agents or buying clients (use ucp-consumer-surface-shopping-agents).

0 installs
▌
Real Estate Floorplan · tommywagz bundle
Orchestrates a two-stage spatial research and architectural drafting pipeline using Model Context Protocol (MCP) servers: researching property floor plans across real estate listing platforms (Zillow, Apartments.com, Redfin), and programmatically authoring vector CAD layouts via Floor Builder and CAD MCP servers. TRIGGER when users ask to 'research real estate floor plans', 'extract floor plan from Zillow, Redfin, or Apartments.com', 'generate CAD floor plan from property listing', 'draw floor plan with Floor Builder MCP', 'convert listing blueprint to DXF/SVG', or route queries through real estate research and CAD drafting MCP servers. DO NOT TRIGGER for property price estimation or mortgage calculations, general 3D video game level modeling, or mechanical CAD drafting unrelated to residential architecture.

0 installs
▌
Evaluate Skill 2 · tommywagz bundle
Evaluates an existing Agent Skill's trigger accuracy, task performance, and security posture, then iteratively fixes it until it clears user-set (or default) thresholds. TRIGGER when the user asks to "evaluate a skill", "test a skill", "score/benchmark a skill", "check a skill's trigger precision/recall/false-positive rate", "security review a skill", "red team a skill", "run an eval suite" against a skill, or wants an existing skill's content audited against a production checklist, risk-tiered, or A/B tested. DO NOT TRIGGER for: authoring a brand-new skill from scratch with no existing skill to assess (use a skill-writing skill instead); evaluating general application code or tests unrelated to the Agent Skills format; generic ML/statistics questions about precision, recall, or false positives with no specific Agent Skill in view; or fixing a skill's file layout, folder structure, or word count with no metrics, testing, or security ask attached (use a skill-authoring skill instead).

0 installs
▌
Ucp Extensions Schemas · tommywagz bundle
Guides the authoring, structuring, and date-based versioning of Universal Commerce Protocol (UCP) capability extension schemas (discounts, fulfillment options, food ordering, and lodging verticals) using JSON Schema Draft 2020-12, reverse-domain authority binding, and discovery manifest integration. TRIGGER when: 'author UCP extension', 'design UCP schema', 'version UCP extension', 'date-based versioning for UCP', 'extend UCP checkout schema', 'custom UCP vertical schema', 'UCP food ordering schema', 'UCP lodging schema', 'authority binding validation'. DO NOT TRIGGER when: implementing business server routes and handlers (use ucp-merchant-servers), building client shopping agent negotiation logic (use ucp-consumer-surface), creating AP2 payment mandate credentials (use ap2-agent-payments), or designing generic non-UCP JSON schemas.

0 installs
▌
GCP Iam Privilege Audit · tommywagz bundle
Audits Google Cloud IAM bindings and service-account key exposure, interprets IAM Recommender evidence, and proposes reviewable least-privilege predefined/custom roles or Workload Identity Federation migration without changing access. TRIGGER when users ask to 'audit GCP IAM permissions', 'harden service account keys', 'implement least-privilege roles', 'configure Workload Identity', 'rightsize project-level editor bindings', or review IAM Recommender output. DO NOT TRIGGER for granting new broad production access, rotating secrets without an IAM audit objective, or AWS/Azure IAM reviews.

0 installs
▌
Adk Long Horizon Harness · tommywagz bundle
Designs and operates headless, long-running ADK agents triggered by Pub/Sub events or Cloud Scheduler cron jobs, with idempotent event handling, structured logs, retries/dead-lettering, and session-context compaction. TRIGGER when users ask to 'build an event-driven ADK agent', 'run ADK on a cron schedule', 'configure Pub/Sub triggers', 'manage long-running background tasks', or use `EventsCompactionConfig`/`LlmEventSummarizer` to summarize session history. DO NOT TRIGGER for interactive single-request ADK agents, generic FastAPI endpoints without an autonomous worker, or one-time local scripts.

0 installs
▌
Agents CLI Benchmark Eval · tommywagz bundle
Designs, runs, and scores local evaluation datasets against an ADK agent or command, computes exact-match, token-overlap (ROUGE-like), semantic-similarity proxy, rubric scores, and routing precision/recall, then writes JUnit XML and Markdown reports. TRIGGER when users ask to 'run evaluation datasets', 'evaluate agent accuracy', 'calculate trigger precision/recall', 'generate a JUnit test report for my agent', 'set up an agent benchmark suite', or score an ADK agent locally. DO NOT TRIGGER for live production load testing, training/fine-tuning a model, or general unit tests without an agent output/dataset evaluation objective.

0 installs
▌
Adk OAUTH User Consent Flow · tommywagz bundle
Designs user-authenticated OAuth 2.0/OIDC consent flows for ADK agents accessing Google Workspace APIs, using least-privilege scopes, authorization-code + PKCE redirects, and ADK credential-request callbacks without exposing user tokens to the model. TRIGGER when users ask to 'configure OAuth for ADK agent', 'request user consent in ADK', 'connect my agent to Google Drive/Workspace', 'handle user OAuth tokens', or use `OAuth2Auth`, `OidcAuth`, or `tool_context.request_credential`. DO NOT TRIGGER for service-account-only server-to-server access, creating Google Cloud API keys, or general Google Workspace administration.

0 installs
▌
Agents CLI Plugin Moderator · tommywagz bundle
Configures and deploys a runner-wide ADK BasePlugin that wraps every coordinator and sub-agent with GCP Model Armor safety guardrails, blocking harmful inputs, session-state poisoning, and sensitive-data (PII) exfiltration at model boundaries and configured outbound tools. TRIGGER when the user asks to "add safety guardrails in ADK", "configure Model Armor in agents-cli", "block harmful content or prompts", "implement exfiltration detection", "write a runner-wide safety plugin", or mentions `BasePlugin`, `before_model_callback`, `sanitizeUserPrompt`/`sanitizeModelResponse`. DO NOT TRIGGER for agent-specific (non-global) callback logic unrelated to safety, generic content moderation outside an ADK Runner, or GCP IAM/Terraform security auditing (use gcp-terraform-security-policy for that).

0 installs
▌
Adk Durable Human In The Loop · tommywagz bundle
Scaffolds and explains a durable, asynchronous Human-in-the-Loop (HITL) approval gate for ADK agent workflows: pauses a node via LongRunningFunctionTool, publishes a signed state-holding webhook to an external dashboard, and resumes the exact paused invocation via ADK's /run_sse resume contract once a signed decision arrives. TRIGGER when the user asks to "add a workflow approval gate in ADK", "suspend/pause ADK graph execution for human input", "implement human sign-off" or "durable human-in-the-loop" for an ADK agent, "resume a paused ADK invocation", "integrate ADK asynchronous resume", or needs ResumabilityConfig / LongRunningFunctionTool / a signed approval webhook. DO NOT TRIGGER for synchronous same-turn clarification via request_input or a graph RequestInput node with no cross-process durability need, ADK Tool Confirmation used purely in-memory, or cross-session agent memory (use adk-cross-session-knowledge-bank).

0 installs
▌
Agents CLI Conformance Tester · tommywagz bundle
Spins up a local, dependency-free mock sandbox to run a MUST/SHOULD/MAY-leveled conformance suite against a loopback-bound UCP merchant server or A2A host/remote agent, printing a JSON or JUnit compliance summary. TRIGGER for "run UCP conformance tests", "verify A2A compliance of my local server", "agents-cli test-compliance", "check protocol compatibility", or a mock sandbox to smoke-test a local merchant server or agent. DO NOT TRIGGER for standard PyTest/Vitest unit-testing or generic linting; DO NOT TRIGGER for a remote/staging/production (non-loopback) endpoint -- use the official Universal-Commerce-Protocol/conformance or a2aproject/a2a-tck suites for those; DO NOT TRIGGER for authoring a new UCP server or A2A agent from scratch (use ucp-merchant-servers or a2a-workflows first).

0 installs
▌
Agents CLI Scaffold Extension · tommywagz bundle
Generates a polyglot agent workspace linking a TypeScript/Hono HTTP gateway to a Python/ADK multi-agent workflow, with package manifests, boundary contracts, and run instructions. TRIGGER when users ask to 'scaffold a multi-agent polyglot workspace', 'agents-cli scaffold enhance multiple languages', 'add Node.js/Python boundaries to an agent project', or connect a Hono handler to an ADK orchestrator. DO NOT TRIGGER for standard single-agent scaffolding, a Python virtual environment alone, generic Hono endpoint authoring, or deploying an existing service.

0 installs
▌
GCP Terraform Security Policy · tommywagz bundle
Audits Google Cloud Terraform configuration (raw .tf files or a `terraform show -json` plan) against CIS Google Cloud Platform Foundation Benchmark controls, private-by-default storage/network defaults, and least-privilege IAM, then proposes remediation HCL before `terraform apply`. TRIGGER when the user asks to "audit Terraform for GCP security", "scan for public GCS buckets/IAM/firewall rules", "check CIS GCP benchmark compliance", "review least-privilege IAM in Terraform", or provides a `terraform plan`/`terraform show -json` output for GCP. DO NOT TRIGGER for general Terraform authoring/module design unrelated to security, AWS/Azure/other-cloud IaC scanning, or actually running `terraform apply` (this skill only audits and proposes; it never applies infrastructure changes).

0 installs
▌
GCP Kubernetes Resource Triage · tommywagz bundle
Diagnoses failing GKE/Kubernetes workloads from read-only pod status, events, logs, container exit codes, resource settings, and Artifact Registry image-pull signals; produces reviewable remediation patch manifests without applying them. TRIGGER when users mention `CrashLoopBackOff`, `OOMKilled`, `ImagePullBackOff`, `ErrImagePull`, `CreateContainerConfigError`, a pod stuck `Pending`, or ask why a Kubernetes/GKE deployment is crashing or restarting. DO NOT TRIGGER for deploying a new Kubernetes app, modifying a healthy workload, cluster-node/network outages, or running destructive `kubectl` recovery commands.

0 installs
▌
Adk Cross Session Knowledge Bank · tommywagz bundle
Seeds, queries, and explains Vertex AI Memory Bank cross-session memory for ADK agents: PreloadMemoryTool/LoadMemoryTool recall, generate_memories_callback writes, managed/custom memory topics, and scope-based consolidation. TRIGGER when the user asks to "implement cross-session memory in ADK", "configure Vertex AI Memory Bank", "persist agent knowledge/preferences across conversations", "use PreloadMemoryTool or LoadMemoryTool", or seed/query Memory Bank facts by scope. DO NOT TRIGGER for short-term session state (state["key"]) with no cross-session need, generic RAG/document retrieval corpora, or non-Vertex memory stores (Redis, a custom vector DB) unrelated to Agent Engine Memory Bank.

0 installs

27 published skills