Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add Azure OpenAI backend, add AI Foundry model, test AI gateway, LLM policies, configure AI backend, token metrics, AI cost control, convert API to MCP, import OpenAPI to gateway.

Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and continuous monitoring. Use when the user mentions create evaluator, LLM judge, hallucination, faithfulness, correctness, relevance, run eval, score spans, score experiment, trigger-run, column mapping, continuous monitoring, or improve evaluator prompt.

Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports any LLM provider (e.g. OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM). Use when the user mentions AI integration, LLM provider credentials, create integration, list integrations, update credentials, delete integration, or connecting an LLM provider to Arize.

DRAFT. Use when running a Luma-centered GTM event campaign: pull/export guests, enrich and score, draft invites and social, stage email+LI sequences paused for approval, and wire registration sync. Not installed by deepline skills.

Install and configure the GitHub CLI (gh) for AI agent environments where gh may not be pre-installed and git remotes use local proxies instead of github.com. Use when gh command not found, shutil.which returns None, need GitHub API access for issues or PRs or releases or workflow runs, or repository operations fail with 'failed to determine base repo' error. Provides auto-install script with SHA256 verification, GITHUB_TOKEN auth with anonymous fallback, and the required -R flag pattern for proxy environments. Covers project management via GitHub Projects V2, milestones via REST API, issue lifecycle templates, and label taxonomy management.

Verifies claims in backlog items, skill documentation, or plugin content against primary sources using web lookups. Spawns parallel verification agents that must use WebFetch/WebSearch/gh — training data recall is explicitly rejected as evidence. Produces VERIFIED/REFUTED/INCONCLUSIVE verdicts with citations. Use when items are marked UNVERIFIED or when verifying tool API claims, CLI flags, or documented software behavior.

Generates a structured Bug Fix Brief (BFB) to document issue corrections. Includes root cause analysis, repro steps, fix options, and fix checklist. Use when user asks to create a BFB, document a bug fix, or generate a bug correction document.

End-to-end onboarding for a freshly-plugged-in M5Stack ESP32 device (Cardputer, Cardputer-Adv, Core, CoreS3, Stick) — detect on USB, flash UIFlow 2.0 firmware, and install the Claude Buddy MicroPython app bundle. Use whenever the user plugs in or wants to flash/provision/reset an M5Stack or ESP32 board, or says "m5-onboard go".

The index of every pro-workflow skill and command, grouped by job, with when to reach for each and whether it is human-run or auto-triggered. Use when you are not sure which skill fits, want the full map, or ask "what can this do", "which skill for X", "list the workflow".

Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for future sessions. Use after mistakes or when the user says "remember this", "don't forget", "note this", or "learn from this".

Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this".

Safely remove a feature flag from code while preserving production behavior. Use when the user wants to remove a flag from code, delete flag references, or create a PR that hardcodes the winning variation after a rollout is complete.

Linting best practices and golangci-lint configuration for Golang projects — running linters, configuring .golangci.yml, suppressing warnings with nolint directives, interpreting lint output, and selecting linters. Use when configuring golangci-lint, asking about lint warnings or nolint suppressions, setting up code quality tooling, or choosing linters. Also use when the user mentions golangci-lint, go vet, staticcheck, or revive. Not for wiring a lint step into a GitHub Actions pipeline (→ See `samber/cc-skills-golang@golang-continuous-integration` skill).

Automate Freshservice ITSM tasks via Rube MCP (Composio): create/update tickets, bulk operations, service requests, and outbound emails. Always search tools first for current schemas.

Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting a fine-tuning effort, when converting traces into an eval set, or when calibrating a judge against human labels.

Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model. Use when starting any fine-tuning effort, when unsure whether RAG or prompting would suffice, or when choosing between preference-optimization and reinforcement methods.

Pre-build product and feature risk review for founders, product managers, and AI-assisted builders. Use this skill when the user is about to build a landing page, MVP, SaaS product, internal tool, agent workflow, or major feature and needs to check demand, positioning, monetization, retention, trust, distribution, and adoption risk before implementation starts.

Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.

Use when writing or reviewing Java code in this repo that calls Deepgram Conversational STT v2 / Flux over `/v2/listen`. Covers `client.listen().v2().v2WebSocket()`, `V2ConnectOptions`, `onTurnInfo`, and turn-aware close handling. Use `deepgram-java-speech-to-text` for standard v1 transcription and `deepgram-java-voice-agent` for fully interactive assistants. Triggers include "flux", "conversational stt", "listen v2", "turn detection", "end of turn", and "eot".

Implement and verify joelclaw observability on every change so failures cannot stay silent. Use when adding/updating Inngest functions, gateway channels, webhook providers, APIs, workers, or any pipeline step. Enforces canonical OTEL contract, storage path, and verification gates. Triggers on: 'o11y', 'observability', 'logging', 'otel', 'instrument this', 'silent failure', 'add telemetry', 'log this function'.