Search persistent memory for relevant context — including architectural decisions, resolved bugs, and implementation patterns — when the user asks about past decisions, when debugging a recurring issue, when uncertain whether something was already decided, or before re-implementing something that may have been done before. Use when the user says "do you remember…", "what did we decide about…", or "have we solved this before".

Pin session decisions, questions, objections, scope constraints, and corrections to a persistent board that survives context compaction. Use PROACTIVELY when: (1) user approves/rejects a recommendation, (2) user asks a clarifying question about a proposal, (3) user states a scope constraint, (4) user corrects a misunderstanding. Also use when user says pin, track this, mark as approved, board, show pins. Auto-invoke without user asking whenever a decision, question, or constraint is detected.

Resume session from CONTEXT-llm.md. Use when resuming work, loading saved context, continuing a previous session. Triggers include "load context", "resume session", "continue where I left off".

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.

Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).

Route agentic-flow work across Anthropic, OpenRouter, Gemini and local ONNX models, and run the Anthropic-compatible translation proxy with its per-run token. Use when the user wants cheaper models, a non-Anthropic provider, local inference, or to point Claude Code at OpenRouter or Gemini.

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live. Covers WebSocket-based audio/video/text streaming, voice activity detection (VAD), background reasoning (extended thinking), asynchronous function calling, session management, ephemeral tokens, live transcription, and live translation. SDKs covered - google-genai (Python), @google/genai (JavaScript/TypeScript).

Map private customer access onto an existing personal app with a short host-specific plan, implementation guidance and checks. Use when login/authentication, multi-tenant isolation, customer-owned connections, background imports, subscription billing, service credits or admin screens need connecting to existing entities and workflows. Skip new-app scaffolding and SDK mechanics whose host mapping is already solved.

Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.

Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.

Cost visibility and tag governance for platform changes. Estimates the monthly cost of a Terraform pull request with Infracost, sets up in-cluster cost allocation by namespace and label with OpenCost, and enforces required cost tags in four layers (Terraform default_tags and variable validation, a Conftest gate on the plan, AWS Config REQUIRED_TAGS, and a Kyverno namespace-label policy). Use when asked "what will this cost", "add cost estimates to PRs", "who owns this spend", "enforce cost-center tags", or "set up OpenCost". Cost as one dimension of a full PR review → /platform-skills:pr-review.

Cost visibility and tag governance for platform changes. Estimates the monthly cost of a Terraform pull request with Infracost, sets up in-cluster cost allocation by namespace and label with OpenCost, and enforces required cost tags in four layers (Terraform default_tags and variable validation, a Conftest gate on the plan, AWS Config REQUIRED_TAGS, and a Kyverno namespace-label policy). Use when asked "what will this cost", "add cost estimates to PRs", "who owns this spend", "enforce cost-center tags", or "set up OpenCost". Cost as one dimension of a full PR review → /platform-skills:pr-review.

Writes Git commit messages. Activates when the user asks to write a commit message, draft a commit message, or similar.

Extract HTML content to Markdown using pandoc. Use when processing HTML files for text extraction, converting web content to readable markdown, or batch converting HTML files in a course/project directory to markdown format for downstream processing. Routed from file-identifier.

Extract MySQL database content to text-readable formats (CSV, JSON, Markdown) for LLM processing and content synthesis. Use when working with MySQL databases that need to be converted to text formats for analysis, synthesis, or inclusion in LLM context windows. Routed from db-router skill.

Extract MySQL database content to text-readable formats (CSV, JSON, Markdown) for LLM processing and content synthesis. Use when working with MySQL databases that need to be converted to text formats for analysis, synthesis, or inclusion in LLM context windows. Routed from db-router skill.

Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.

Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.

Use when adding an interactive UI component that requires client-side JavaScript - creates a framework island with hydration strategy.