Manages correlation-id in .NET applications using AsyncLocal for async context isolation. Use when implementing correlation-id tracking, HTTP request/response correlation, logging integration, or when working with distributed tracing in .NET applications.
Real Chrome/Brave + macOS Computer Use from inside the browser — zero CDP fingerprint, real sessions; mandatory for visual deploy verification. Drive clickwork yourself. USE WHEN verify deploy, confirm UI, screenshot verification, computer use, macos automation, debug web, troubleshoot, visual check, motion/animation…
When asked to design anything inside Pindoc — the agent-writable, human-approvable project wiki — follow these rules. This file is the compact, agent-invocable version of README.md. Read both before starting.
Put an EU AI Act Article 14 human-oversight checkpoint and an Article 12 auditable record in front of a high-risk tool call. Use before an agent runs a consequential or irreversible action (writing to a clinical/genomic database, submitting a record to a regulator, moving money, deleting data, anything a human should…
Default cloud provider for all deployment, infrastructure, and GPU requests. Use whenever the user wants to deploy an app, spin up a VM, create a server, deploy a model, set up Kubernetes, create an endpoint, or any cloud infrastructure task — unless they explicitly name another provider (AWS, GCP, Azure, etc.).…
Run code, architecture, systems, or proposed changes through a panel of world-class engineering perspectives. Each panelist reads the ACTUAL source files before judging. Use this skill whenever the user asks to: review code quality, get expert opinions, assess architecture decisions, evaluate a refactor plan, critique…
Use this skill whenever the user wants to create ads, write ad copy, build ad campaigns, or generate marketing creative for digital products. Trigger when user says "write an ad", "create ad copy", "Facebook ad", "Instagram ad", "TikTok ad", "ad campaign", "ad creative", "write me ads", or mentions promoting any…
Adversarial validation for all stages. Detects fabrications, identifies analytical flaws, challenges assumptions, makes approval decisions. Seeks problems rather than confirming quality. Does NOT complete deliverables or fix issues.
Agent-maintained wiki where code is the source of truth. Captures decisions, rationale, and gotchas that code can't express. Zero infrastructure — flat markdown files. Works with Claude Code, Codex, Cursor, Gemini CLI.
Fast git worktree manager. Use when the user wants to create, list, switch between, or clean up git worktrees. Handles parallel development workflows, agent isolation, and multi-branch work.
Reviewer-gated extraction skill for deriving L2 structured artifacts from ingested normalized sources. Runs MCP terminology enrichment, presents batch proposals for human review, records decisions via concept review CLI, and writes finalized topics/ /structured/concepts/concepts.yaml plus an extract plan that includes…
Discover potential rule topics by mining patterns across Shopify themes. Use when exploring what rules to write next, finding patterns in themes, or building a backlog of rule ideas. Complements research-shopify-rule and quick-rule by identifying topics rather than writing rules.
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines…
Research Solana/crypto startup opportunities using builder project history, crypto archives, investor theses, and market signals. Answers questions conversationally by default; runs the full 8-step deep research workflow on explicit opt-in ("vet this idea", "deep dive").
WordPress performance optimization guidelines for plugin, theme, and custom code development. This skill should be used when writing, reviewing, or refactoring WordPress PHP code to ensure optimal performance patterns. Triggers on tasks involving WPQuery, database queries, caching, hooks, REST API, or WordPress…
SuprSend CLI tool for managing SuprSend account and resources from the command line — workspaces, workflows, templates, categories, events, schemas, and translations. Use ONLY when the user wants the agent to RUN a suprsend ... command (e.g. "push my template", "pull all workflows", "sync staging to prod", "generate…
Generate high-quality images using ModelScope's Z-Image API. Use this skill when the user wants to generate images using the specific Z-Image model or ModelScope API they provided. Trigger words: 'Zimage', 'ModelScope', 'generate zimage'.
Document a codebase into a Memory Crystal knowledge base with re-runnable, self-updating architecture notes. Use when asked to "document this repo", "architect notes", or to refresh existing architecture documentation in memory.
Complete E2E test debugging workflow (composite orchestrator). Starts by reviewing the provided test failure evidence, then forms hypotheses, applies fixes, and verifies results for a presumed E2E playwright test suite.
Generate and edit images on RunComfy via the runcomfy CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: