sunkit

Convert prompts, vague tasks, product requirements, coding requests, research plans, monitors, reminders, and agent workflows into repeatable, verifiable loops. Use when the user asks to "loopify" a requirement, turn a prompt into an agent loop, design unattended or recurring work, define /loop or routine instructions, create guardrails for autonomous agents, convert one-shot tasks into monitored workflows, or make future prompts more reliable through goal/scope/verification/escalation/stop conditions.

Frontend design cognitive system grounded in Michael Polanyi's tacit knowledge theory. Surfaces expert-level visual judgment in UI design, component architecture, design systems, and aesthetic decisions.

Domain knowledge for designing a search harness for coding agents — search API landscape, ground-API pipeline/strategy, CLI + skills architecture, and roadmap. Use when discussing search agent infrastructure, choosing search APIs for agents, designing search pipelines, or reviewing the search-harness project direction.

Remotion video composition best practices for searchpo. Use when editing src/ components, configuring rendering, optimizing video output, or adding animations/effects to the Remotion pipeline.

Use when Searchpo agents need to inspect available .env keys, provider/API capabilities, DeepWiki MCP availability, credential routing, side-effect boundaries, or decide which agent should use which external service without exposing secrets.

Use when a Searchpo task involves GitHub repository understanding, DeepWiki MCP, repo architecture questions, dependency exploration, or source-code context as supporting context after AnySearch-first evidence planning has started.

Run the full Searchpo provider/live flow from input selection through evidence, FactBank, DeepSeek/Gemini, Remotion render, audit, delivery package, and Douyin gate verification. Use when the user asks to run the complete flow, full flow, /searchpo-full-flow, end-to-end publishable render, or live publish.

Use when implementing or running searchpo provider scripts, Remotion rendering, Gemini visual audit, and Douyin publish/check commands.

Use when orchestrating a searchpo run from source selection and research through Remotion render, Gemini audit, and gated Douyin publishing. Owns task-plan state, verification, and release gates.

Validate the Searchpo Claude/Codex agent bridges, slash commands, and skill bundle. Use when checking bridge health, skill frontmatter, command mirrors, agent mirrors, resolver consistency, or after editing AGENTS.md, tools/skill-bridge-map.json, tools/sync-agent-skills.js, commands/*.md, agents/*.md, or any skills/*/SKILL.md file.

Use when collecting Searchpo source evidence, running AnySearch enrichment or DeepWiki repo-context research, building FactBank/TopicBrief artifacts, and strengthening cross-check before copy generation or publishing.

Real-time search engine supporting web search, vertical domain search, parallel batch search, and URL content extraction.

Use this skill when the user wants Agent-engineering-positioned X/Twitter content from technical inputs including GitHub repos, owner/repo strings, local paths, arXiv/alphaXiv papers, blog/docs URLs, PDFs, notes, source lists, existing posting packs, raw ideas, KYC/support complaints, profile text, or prior run workspaces. It collects evidence, separates verified facts from inference and user vision, drafts responsible posts or threads with reusable assets and concrete discussion questions, governs GPT Image 2-style visual assets, optionally publishes through the official X API, records outcomes, and can synthesize skill-evolution reports or patch plans without weakening claim safety.

Cognitive operating system for software engineering and design, based on Michael Polanyi's tacit knowledge framework. Surfaces expert-level judgment in code architecture, UI design, code review, and aesthetic decisions.