Skip to main content
Manus에서 모든 스킬 실행
원클릭으로
SunflowersLwtech
GitHub 제작자 프로필

SunflowersLwtech

2개 GitHub 저장소에서 수집된 26개 skills를 저장소 단위로 보여줍니다.

수집된 skills
26
저장소
2
업데이트
2026-07-17
저장소 탐색

저장소와 대표 skills

loopify-requirements
소프트웨어 개발자

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.

2026-07-17
polanyi-design
웹·디지털 인터페이스 디자이너

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.

2026-07-17
search-harness
소프트웨어 개발자

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.

2026-07-17
remotion-best-practices
소프트웨어 개발자

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.

2026-07-17
searchpo-agent-capabilities
소프트웨어 개발자

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.

2026-07-17
searchpo-deepwiki-research
소프트웨어 개발자

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.

2026-07-17
searchpo-full-flow
소프트웨어 개발자

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.

2026-07-17
searchpo-impl-agent
소프트웨어 개발자

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

2026-07-17
이 저장소에서 수집된 skills 14개 중 상위 8개를 표시합니다.
contrastive-behavioral-examples
소프트웨어 개발자

Good vs. bad behavioral examples showing what excellent play looks like vs. common mistakes. Derived from xuyuzhuang-Werewolf contrastive prompting and Avalon-LLM self-play reflection.

2026-07-05
deception-detection-mastery
소프트웨어 개발자

Faction-conditional strategies for deception and detection, derived from xuyuzhuang-Werewolf and LLMWereWolf role strategies. Evil agents get deflection and alibi techniques; good agents get detection heuristics.

2026-07-05
memory-consolidation-system
소프트웨어 개발자

3-tier memory tracking (STM/Episodic/Semantic) derived from ai-traitors-v2 and ai-town generative agent reflection. Helps agents maintain beliefs about each player and synthesize round memories into strategic conclusions.

2026-07-05
social-intelligence-evaluation
소프트웨어 개발자

Enriches GameMaster narration with awareness of social dynamics, derived from Sotopia 7-dimensional social intelligence evaluation. Tracks influence shifts, trust erosion, and narrative tension cues.

2026-07-05
strategic-reasoning-protocol
소프트웨어 개발자

Internal 5-step reasoning pipeline derived from xuyuzhuang-Werewolf. Agent performs Situation-Suspicion-Reflection-Strategy-Response analysis implicitly before generating any output.

2026-07-05
contrastive-behavioral-examples
코치 및 스카우트

Good vs. bad behavioral examples showing what excellent play looks like vs. common mistakes. Derived from xuyuzhuang-Werewolf contrastive prompting and Avalon-LLM self-play reflection.

2026-03-14
deception-detection-mastery
배우

Faction-conditional strategies for deception and detection, derived from xuyuzhuang-Werewolf and LLMWereWolf role strategies. Evil agents get deflection and alibi techniques; good agents get detection heuristics.

2026-03-14
memory-consolidation-system
소프트웨어 개발자

3-tier memory tracking (STM/Episodic/Semantic) derived from ai-traitors-v2 and ai-town generative agent reflection. Helps agents maintain beliefs about each player and synthesize round memories into strategic conclusions.

2026-03-14
이 저장소에서 수집된 skills 12개 중 상위 8개를 표시합니다.
저장소 2개 중 2개 표시
모든 저장소를 표시했습니다