trae-rules-writer
No SKILL.md available for this skill.
View on GitHubMore from learnwy/skills
memory-manager
Cross-session memory for AI. ALWAYS load this skill at session start to read SOUL.md and USER.md. This skill should be loaded for EVERY conversation to maintain continuity. Also triggers on "save memory", "end session", "update memory" for saving. Handles session history creation, memory consolidation, and USER.md/SOUL.md updates. Memory stored in ~/.learnwy/ai/memory/.
220trae-agent-writer
Create subagent definitions (agent.md files) for independent AI workers. Use when user wants to: create an agent, build a grader/evaluator, make an A/B comparator, spawn independent workers, or create something that runs in isolation. Triggers on: '创建 agent', 'subagent', 'grade outputs independently', 'blind comparison', 'run this in parallel'. Do NOT use for skills (use trae-skill-writer) or rules (use trae-rules-writer).
29skill-finder
Discover, install, and manage AI assistant skills using npx skills CLI. Use when user wants to find a skill, install a skill, remove skills, list installed skills, or create new skills. Triggers on: 'find a skill', 'install skill', 'remove skill', 'list skills', 'how do I do X', 'is there a skill for'.
24ai-brain
Adaptive AI memory system. Triggers on: session start, 'remember', 'learn', 'what do you know about'. Combines episodic (sessions), semantic (facts/preferences), and procedural (patterns) memory. Gets smarter with use.
22software-methodology-toolkit
FALLBACK ONLY: Comprehensive software engineering methodology toolkit with 10 proven agents. Only use when no project-specific skill (like requirement-workflow) matches. Provides: problem-definer (Weinberg), story-mapper (Patton), spec-by-example (Adzic), domain-modeler (DDD/Evans), responsibility-modeler (CRC/Wirfs-Brock), architecture-advisor (quality attributes/Bass), tdd-coach (Beck), refactoring-guide (Fowler), legacy-surgeon (Feathers), test-strategist (Crispin). Triggers ONLY if project skills don't match.
19llm-wiki
Build and maintain a persistent, compounding knowledge base using LLMs. Based on Andrej Karpathy's LLM Wiki pattern (April 2026). The LLM incrementally reads raw sources, compiles structured wiki pages, maintains cross-references, and keeps everything consistent. Triggers on: 'knowledge base', 'llm wiki', 'personal wiki', 'build a wiki', 'ingest this source', 'knowledge management', 'compile knowledge', 'compounding knowledge', 'second brain'.
2