{"skill":{"slug":"project-context-anchor","displayName":"Dynamic Project Soul Snapshot | 动态项目灵魂快照","summary":"Writes AI_CONTEXT.md into the project root as a \"dynamic soul snapshot\" — capturing tech stack, recent git diffs, key decisions, active plan, and a compresse...","tags":{"latest":"1.0.2"},"stats":{"comments":0,"downloads":84,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":3},"createdAt":1775283750270,"updatedAt":1775302610604},"latestVersion":{"version":"1.0.2","createdAt":1775302530948,"changelog":"project-context-anchor v1.0.2\n\n- Clarified and strengthened override instructions: this skill now always writes to ./AI_CONTEXT.md in the project root, never to MEMORY.md or ~/.claude/.\n- Added a dedicated comparison table and warning section explaining the difference between AI_CONTEXT.md (created by this skill) and Claude built-in memory.\n- Updated trigger instructions to strongly recommend explicit invocation by skill name for reliable operation in Claude Code.\n- All output is now always written to AI_CONTEXT.md in the project folder, never into any memory files.\n- Documentation emphasizes that this skill must not use or update any internal memory tooling.","license":"MIT-0"},"metadata":null,"owner":{"handle":"xiao3333","userId":"s176rm9rbzxf4b2ee63vp0zckd83n5ss","displayName":"xiao3333","image":"https://avatars.githubusercontent.com/u/99626958?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.2.0","updatedAt":1775302610604}}