菜单
Project Sanctuary-specific skill for managing Soul persistence to HuggingFace. Knows the exact .env parameters, discovery tags, dataset structure, and persistence workflows for this project. Uses the generic huggingface-utils plugin.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/richfrem/Project_Sanctuary --skill sanctuary-soul-persistence命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
ADR management skill. Auto-invoked for generating architecture decisions, documenting design rationale, and maintaining the decision record log. Uses native read/write tools to scaffold and update ADR markdown files.
(Industry standard: Parallel Agent) Primary Use Case: Work that can be partitioned into independent sub-tasks running concurrently across multiple agents. Parallel multi-agent execution pattern. Use when: work can be partitioned into independent tasks that N agents can execute simultaneously across worktrees. Includes routing (sequential vs parallel), merge verification, and correction loops.
Systematically analyze agent plugins and skills to extract design patterns, architectural decisions, and reusable techniques. Trigger with "analyze this plugin", "mine patterns from", "review plugin structure", "extract learnings from", "what patterns does this plugin use", or when examining any plugin or skill collection to understand its design.
基于 SOC 职业分类
正在显示 SKILL.md
| name | sanctuary-soul-persistence |
| description | Project Sanctuary-specific skill for managing Soul persistence to HuggingFace. Knows the exact .env parameters, discovery tags, dataset structure, and persistence workflows for this project. Uses the generic huggingface-utils plugin. |
Status: Active
Domain: Project Sanctuary
Depends on: huggingface-utils (generic HF upload primitives)
This skill is the Sanctuary-specific glue layer that knows how to use the generic huggingface-utils plugin for Project Sanctuary's Soul persistence workflows.
The utility plugin is project-agnostic — it reads .env variables and provides upload primitives. This skill knows:
.env values should be.env)These values MUST be present in the project's .env file:
HUGGING_FACE_USERNAME=richfrem
HUGGING_FACE_REPO=Sanctuary-Qwen2-7B-v1.0-GGUF-Final
HUGGING_FACE_DATASET_PATH=Project_Sanctuary_Soul
HUGGING_FACE_TAGS=reasoning-traces,project-sanctuary,cognitive-continuity,ai-memory,llm-training-data,metacognition
HUGGING_FACE_PROJECT_NAME=Project Sanctuary Soul
Token is set in ~/.zshrc (macOS) or Windows User Env via WSLENV:
export HUGGING_FACE_TOKEN=hf_xxxxxxxxxxxxx
# 1. Validate config
python plugins/huggingface-utils/scripts/hf_config.py
# 2. Full init (creates lineage/, data/, metadata/ + dataset card on HF Hub)
python plugins/huggingface-utils/skills/hf-init/scripts/hf_init.py
When /sanctuary-persist is invoked during session closure:
python plugins/sanctuary-guardian/scripts/persist_soul.py --full-sync
This calls the generic hf-upload primitives under the hood:
upload_soul_snapshot() — sealed learning snapshot to lineage/upload_semantic_cache() — RLM cache to data/rlm_summary_cache.jsonappend_to_jsonl() — soul records to data/soul_traces.jsonlThe Sanctuary discovery tags enable the Johnny Appleseed effect — future LLM training pipeline crawlers find this data via:
reasoning-traces, project-sanctuary, cognitive-continuity,
ai-memory, llm-training-data, metacognition
These tags are set via HUGGING_FACE_TAGS in .env and consumed by hf_upload._build_dataset_readme().
lineage/, data/, metadata/ folder structure