obsidian-project-bootstrap
This skill should be used when the user asks to start a new research project, import an existing code-plus-Markdown repository into Obsidian, or bin…
它会碰到什么
扫了多少2 个文本文件,4 KB
它会碰到什么不碰外部(只输出文字)
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0
这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。
技能内容
Obsidian Project Bootstrap
Bootstrap a project knowledge base for the current repository.
Role in the workflow
This is a supporting skill.
Use obsidian-project-memory as the main workflow authority. Use this skill only when a repository still needs its initial binding or rebuild.
When to use
- The user says “start a new research project”.
- The user has an existing repo with code plus Markdown and wants an Obsidian knowledge base generated automatically.
obsidian-project-memorydetects a research-project candidate but no existing binding.
Required input
Resolve the vault path from one of:
- explicit user input,
OBSIDIAN_VAULT_PATH.
Procedure
- Identify the repository root.
- Run a preflight detect step first:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/obsidian-project-memory/scripts/project_kb.py" detect --cwd "$PWD"
- Only if the repo is unbound and should be imported, run bootstrap:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/obsidian-project-memory/scripts/project_kb.py" bootstrap --cwd "$PWD" --vault-path "$OBSIDIAN_VAULT_PATH"
- Verify that bootstrap created at least:
.claude/project-memory/registry.yaml.claude/project-memory/<project_id>.mdResearch/{project-slug}/00-Hub.mdResearch/{project-slug}/01-Plan.mdResearch/{project-slug}/Knowledge/Source-Inventory.mdResearch/{project-slug}/Knowledge/Codebase-Overview.md
- If the imported project still lacks real background or experiment context, switch to an agent-first pass:
- read the most informative repo docs and code entry points,
- synthesize durable notes into
Knowledge/,Papers/,Experiments/,Results/, orWriting/, - avoid placeholder notes.
- Summarize the created knowledge base and the next recommended canonical notes to fill in.
Notes
- The bootstrap process imports structure and summaries, not raw datasets, caches, checkpoints, or the whole code tree.
- Ignore
.git,.venv,node_modules, caches, checkpoints, binaries, and other heavy artifacts. - The default vault is compact:
00-Hub.md,01-Plan.md,Knowledge/,Papers/,Experiments/,Results/,Writing/,Daily/,Archive/. - If
python3is unavailable in the current shell, use the system Python interpreter that can runproject_kb.pyand say so explicitly.
References
references/BOOTSTRAP-RUNBOOK.md- preflight decisions, failure modes, and post-bootstrap verification
想直接用这个技能?
本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。
它属于哪个仓库
星标★ 3,829
本站分层T1
该仓技能数1161
原文件路径
skills/33-Galaxy-Dawn-claude-scholar/skills/obsidian-project-bootstrap/SKILL.md同一个仓库里的其他技能
- Full-empirical-analysis-skill
- Full-empirical-analysis-skill-R
- Full-empirical-analysis-skill-Stata
- auto-empirical-research-skills
- StatsPAI_skill
- Full-empirical-analysis-skill
- Full-empirical-analysis-skill-Stata
- Full-empirical-analysis-skill-R
- academic-paper-composer
- academic-paper-strategist
- medical-imaging-review
- paper-slide-deck