菜单
Use this skill for efficient Obsidian vault navigation and search. Covers which MCP tools to use, search strategies, batch operations, and how to leverage frontmatter summaries for quick triage.
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/cajias/claude-skills --skill search-navigation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。
Research (as an internal step) a GitHub/GitLab milestone's open issues in order to PRINT a copy-paste autonomous-loop prompt that drives the milestone to completion — behavior-driven (BDD) scenarios, adversarial gap-checking, a per-iteration Definition-of-Done gate (build + all tests + zero lint + /code-review + /security-audit + /ponytail:ponytail findings all cleared), specialized-agent selection with model tier scaled to task complexity, and a root-cause→harness-hardening loop. Use this whenever the user says "generate a goal prompt", "goal-driven prompt", "milestone loop prompt", "prompt to finish/complete the milestone", "clear-and-paste prompt for milestone N", "make me a prompt to drive /autoresearch", or otherwise wants a ready-to-paste block that autonomously completes a milestone's remaining issues. The deliverable is the prompt itself, not a summary. NOT for actually executing the work (this only GENERATES and PRINTS the prompt — the loop does the work), NOT for merely summarizing or listing a mile
Eight APM-marketplace-authoring gotchas discovered during real migrations from hand-authored .claude-plugin/marketplace.json to APM-managed and from CC-native plugin authoring. Use when: (1) running APM's packaging step (with or without `--dry-run`) or its marketplace-check command in a repo with an `apm.yml`; (2) wiring CI for an APM marketplace; (3) the CI staleness check (repack, then `git diff --quiet`) fails despite a clean local; (4) prettier reformats `marketplace.json` after APM's packer writes it; (5) APM exit code 1 on local-path-only marketplaces; (6) confused by `packages:` in apm.yml vs `plugins:` in marketplace.json; (7) commitlint rejects a commit with `footer-leading-blank` despite no apparent footer; (8) `apm compile -t claude` exits 0 with zero output and no compiled plugin appears; (9) husky+lint-staged pre-commit blocks the FIRST marketplace commit with markdownlint `MD040/fenced-code-language` errors on a SKILL.md file copied verbatim from `~/.claude/skills/`. The gotchas form a chain — f
Canonical authoring layout for an APM (microsoft/apm) package, plus the decision matrix for whether you need a `marketplace:` block. Use when: (1) you've run `apm init` and are unsure where SKILL.md / agent .md / command .md files belong (answer: under `.apm/`, NOT at repo root); (2) you've authored CC-native files at `commands/agents/skills/` at repo root and wonder if that's "right" (it works as fallback layout #3 "Claude plugin", but it's not the canonical authoring path); (3) you're trying to choose between the three layouts APM recognizes (one-skill repo, multi-primitive `.apm/`, Claude plugin); (4) `apm targets` fails with "No such command" in CLI 0.12.1 (subcommand doesn't exist); (5) `apm validate` fails with "No such command" in CLI 0.12.1 (use APM's packaging command in dry-run mode instead); (6) wondering whether `apm compile -t claude` will generate output for a hand-authored CC-native plugin (it won't; it's a no-op for layout #3); (7) wondering if you need a `marketplace:` block in apm.yml (you d
基于 SOC 职业分类
正在显示 SKILL.md
| name | search-navigation |
| description | Use this skill for efficient Obsidian vault navigation and search. Covers which MCP tools to use, search strategies, batch operations, and how to leverage frontmatter summaries for quick triage. |
Efficient strategies for finding and accessing information in the Obsidian vault.
| Need | Tool | Why |
|---|---|---|
| Read one file | read_note | Direct access |
| Read multiple files | read_multiple_notes | Batch (max 10) |
| Check file exists/metadata | get_notes_info | No content load |
| Get just frontmatter | get_frontmatter | See summary without content |
| Search by content | search_notes with searchContent: true | Full-text search |
| Search by metadata | search_notes with searchFrontmatter: true | Find by type/status/tags |
| Browse structure | list_directory | See folder contents |
| Find all tags | manage_tags with operation: list | See note's tags |
| Vault overview | get_vault_stats | Size, recent files |
get_frontmatter - Fast Metadata CheckUse when: You need to understand what a file is about without reading content
Returns: Just the YAML frontmatter (type, status, summary, tags)
Perfect for: Triaging multiple files quickly
get_notes_info - Batch MetadataUse when: Checking multiple files at once (up to array of paths)
Returns: Path, size, modified date, hasFrontmatter flag
Perfect for: Quick scan of a folder's contents
search_notes - Find ContentParameters:
- query: Search text
- searchContent: true (default) - search in note body
- searchFrontmatter: true - search in YAML frontmatter
- limit: Max results (default 5, max 20)
- caseSensitive: false (default)
Use searchFrontmatter for:
- Finding notes by type: "type: decision"
- Finding by status: "status: active"
- Finding by summary keywords
read_multiple_notes - Batch ReadParameters:
- paths: Array of note paths (max 10)
- includeContent: true (default)
- includeFrontmatter: true (default)
Use when: You know which files you need and want to read them efficiently
When looking for notes on a topic:
Search frontmatter for summary keywords
search_notes(query: "authentication", searchFrontmatter: true, searchContent: false)
Get info on promising results
get_notes_info(paths: [results])
Read only the relevant ones
read_note(path: "the-one-I-need.md")
When you know the category:
List directory to see options
list_directory(path: "knowledge-base/aws-services")
Get frontmatter for files of interest
get_frontmatter(path: "knowledge-base/aws-services/lambda-patterns.md")
Read if summary matches need
When looking for cross-cutting concerns:
Search frontmatter for tag
search_notes(query: "#blocker", searchFrontmatter: true)
Or search content for inline tags
search_notes(query: "#decision", searchContent: true)
When looking for recent work:
Get vault stats with recent files
get_vault_stats(recentCount: 10)
Read recent files that look relevant
Before starting work on a client/project:
1. list_directory("engagements/active/[client]")
2. read_note("engagements/active/[client]/context.md")
3. If decisions folder exists: list_directory + get_frontmatter on ADRs
When making a technical choice:
1. search_notes(query: "[technology]", searchFrontmatter: true)
2. Filter results for type: decision
3. read_multiple_notes on relevant ADRs
When someone is mentioned:
1. list_directory("people")
2. Look for matching filename
3. read_note("people/[name].md")
When resuming previous work:
1. list_directory("agent-workspaces")
2. Find relevant session folder by date/context
3. read_note("agent-workspaces/[session]/context.md")
get_notes_info before reading full notes (check if worth reading)read_multiple_notes instead of multiple read_note callslimit parameter in search to avoid overwhelming resultshasFrontmatter in get_notes_info - files without it need full read| Path | Contains |
|---|---|
engagements/active/ | Current client work |
engagements/completed/ | Archived engagements |
knowledge-base/ | Reference material by technology |
playbooks/ | Reusable methodologies |
people/ | Information about individuals |
career/ | Brag doc, promotion materials |
agentic-platform-program/ | Tech lead domain work |
agent-workspaces/ | Session workspaces |
agent-workspaces/shared/ | Cross-session persistent notes |
| Looking for... | Search approach |
|---|---|
| Active blockers | search_notes("#blocker", searchFrontmatter: true) |
| Decisions on X | search_notes("type: decision", searchFrontmatter: true) + filter |
| Lessons learned | list_directory("knowledge-base/lessons-learned") |
| Person info | list_directory("people") + read_note |
| Recent session | get_vault_stats(recentCount: 5) |
obsidian-memory:memory-system skill for when/what to storeCLAUDE.md in vault root for vault-specific conventions