agentleFS
AndyMelnykovAndyMelnykov/obsidian-claude/skills/ask/SKILL.md

ask

Skill2 starsChanged 3 months agoMITView on GitHub

Answer a question from what's already captured in the vault: check indexes/ for a matching topic, then grep across every folder for relevant terms, read the matching notes, and answer directly from their content with [[wikilink]] citations — saying plainly when the vault doesn't have an answer rather than silently falling back to general knowledge. Read-only, never writes to the vault. Use when the question should be answered from existing vault notes, not when the user is handing Claude something new to capture.

75 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • phanghonghaoSkill

    poster

    HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 62 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Answer directly from what those notes say: If the vault doesn't have an answer, say so plainly rather than guessing or silently falling …

    line 29
  2. Distinctive:

    No retrieval beyond Grep/glob text search (no BM25, embeddings, or reranking).

    line 40

“Common” is measured: kept by at least 6 in 10 of the 62 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ask the vault

This skill is read-only. It never creates, edits, or moves a note. If the user wants the answer itself saved, that's a separate capture of the conversation content (pasted text) — ask doesn't do that automatically.

Steps

  1. Resolve the vault per Resolving the vault — an explicit directory named in the request, then the OBSIDIAN_VAULT environment variable, then the current directory. The OBSIDIAN_VAULT fallback is what lets this work consistently from an unrelated project directory or a different chat session, without repeating the vault path every time.
  2. Check indexes/ first for a topic index matching the question — per Indexes, it's a faster, curated map of what exists and where than a cold grep. If nothing there covers it, or the question needs more than the index's own notes, grep the whole vault — all folders — for terms from the question: note titles, frontmatter tags, and body text. Read the notes that look relevant, starting with a handful; read more only if the question clearly needs broader coverage.
  3. Answer directly from what those notes say. If the vault doesn't have an answer, say so plainly rather than guessing or silently falling back to general knowledge. It's fine to answer from general knowledge if the user asks for that too — just say explicitly when that's what's happening, versus when the answer is coming from the vault.
  4. Cite which notes the answer drew from as [[wikilink]]s, so the user can jump to them in Obsidian.

Out of scope

No retrieval beyond Grep/glob text search (no BM25, embeddings, or reranking). No vault writes of any kind.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.