Answer questions against the local Obsidian wiki — not from model memory.

MITAuto-check passedKnowledge Management

Install Query

skills CLI
$ npx skills add HurricaHjz/second-yourself --skill query -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HurricaHjz/second-yourself query --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HurricaHjz/second-yourself.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/query .claude/skills/query && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
query
GitHub stars
123
Token cost
~2.2k tokens
SKILL.md length
1,167 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Answer questions against the local Obsidian wiki — not from model memory.

  • Works in 6 steps: Read the global index (always first) → Deep-read the targets (triage by… → Synthesize with citations (weighted by… → …
  • The user runs /query
  • SKILL.md covers Goal, Triggers, Depth (see CLAUDE.md →… and Pipeline, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Query is an agent skill from HurricaHjz/second-yourself. Answer questions against the local Obsidian wiki — not from model memory. Use when the user runs /query, or asks in natural language about "my notes / my wiki / what I've researched / my past decisions / what do I know about X". Always read wiki/index.md FIRST and WHOLE to locate pages, then read them in full, then answer with [[wikilink]] citations. If the wiki has nothing relevant, say so explicitly before giving any general-knowledge answer. Offers to file high-value answers back into wiki/syntheses/ so…

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management, covering Citation management. It works with Obsidian. The repository describes itself as: Second yourself. One agent that remembers you, with many hands to act for you: a multi-agent harness (Claude Code, with Codex helpers), a self-maintaining local wiki as its… The licence is MIT.

When your agent uses it

  • The user runs /query
  • Asks in natural language about my notes / my wiki / what Ive researched / my past decisions / what do I know about X

Example prompts

  • “my notes / my wiki / what I”
  • “/query”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Read the global index (always first)
  2. Deep-read the targets (triage by confidence)
  3. Synthesize with citations (weighted by confidence)
  4. Degrade gracefully (two cases, never a bare refusal)
  5. File high-value answers back
  6. Log it (only if you filed a synthesis)

What it can do on your machine

Read from SKILL.md and the folder at commit 17c03f2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Query loads about 2.2k tokens when it runs. Until then it costs about 135 tokens; SKILL.md has 1,167 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~135
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HurricaHjz/second-yourself at commit 17c03f2, republished under its MIT licence (© HurricaHjz). 1,167 words, ~2,176 tokens.

Download SKILL.mdSave it as .claude/skills/query/SKILL.md (or your agent's skills folder).
name
query
description
Answer questions against the local Obsidian wiki — not from model memory. Use when the user runs /query, or asks in natural language about "my notes / my wiki / what I've researched / my past decisions / what do I know about X". Always read wiki/index.md FIRST and WHOLE to locate pages, then read them in full, then answer with [[wikilink]] citations. If the wiki has nothing relevant, say so explicitly before giving any general-knowledge answer. Offers to file high-value answers back into wiki/syntheses/ so explorations compound.
user-invocable
true

query — answer from the wiki, with citations

Goal

Turn a question into a deep read of the compiled wiki and a synthesized, cited answer. When the answer is valuable, file it back into the wiki so knowledge compounds.

Triggers

  • /query <question>
  • Natural language: "what do my notes say about X", "what was my past decision on Y", "search my wiki for Z"
  • Mentions of: my wiki / my notes / my knowledge base / what I've researched.

Depth (see CLAUDE.md → Processing depth)

Match answer depth to the question (auto standard/concise; research is opt-in or ask-first, never silent — this is query's rule and it is unchanged. ingest differs deliberately: it picks each source's depth after reading and records it, because a batch of forty sources cannot carry forty asks. One question can.) All depths stay token-efficient — research permits more depth, never filler.

  • standard (DEFAULT) — balanced, cited synthesis.
  • concise — a tight, direct answer citing only the few key pages.
  • research — rigorous and exhaustive: exact figures, verbatim quotes with refs, explicit treatment of agreements/contradictions across sources, and a short "limitations / gaps" note. Higher accuracy bar, still no filler. A filed synthesis uses academic structure + depth: research.

Pipeline

Step 1 — Read the global index (always first)

Read wiki/index.md whole — route mode, CLAUDE.md §5 — and locate candidate pages across every ## section. Read the whole catalogue before choosing pages: lexical search or a hand-picked list can omit pages relevant to the answer.

Step 2 — Deep-read the targets (triage by confidence)

Open the most relevant pages in full with the read tool (or obsidian-cli). Follow ## Related links one hop out when it helps. When candidates are many, first check their confidence cheaply (one grep "^confidence:" <candidate files>, frontmatter only) and deep-read authoritative/high first; pull in medium as needed; consult low/very-low only to fill gaps. If the catalogue under-covers the question and qmd is active (the qmd-search skill — dormant unless qmd is installed + enabled), use it as the semantic fallback (qmd query "<q>" --json --files), confidence-rank the hits, then deep-read; otherwise grep as usual.

Step 3 — Synthesize with citations (weighted by confidence)
  • Cite every page you draw from inline as [[Page Name]].
  • For a verbatim claim, use a > blockquote.
  • Don't over-cite: one citation at the start and end of a passage from the same page is enough.
  • Weight by confidence: resolve conflicts toward the higher tier (and, if tied, the newer updated); state authoritative/high plainly, but attribute and hedge low/very-low ("a promotional listing claims…", "an unverified transcript suggests…"); never let a very-low or unverified claim harden into an asserted fact. Optionally flag a weak citation inline, e.g. [[X]] *(low-confidence)* (only for low/very-low).
Step 3b — Freshness duty (Tier-2 flags; costs no extra reads)

Judge only the pages you have ALREADY read for this answer — never read extra pages for this duty:

  • Contradiction (page vs page, or page vs clearly newer evidence just read) → surface it in the reply and add/extend the page's ## Conflicts / Open Questions block (CLAUDE.md §4.4).
  • Staleness suspicion (old updated against newer in-wiki evidence; a superseded claim) → one line in the reply + offer the fix now; if not fixed on the spot, record it on the page as frontmatter flagged: YYYY-MM-DD <one-phrase reason> so /deep-lint reconciles it later.
  • Flags are annotations, not logged ops — the reconciling deep-lint run logs their resolution.
  • The freshness line — a completion gate. Every reply that read wiki pages ends with one line, whatever the active style: Freshness: <N> pages read · oldest [[page]] (updated YYYY-MM-DD) · <k> flagged (k = flags placed or staleness fixes made this run; usually 0). The answer is not done until the line has appeared. Naming the oldest page is the locator — the line cannot be written without looking at the updated: dates already in hand. A reply that read no wiki pages (general-knowledge fallback) skips the line and says so.
Step 4 — Degrade gracefully (two cases, never a bare refusal)
  • No coverage — if index.md has nothing relevant and the question is general knowledge, say so first:

    Nothing in the local wiki covers this — answering from general knowledge: …then answer. Never silently pretend the wiki had the answer.

  • Only low-confidence coverage — if the wiki does cover it but only at low/very-low, still give the substantive answer from those pages, opening with an explicit warning, e.g.:

    ⚠ Low-confidence: the only sources here are a promo listing and an auto-transcript — treat as provisional. Never refuse with a bare "I don't know".

Show full SKILL.md (442 more words)Show less
Step 4b — Gap proposal (propose-only; CLAUDE.md §6)

When Step 4 declared missing or weak coverage, a gather proposal MAY follow the answer — never replace it — if ALL four hold: the gap is evidenced by the search just run (the brief cites what was searched — a zero-findings claim carries its probe, CLAUDE.md §11); load-bearing for the core of the task (answerable-but-low coverage stays a warning, not a proposal); plausibly fixable by public web sources (not owner-only knowledge); and not explicitly declined this session. At most ONE proposal per reply, surfaced whatever the active style, formatted why (gap + evidence) · what (source kinds, rough count) · how (the literal /gather command with its page budget — never --yes) · cost. Only the owner's explicit yes runs it — that run-spec only; gather's own gates unchanged. Consent ledger: explicit no → dead this session (a concise gap note) · unaddressed → one compact reminder while the task is live, then quiet (a later re-fire on a new task references the earlier brief concisely, never a full re-brief) · "later" → one re-offer at the natural point. Non-interactive runs never propose — state the gap in the report.

Step 5 — File high-value answers back

If the answer is more than ~2 paragraphs or is comparative/analytical, ask:

This looks worth keeping — save it to wiki/syntheses/?

On yes, create wiki/syntheses/<slug>.md (kebab-case) with synthesis frontmatter, a ## Sources Used section listing every cited [[page]], and register it under Syntheses in index.md. Give it a conservative inherited confidence (a synthesis defaults to medium as agent-derived and caps at high, per §4.6; drop to low if it rests mainly on low sources); never crystallise a low/unverified claim as asserted fact. Report the filed page and its confidence to the user — every newly added wiki file states its level (as ingest Step 8 does), so you can review and re-grade it. Refresh on write: the new page's qmd embedding refreshes per the qmd-search contract — a turn-end hook where installed, inline only where not; a no-op when qmd is dormant.

Step 6 — Log it (only if you filed a synthesis)

A pure inline answer is NOT logged — logging is for brain-updating ops only (see CLAUDE.md §5). Only if Step 5 actually filed a synthesis, append:

markdown
## [YYYY-MM-DD] synthesis | <short question>
- **Output**: filed [[synthesis-slug]]; updated [[index.md]]

Log a no-synthesis (inline-only) query only if the user explicitly asks.

Hard constraints

  • Never answer substantive questions from memory — read the wiki first.
  • Never silently answer when the wiki lacks coverage — declare it.
  • Use confidence to triage, weight and hedge; on only-low coverage, answer with a warning, never a bare refusal.
  • The freshness line is a completion gate (Step 3b) — every reply that read wiki pages carries it; no done-declaration without it.
  • Output in British/UK English with real [[wikilink]] citations.

© HurricaHjz, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/query of HurricaHjz/second-yourself.

Open the folder on GitHubat commit 17c03f2

Compare with similar skills

Query next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Query compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Query this skillHurricaHjz/second-yourself123—~2.2kAutomated safety check: PassMIT
Wiki Context PackAr9av/obsidian-wiki3.5k—~752Automated safety check: NotesMIT
Llmwikiatomicstrata/llm-wiki-compiler2.2k—~814Automated safety check: PassMIT
Corgispec Askricoyudog/Coding_Corgi_flow104—~689Automated safety check: PassNone
Auditpricklywiggles/niamos192—~1.4kAutomated safety check: PassNone
Brainpoteto/brainmaxxing325—~635Automated safety check: PassMIT

Similar skills

  • Wiki Context Pack

    Ar9av/obsidian-wiki

    Produce a token-bounded, citation-ready context slice from an existing Obsidian vault for a downstream agent or task.

    3.5k GitHub stars~752 tokensUpdated 2 days ago
    Knowledge ManagementAuto-check: notes
  • Llmwiki

    atomicstrata/llm-wiki-compiler

    Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation.

    2.2k GitHub stars~814 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Corgispec Ask

    ricoyudog/Coding_Corgi_flow

    Answer pending Obsidian questions from CorgiSpec Memory/Wiki with early-stop retrieval, source citations, and a strict file budget.

    104 GitHub stars~689 tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • Audit

    pricklywiggles/niamos

    Scan this Obsidian vault for content that's drifted from the conventions in CLAUDE.md (status↔folder drift, missing required fields, naming violations, stale active items, frontmatter health issues…

    192 GitHub stars~1.4k tokensUpdated 3 mo ago
    Knowledge ManagementAuto-check passed
  • Brain

    poteto/brainmaxxing

    Read/write brain files (Obsidian vault at brain/). An agent skill from poteto/brainmaxxing.

    325 GitHub stars~635 tokensUpdated 7 mo ago
    Knowledge ManagementAuto-check passed
  • Zotero Obsidian Bridge

    Galaxy-Dawn/claude-scholar

    Moves papers from Zotero into an Obsidian project knowledge base as source notes, literature synthesis and writing outputs, with evidence records behind every promoted claim.

    5.7k GitHub stars~514 tokensUpdated 17 days ago
    Research & ScienceAuto-check passed

More from HurricaHjz/second-yourself

All 12 skills in this repo
  • Qmd Search

    HurricaHjz/second-yourself

    OPTIONAL, DORMANT semantic-search layer over the wiki, powered by qmd (local hybrid BM25 + vector + rerank).

    123 GitHub stars~1.9k tokensUpdated 8 days ago
    Auto-check passed
  • Export Template

    HurricaHjz/second-yourself

    Sync THIS LLM-Wiki framework with its public GitHub repo, ONE direction per run: --push (vault → repo) publishes your framework; --pull (repo → vault) updates your framework from a newer repo version.

    123 GitHub stars~4.8k tokensUpdated 8 days ago
    Auto-check: warnings
  • Lint

    HurricaHjz/second-yourself

    Health-check the Obsidian wiki — the "static analysis" pass for a knowledge base.

    123 GitHub stars~6.3k tokensUpdated 8 days ago
    Auto-check passed
  • Compile Core

    HurricaHjz/second-yourself

    The compile lane's half of the ingest skill: choose a source's depth after reading it, write the source page from the depth's template, assign confidence, network the knowledge, and propose the…

    123 GitHub stars~4.4k tokensUpdated 8 days ago
    Auto-check passed
  • Lint Slice

    HurricaHjz/second-yourself

    The read-only half of the lint skill for a headless lane: index consistency, link and orphan health, the pending-flag count, the attic, qmd-registry, injection, customisation-pairing and…

    123 GitHub stars~3.5k tokensUpdated 8 days ago
    Auto-check passed
  • Output

    HurricaHjz/second-yourself

    Produce a user-facing DELIVERABLE (report, brief, literature review, slide deck, table, email, outline, …) into the output/ directory — grounded in the wiki and strictly following the user's…

    123 GitHub stars~2k tokensUpdated 8 days ago
    Auto-check passed

Works with

Questions about Query

What does Query do?

Answer questions against the local Obsidian wiki — not from model memory. Query is an agent skill from HurricaHjz/second-yourself. Answer questions against the local Obsidian wiki — not from model memory.

When should I use Query?

Query fits situations like: the user runs /query; asks in natural language about my notes / my wiki / what Ive researched / my past decisions / what do I know about X.

How do I install Query in Claude Code?

Run `npx skills add HurricaHjz/second-yourself --skill query -a claude-code`. Or copy the skill folder (.claude/skills/query in HurricaHjz/second-yourself) into .claude/skills/query in your project. Claude Code loads it when a task matches its description.

How do I install Query in Codex?

Run `npx skills add HurricaHjz/second-yourself --skill query -a codex`. Or copy the skill folder (.claude/skills/query in HurricaHjz/second-yourself) into .agents/skills/query in your project. Codex loads it when a task matches its description.

Can I use Query in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HurricaHjz/second-yourself --skill query -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/query, .gemini/skills/query, .github/skills/query and .opencode/skills/query in your project.

What does Query need to run?

SKILL.md names no scripts, command-line tools or credentials: Query is instructions for the agent only.

Does Query access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Query safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Query use?

Query is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Query use?

About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Query?

Skills that share tags, products or a category with Query: Wiki Context Pack (Ar9av/obsidian-wiki, 3.5k stars), Llmwiki (atomicstrata/llm-wiki-compiler, 2.2k stars), Corgispec Ask (ricoyudog/Coding_Corgi_flow, 104 stars) and Audit (pricklywiggles/niamos, 192 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Query?

HurricaHjz (a GitHub user) maintains it in HurricaHjz/second-yourself, which has 123 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 1, 2026.

Source: HurricaHjz/second-yourself on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.