Skip to content
Skills Library
Personal productivity · Automation

source-mine

/source-mine

Mine one external source — GitHub, Google Drive/Gmail, ChatGPT or Perplexity history, or the local filesystem — into attributed vault notes on a fixed schema. Use when Shane says "mine my GitHub", "pull context out of my ChatGPT history", "what's in ~/Code that isn't in the vault", "extract X into the knowledge graph", or when bootstrapping vault context for a new project. Do NOT use for a single document or article (use /ingest), for reading the vault itself (use /vault-retrieve), or for web research on a topic (use /research-sweep).

Licence
MIT
Last repository change
20.09.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 20.09.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Mine one external source — GitHub, Google Drive/Gmail, ChatGPT or Perplexity history, or the local filesystem — into attributed vault notes on a fixed schema. Use when Shane says "mine my GitHub", "pull context out of my ChatGPT history", "what's in ~/Code that isn't in the vault", "extract X into the knowledge graph", or when bootstrapping vault context for a new project. Do NOT use for a single document or article (use /ingest), for reading the vault itself (use /vault-retrieve), or for web research on a topic (use /research-sweep).

Triggers from the description

mine my GitHubpull context out of my ChatGPT historywhatt in the vaultextract X into the knowledge graph
Original author description

Mine one external source — GitHub, Google Drive/Gmail, ChatGPT or Perplexity history, or the local filesystem — into attributed vault notes on a fixed schema. Use when Shane says "mine my GitHub", "pull context out of my ChatGPT history", "what's in ~/Code that isn't in the vault", "extract X into the knowledge graph", or when bootstrapping vault context for a new project. Do NOT use for a single document or article (use /ingest), for reading the vault itself (use /vault-retrieve), or for web research on a topic (use /research-sweep).

How it works

  1. Inputs
  2. Steps
  3. Output
  4. Scope guard
Original SKILL.md headings · 47 lines, 415 words
SKILL.md preview
---
name: source-mine
description: Mine one external source — GitHub, Google Drive/Gmail, ChatGPT or Perplexity history, or the local filesystem — into attributed vault notes on a fixed schema. Use when Shane says "mine my GitHub", "pull context out of my ChatGPT history", "what's in ~/Code that isn't in the vault", "extract X into the knowledge graph", or when bootstrapping vault context for a new project. Do NOT use for a single document or article (use /ingest), for reading the vault itself (use /vault-retrieve), or for web research on a topic (use /research-sweep).
---

# Skill: /source-mine [source]

Turn an account, corpus, or directory you already own into attributed vault notes — the sweep that gets the graph from empty to useful, and the one nobody wants to hand-write twice.

**Don't:** write a note without its source and mine date in the body; an unattributed claim is unverifiable a month later and indistinguishable from something you made up. **Don't** mine and synthesize in one pass — extract first, decide what deserves a note second, or the interesting-but-irrelevant all gets written up. **Don't** touch the source: mining is read-only, always.

## Inputs

`source` is one of: `github`, `filesystem`, `google`, `chat-history` (ChatGPT / Claude.ai / Perplexity), or `vault` (re-reading for unlinked material). If ambiguous, ask which — the extraction rules differ per source.

## Steps

1. **Read [source-recipes.md](../_lib/source-recipes.md)** for this source's endpoints, extraction targets, and known pitfalls.
2. **Inventory before extracting.** List what exists — repo count, thread count, directory listing — and report the scale. A sweep whose size is unknown at the start silently becomes a sample.
3. **Extract to a scratch list**, not to the vault. One line per candidate: what it is, why it might matter, where it came from.
4. **Check each candidate against the vault** before writing: `obsidian search query='<candidate>' limit=5`. Existing note → append an `## Update — <date>` section. No note → create.
5. **Write the notes.** Route by type:
   - a durable idea or framework → `Knowledge/Concepts/` via `/ingest` (it enforces the Vault Schema)
   - project state → `Knowledge/Projects/<project>/`
   - an external artifact worth keeping → `Knowledge/Reference/`
   - anything you cannot place → `Inbox/`, for `/inbox-triage` to route
6. **Attribute in the body:** `*Source: <source> — mined <date>*`.
7. **Commit the vault** once at the end, not per note:
   ```bash
   VAULT="$HOME/Library/Mobile Documents/iCloud~md~obsidian/Documents/Personal"
   git -C "$VAULT" add '<the note paths you wrote>' && git -C "$VAULT" commit -m "docs: mine <source> → N notes"
   ```

## Output

Report, before the commit:

```
Source: <source>          Inventoried: <n>    Extracted: <n>    Written: <n>
Created:  <paths>
Updated:  <paths>
Skipped:  <n> — <why: transient, duplicate, out of scope>
Not read: <n> — <why: timeboxed, auth failed>
```

`Skipped` and `Not read` are the load-bearing lines. Without them a partial sweep reads as complete.

## Scope guard

Mining reads widely across personal accounts. Extract only what serves the stated goal — do not compile a profile because the data is reachable. When a source needs a sign-in that isn't already active, stop and ask rather than working around it.

Versions

The database has no other skills named source-mine.

Database snapshot: 13.11.2026 · package version 381fe00deab3 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100vault-retrieve
    Answer a question from the vault — generate the query fan-out, read every match, and return the relevant content verbatim with its paths. Use when Shane says "what do my notes say about X", "search the vault for X", "pull everything on X", "check my notes before we start", or…
  • 90graph
    Maintain the Obsidian activity graph (engineering vault): set up a new project folder, ingest a raw source, close a session, run the lint, pull GitHub activity, write the weekly rollup, analyse the graph, or move the vault. Use when the user mentions the graph, the vault,…
  • 100kb-init
    Use when setting up a new knowledge base, bootstrapping an Obsidian vault, or when user says 'init kb', 'new knowledge base', 'create kb', or 'setup vault'. Triggers on any request to initialize or scaffold a knowledge base project.
  • 95scout-ask
    Use when the working directory is a Scout vault (it has `knowledge-base/` and `action-items/`) and the user asks about the state of a project, initiative, person, decision, meeting or open thread ("where are we on X", "what's going on with Y", "who is Z", "what's on my plate"),…
  • 86recall
    Deeply retrieve Context Nest vault context for a topic and answer with citations. Use when you need the full graph of related vault knowledge beyond what auto-retrieval injected.
  • 90recall
    Deep context retrieval from the vault (the personal knowledge base) and the Claude setup graph. Use when past decisions, project history, prior research, or how the setup is wired would help and is not already in context — or when the user says "recall X", "what did we decide…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.