source-mine
/source-mine
Wydobywa kontekst z GitHuba, Google Drive, Gmail, historii ChatGPT lub plików lokalnych do notatek w bazie wiedzy.
- Autor
- slogsdon ↗
- Repozytorium
- skills-vault-knowledge ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 20.09.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 20.09.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Wydobywa kontekst z GitHuba, Google Drive, Gmail, historii ChatGPT lub plików lokalnych do notatek w bazie wiedzy.
Wyzwalacze z opisu
Oryginalny opis (EN)
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).
Jak działa
- Inputs
- Steps
- Output
- Scope guard
Podgląd SKILL.md
--- 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.
Wersje
W bazie nie ma innych skilli o nazwie source-mine.
Migawka bazy z 13.11.2026 · wersja paczki 381fe00deab3 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100vault-retrieve
Odpowiada na pytanie na podstawie vaultu Obsidian: przeszukuje notatki i zwraca treść dosłownie wraz ze ścieżkami. - 90graph
Prowadzi graf aktywności w vaultcie Obsidian: notatki z sesji, wnioski, przeglądy tygodniowe i aktywność z GitHuba. - 100kb-init
Konfiguruje nową bazę wiedzy lub vault Obsidian, tworząc szkielet projektu. - 95scout-ask
Odpowiada na pytania o stan projektów, osób i decyzji w vaulcie Scout, opierając się na bazie wiedzy. - 86recall
Przeszukuje vault Context Nest pod kątem tematu i odpowiada z cytatami, wykraczając poza automatyczne podpowiedzi. - 90recall
Wyszukuje decyzje, historię projektu i wcześniejsze badania w bazie wiedzy oraz grafie konfiguracji, gdy brakuje ich w kontekście.