Przejdź do treści
Biblioteka skilli
AI i agenci · Automatyzacja

curator

/curator

Wczytuje pamięć do wiki, uruchamia wiki_curator.py (run, report, validate, lint, search) i sprawdza strukturę wiki.

Repozytorium
agent-skills ↗
Licencja
MIT
Ostatnia zmiana repozytorium
22.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
4
Skrypty
3
Komentarze HTML
2
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 22.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co sprawdzić przed instalacją
  • 3 skrypty w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
  • SKILL.md zawiera komentarze HTML (2). Nie widać ich w podglądzie Markdown, a model je czyta.

Skrypty: scripts/adapters.py, scripts/config_loader.py, scripts/wiki_curator.py

Co robi i kiedy

Wczytuje pamięć do wiki, uruchamia wiki_curator.py (run, report, validate, lint, search) i sprawdza strukturę wiki.

Oryginalny opis (EN)

Use when ingesting memory into the wiki, running wiki_curator.py (run/report/validate/lint/search), or linting wiki structure.

Jak działa

  1. Overview
  2. When to Use
  3. Wiki Location
  4. Plugin config (lumen.yaml)
  5. Adapter layer
  6. CLI
  7. Conservative write policy
  8. OKF v0.2
  9. Lint checks
  10. File naming
Sekcje z nagłówków SKILL.md, w oryginale · 127 linii, 1 062 słów
Podgląd SKILL.md
---
name: curator
description: "Use when ingesting memory into the wiki, running wiki_curator.py (run/report/validate/lint/search), or linting wiki structure."
license: MIT
metadata:
  version: 0.2.0
  author: moonlight-lupin
  platforms: [linux, macos, windows]
  tags: [wiki, curator, knowledge-base, okf]
  hermes:
    category: research
    related_skills: [obsidian, arxiv]
---

# Wiki Curator

## Overview

The curator is the operational half of Lumen. It turns memory-source records into conservative Markdown wiki updates, and it lints the wiki for structural decay. It never calls providers, never deletes pages, and never overwrites operator-confirmed facts.

Pair it with `lumen:wiki` for methodology (OKF frontmatter, ingest/query/lint procedures). This skill is the CLI and adapter layer.

## When to Use

Use this skill when the user wants to:

- Ingest recent memory into the wiki (`run`) or preview that ingest (`report`)
- Lint or validate wiki structure
- Search wiki pages by keyword, alias, or tag
- Configure which memory source the curator reads

## Wiki Location

Resolve the wiki path in this order:

1. `--wiki` CLI override
2. `paths.wiki_path` in plugin config (`shared/config/lumen.yaml` or `--config`)
3. `$WIKI_PATH` environment variable
4. Default `~/wiki`

## Plugin config (`lumen.yaml`)

Default file: `<plugin>/shared/config/lumen.yaml`. Override with `--config` or `LUMEN_CONFIG`.

```yaml
paths:
  wiki_path: ~/wiki          # null → $WIKI_PATH → ~/wiki

curator:
  timezone: Asia/Singapore
  max_write_pages: 20        # 0 or negative disables the cap
  memory_source: sessions    # sessions | auto | json-file | mnemosyne | none
```

`auto` prefers `sessions` when a readable Hermes `state.db` exists (the conversation history is the ground truth; Mnemosyne holds derived notes), then Mnemosyne when `hermes` is on `PATH`, falling back to the json-file adapter if the export fails. `none` disables ingest (file-only lint/search still work).

## Adapter layer

`${HERMES_SKILL_DIR}/scripts/adapters.py` is the read-only memory boundary. Adapters emit `SourceItem` records (`source_id`, `source_kind`, `title`, `text`, `timestamp`, `tags`, `people`, `entities`, `projects`, `raw`). Nothing writes back to a memory store.

| Adapter | Source | Notes |
|---|---|---|
| `sessions` | Hermes `state.db` (conversation history) | Read-only SQLite; user messages paired with the first assistant reply; gateway-origin JSON envelopes stripped. Default source. |
| `json-file` | `<wiki>/.knowledge/memory.json` | Tolerant record shapes (`records` map or list). Missing file → `[]`. |
| `mnemosyne` | `hermes mnemosyne export --output <tmp>` | Parses `working_memory` + `episodic_memory`. Subprocess failure → `[]`. |
| `none` | empty | Explicit opt-out. |

**Record fields.** `people` / `entities` / `projects` take a list for several names; a plain string is one name (`"Acme, Inc."` stays one entity). `tags` may be a list or a comma-separated string. Records without an `id` get a content-derived id (`memory_<digest>` of timestamp and text), so reordering or inserting records does not re-ingest them. When a record names no people/entities/projects, capitalised words in its title/text are used as entity hints; a sentence-initial word ("Met with…", "Sent…") only counts if the same word also appears capitalised mid-sentence, and the `Untitled` placeholder title is never scanned.

**Extension point (`generic-json`).** Any provider that can emit the json-file `memory.json` shape (a `records` mapping or a list of record objects, with tolerant people/entities/projects keys) can be dropped in as `<wiki>/.knowledge/memory.json` and selected with `memory_source: json-file`. A dedicated `generic-json` adapter that takes an arbitrary export path is the documented next step; do not add provider-specific imports.

## CLI

Script: `${HERMES_SKILL_DIR}/scripts/wiki_curator.py` (Hermes substitutes `${HERMES_SKILL_DIR}` with this skill's directory, so the path works from any cwd). Run with system `python3` (stdlib + PyYAML).

```bash
CURATOR="${HERMES_SKILL_DIR}/scripts/wiki_curator.py"

python3 "$CURATOR" run --since 24h          # ingest (writes wiki pages)
python3 "$CURATOR" run --since 24h --dry-run
python3 "$CURATOR" report --since 7d        # planned changes, no writes
python3 "$CURATOR" validate                 # lint; exit 1 on ERROR
python3 "$CURATOR" lint                     # same checks
python3 "$CURATOR" lint --summary           # counts only
python3 "$CURATOR" search "Acme" --format json --limit 10
python3 "$CURATOR" search "Acme" --format text --wiki ~/wiki
```

Global flags: `--config <lumen.yaml>`, `--wiki <path>` (also accepted after the subcommand).

`--since` accepts `90m`, `24h`, `7d`, `2w`; anything else is a usage error (exit 2). Runtime errors such as a wiki subdirectory that is a symlink out of the wiki print `error: …` and exit non-zero.

**Read-only vs mutating:** `lint`, `validate`, `report`, and `search` are read-only. `run` writes. `run --dry-run` previews. The curator never deletes pages.

## Conservative write policy

- Create or update people / project / entity / daily pages from source items only
- Preserve operator-confirmed facts; append observations with `[source: id]`
- Refresh only the `<!-- lumen:auto:start -->` … `<!-- lumen:auto:end -->` block of `index.md` and `overview.md` (hand-written content outside the markers is preserved; a file without markers gets a block appended); append `log.md`
- Record text, titles and names are flattened to one line with `[source:` / `[[` / leading `#` neutralised, so memory content cannot forge sections, source markers or links
- Never overwrite an existing page `title` or `created` value
- Skip an existing page whose YAML frontmatter does not parse: it is left byte-for-byte unchanged, a `skip` line naming the page appears in the run report (and a warning on stderr), and the source is retried on the next run once the page is fixed
- Rewritten files keep their existing permission bits; new files get `0666 & ~umask`
- Cap source items per run at `curator.max_write_pages` (default 20; 0 or negative disables the cap)
- Backup the wiki tree to `<wiki>/.lumen/backup/<timestamp>/` before large batches (>5 items). `.lumen/` is excluded from index and overview regeneration.

## OKF v0.2

Every curated `.md` page needs parseable YAML frontmatter with a non-empty `type` field. See `lumen:wiki` for the full schema. The curator assigns `seq` on create and preserves `aliases` / `relations`.

## Lint checks

- Missing or malformed frontmatter (ERROR)
- Missing `type` (ERROR)
- Broken `[[wikilinks]]` (WARN)
- Duplicate titles (WARN)
- Pages absent from `index.md` (WARN)
- Orphans with no inbound links (INFO)
- Stale pages (updated >90 days) (INFO)

## File naming

Lowercase hyphenated ASCII slugs: `acme-logistics.md`. Accents are folded (`Zoë` → `zoe.md`); a name with no ASCII letters or digits (`张伟`) gets `untitled-<first 8 hex of sha256(name)>.md`, stable across runs and distinct per name. Wikilinks use the page title, so `[[张伟]]` resolves. Avoid generic names like `notes.md`.

## Common pitfalls

1. Skipping orientation (`purpose.md`, `SCHEMA.md`, `index.md`, recent `log.md`)
2. Creating duplicate entity pages without searching first
3. Dumping raw notes as curated knowledge
4. No frontmatter / missing `type`
5. Unlinked pages that lint later reports as orphans

## Verification checklist

- [ ] Wiki path resolved from plugin config, then `$WIKI_PATH`, then `~/wiki`
- [ ] `memory_source` matches the host install (`auto` / `json-file` / `mnemosyne` / `none`)
- [ ] `run --dry-run` reviewed before a mutating `run`
- [ ] Lint reports file paths and severity
- [ ] Query answers cite wiki pages
Pliki w paczce (4)
  • SKILL.md 8 KB
  • scripts/adapters.py 27 KB
  • scripts/config_loader.py 9 KB
  • scripts/wiki_curator.py 77 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · moonlight-lupin/agent-skills100MIT
Embassy-of-the-Free-Mind/sourcelibrary-v2100AGPL-3.0
wonsukchoi/domain-experts100MIT

Migawka bazy z 13.11.2026 · wersja paczki c91b0789a2dd (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

  • 95wiki
    Buduje i obsługuje wiki w stylu Karpathy'ego: powiązaną bazę wiedzy w Markdown, do której dodaje się treści, zadaje pytania i sprawdza spójność.
  • 100migrate
    Podnosi schema_version skarbca wiki do bieżącej wersji wtyczki wiki-curator, stosując migrację między wersjami.
  • 90lint-wiki
    Sprawdza stan wiki podcastu, wyszukuje błędy i sprzeczności oraz poprawia je po dużym imporcie lub na żądanie.
  • 100lint
    Sprawdza kondycję wiki projektu: nieaktualne strony, strony osierocone i sprzeczności w treści, w ramach kontroli field-guide lint.
  • 90wiki-lint
    Sprawdza zdrowie wiki: niepoparte twierdzenia, martwe linki, rozjazdy indeksu i daty, a potem naprawia i podaje wynik od 0 do 100.
  • 90llm-wiki-lint
    Sprawdza strukturę i logikę paczki LLM Wiki OKF względem SPEC.md i AGENTS.md: naruszenia schematu, sprzeczności, nieaktualne twierdzenia, strony osierocone i zepsute wikilinki.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.