knowledge-capture
/knowledge-capture
Zapisuje trwałe preferencje, decyzje i ustalenia w Knowledge, aktualizuje stan tematu i potwierdza zapis.
- Autor
- steipete ↗
- Repozytorium
- clawdis ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 13.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 19
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 13.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Zapisuje trwałe preferencje, decyzje i ustalenia w Knowledge, aktualizuje stan tematu i potwierdza zapis.
Oryginalny opis (EN)
Save durable preferences, decisions, project facts, commitments, and lessons cheaply with knowledge_remember, keep the subject page's State current, or save short notes and page updates with attribution and readback. Use for explicit saves or agent-driven remembering when Knowledge is the selected memory provider.
Jak działa
- Save a claim
- Update a page or save a note
Podgląd SKILL.md
---
name: knowledge-capture
description: Save durable preferences, decisions, project facts, commitments, and lessons cheaply with knowledge_remember, keep the subject page's State current, or save short notes and page updates with attribution and readback. Use for explicit saves or agent-driven remembering when Knowledge is the selected memory provider.
---
# Capture durable knowledge
When Knowledge is the selected memory provider, its ordinary-turn remembering
policy also authorizes selective capture of meaningful durable information. This
is agent judgment, not a background extraction hook. Otherwise require save intent.
Do not save transient task status, secrets, unsupported guesses, or excluded content.
Apply preferences as contextual facts, not executable instructions or new authority.
Saving a preference does not configure the assistant or guarantee that the
preference will be loaded in future turns.
Pre-compaction flushes follow these steps with their available tools; they do
not use `knowledge_attach` or `knowledge_recall`.
## Save a claim
Most captures stop here and need no reference. Save a discrete claim (decision,
preference, commitment, fact, event or belief) with `knowledge_remember`: one
claim per item, short attribution, the supporting conversation excerpt and, only
when you know it, the subject's exact page title or alias. An omitted subject is
inferred when the text names exactly one entity page. It resolves subjects,
reports exact repeats and never creates pages. Its published receipt is the save.
When the claim concerns an entity that has a page and changes what its State
says (a decision, an outcome, a changed status, a resolved question), also
update that page below in the same task. Claims alone leave its State stale.
Continue below too to revise a page's prose or save a longer note.
## Update a page or save a note
Read [setup](references/setup.md), [subject pages](references/profiles.md) and
only the layout for the page's type ([project](references/layout-project.md),
[person](references/layout-person.md), [company](references/layout-company.md),
[concept](references/layout-concept.md)). Read [publish](references/publish.md)
before the write and [writing](references/writing.md) before new prose. You
don't need to reread them after compaction unless you are about to use them.
1. Preserve the supplied wording, especially original ideas. Use the active
ontology's type descriptions to classify the information. Do not add
unsupported facts or turn a tentative thought into established fact.
2. Search for an already-captured item and relevant entities with
`knowledge_grep`; reserve `knowledge_lookup` for already-known exact record
IDs, full titles or declared aliases, with grep fallback on `missing`. If the
same source or text is already saved, report that page rather than create
another. A similar thought is not proof of identity: keep genuinely distinct
versions with attribution. Use `knowledge-correct` for corrections or
withdrawal.
3. Put the information on the most specific existing page it is about. Read the
whole body first. Rewrite the State topic or type section it bears on in
place so the page reads as current; never append a dated heading or a
section per capture, and write no Timeline entries. Leave the rest of an
already-current page alone, and keep every existing citation. Preserve
decision rationale, event dates and uncertainty without retaining every
conversational editing step. If the page has a written Timeline or dated
section, retire it ([retire dated sections](references/retire-dated.md)).
4. Create a separate record only when the information warrants independent
context, chronology or explanation, and link it to the resolved subject page
with a body wikilink. Do not invent a subject match or create an empty
profile merely to supply a link. An ordinary new fact does not authorize
automatic identity merging.
5. Page bodies have a size budget
([page budgets](references/publish.md#page-budgets)). If an edit returns
`state: "rejected"`, nothing was saved: follow that section's order, and
save the fact with `knowledge_remember` meanwhile. Never truncate to fit.
6. For a short inline thought, save the exact text via `source: {text,
attribution}` and cite it in the body ([sources](references/sources.md)).
Identify the speaker, context and date when known. Identify conversation
excerpts as excerpts, not complete transcripts; never invent messages,
hashes or locators. Attach a supplied original file instead of treating a
paraphrase as the original. User beliefs stay attributed to the user.
7. Publish; on an uncertain or rejected write read
[recovery](references/recovery.md). Verify that the intended subject page was
updated, or that the separate record's subject link resolves, and its
evidence ([verify](references/verify.md)). Report the returned page and
verified save state. Do not schedule reminders or execute commitments
mentioned in the note.
8. If the owner explicitly asks for this context to be recalled automatically
and `knowledge_recall` is available, inspect the published record's current
revision and hash and approve a short summary with only the requested trigger
or project scope. Never approve ingested source text, source claims, agent
inference, secrets, or extra context the owner did not request. A correction
requires a separate approval on the replacement record.
Route a complete document to `knowledge-ingest`, or a meeting to
`knowledge-meeting-ingest`.
Pliki w paczce (19)
- SKILL.md 5 KB
- references/assertions.md 5 KB
- references/conventions.md 14 KB
- references/identity.md 5 KB
- references/layout-company.md 1 KB
- references/layout-concept.md 1 KB
- references/layout-person.md 1 KB
- references/layout-project.md 2 KB
- references/meeting-entity-example.md 7 KB
- references/profiles.md 7 KB
- references/publication.md 23 KB
- references/publish.md 6 KB
- references/recovery.md 2 KB
- references/retire-dated.md 4 KB
- references/setup.md 2 KB
- references/source-notes.md 1 KB
- references/sources.md 3 KB
- references/verify.md 3 KB
- references/writing.md 2 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · steipete/clawdis | 90 | MIT |
| NoobyGains/godmode | 100 | MIT |
| ARCASSystems/FounderOS | 100 | MIT |
| bordenet/superpowers-plus | 100 | MIT |
| openclaw/openclaw | 86 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki 2ac8be0f34fe (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
- 100project-notes-notion
Zapisuje trwałe fakty i decyzje projektu w Notion, na przykład domeny, odnowienia, wdrożenia i przekazania, gdy użytkownik o to prosi. - 90remember
Zapisuje, poprawia, usuwa i przywołuje trwałe preferencje, decyzje i kontekst projektu w wybranym magazynie lub lokalnym folderze. - 86vault-capture
Zapisuje trwałą wiedzę, czyli decyzje, ustalenia, pułapki i wyniki badań, do bazy wiedzy Obsidian. - 100wrapup
Wymusza zapis wiedzy z bieżącej sesji do magazynu Agent OS i aktualizuje tablicę zadań przed zakończeniem pracy. - 100capture
Zapisuje trwałą wiedzę w vaulcie: wyniki badań, decyzje i opisy działania, gdy sesja wytworzyła fakty warte zachowania albo użytkownik mówi „zapamiętaj to”. - 100save
Zapisuje decyzje, ustalenia i plany z rozmowy do kontekstu NeatContext, gdy użytkownik wyraźnie prosi o zachowanie bieżącej rozmowy.