knowledge-capture skill
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.
Is the knowledge-capture skill safe?
Clean: nothing in its files matched our rules. We read 19 files in the folder on 2026-11-14.
No findings.
Install the knowledge-capture skill
A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.
git clone --depth 1 https://github.com/openclaw/openclaw.git /tmp/openclaw mkdir -p ~/.claude/skills cp -r /tmp/openclaw/extensions/knowledge/skills/knowledge-capture ~/.claude/skills/knowledge-capture
In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub
The instructions your agent would load
SKILL.md as published, without the frontmatter. Read it on GitHub
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 knowledgeattach or knowledgerecall.
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, subject pages and only the layout for the page's type (project, person, company, concept). Read publish before the write and writing before new prose. You don't need to reread them after compaction unless you are about to use them.
ontology's type descriptions to classify the information. Do not add unsupported facts or turn a tentative thought into established fact.
- Preserve the supplied wording, especially original ideas. Use the active
knowledgegrep; reserve knowledgelookup 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.
- Search for an already-captured item and relevant entities with
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).
- Put the information on the most specific existing page it is about. Read the
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.
- Create a separate record only when the information warrants independent
(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.
- Page bodies have a size budget
attribution} and cite it in the body (sources). 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.
- For a short inline thought, save the exact text via source: {text,
recovery. Verify that the intended subject page was updated, or that the separate record's subject link resolves, and its evidence (verify). Report the returned page and verified save state. Do not schedule reminders or execute commitments mentioned in the note.
- Publish; on an uncertain or rejected write read
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.
- If the owner explicitly asks for this context to be recalled automatically
Route a complete document to knowledge-ingest, or a meeting to knowledge-meeting-ingest.
More skills from openclaw/openclaw
- A1passwordSet up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
- Aacp-routerRoute plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Grok Build, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation. Codex chat binding defaults to the native Codex app-server plugin unless ACP is explicit or background spawn needs ACP.
- Aadd-model-providerAdd and live-prove a model provider with non-interactive config one-liners, without exposing credentials.
- Aagent-transcriptRequested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.
- Aapple-notesCreate, view, edit, delete, search, move, or export Apple Notes via the memo CLI on macOS.
- Aapple-remindersList, add, edit, complete, or delete Apple Reminders and reminder lists via remindctl.
- Aauto-qaRun OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.
- AautoreviewStructured code review through the shared OpenClaw agent-skills installation.
- Abear-notesCreate, search, and manage Bear notes via grizzly CLI.
- Ablock-kitUse proactively for structured or interactive Slack replies, and when asked to author or validate native Slack Block Kit JSON.
- AblogwatcherMonitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
- AblucliBluOS CLI (blu) for discovery, playback, grouping, and volume.