- name
SKILL.md
File skill tetap berada di repositori penerbit.
Tempel perintah yang disalin di terminal. Perintah itu memasang SKILL.md ini ke agen tersebut.
npx skills add Ar9av/obsidian-wiki --skill wiki-agent -a cursor -yTempel perintah yang disalin di terminal. Perintah itu memasang SKILL.md ini ke agen tersebut.
npx skills add Ar9av/obsidian-wiki --skill wiki-agent -a claude-code -yTempel perintah yang disalin di terminal. Perintah itu memasang SKILL.md ini ke agen tersebut.
npx skills add Ar9av/obsidian-wiki --skill wiki-agent -a codex -yTempel perintah yang disalin di terminal. Perintah itu memasang SKILL.md ini ke agen tersebut.
npx skills add Ar9av/obsidian-wiki --skill wiki-agent -a grok -yKirim pesan yang disalin di chat Grok Bot. Bot mengambil SKILL.md ini dari GitHub dan menambahkannya ke skill yang dipakai bersama oleh semua Bot Anda.
Install this skill: https://github.com/Ar9av/obsidian-wiki/tree/HEAD/skills/wiki-agentDari penerbit
You are doing a query-driven targeted ingest from one specific AI agent's raw conversation history. The user is typically working in a different agent right now and wants to pull in context from another agent's past sessions.
This is not bulk ingest. You find sessions about a specific topic, extract the relevant blobs, distill them into the wiki, and return a synthesized answer the user can act on immediately.
Parse the invocation to determine the target agent and optional query:
If no query is given, default to recent sessions mode: ingest the last 5 unprocessed sessions from that agent and return a summary of what was found. This is equivalent to a focused wiki-history-ingest for that agent only.
Writing profile: Before drafting or rewriting natural-language Markdown, read and apply the Writing Profile Resolution section in llm-wiki/SKILL.md. Framework schema, provenance, safety, and operation-specific requirements take precedence.
WRITING.md preferences apply only to newly drafted or rewritten natural-language Markdown; preserve source content and structured records.
llm-wiki/SKILL.md (inline @name override → walk up CWD for .env → global config → prompt setup). This gives OBSIDIAN_VAULT_PATH.$OBSIDIAN_VAULT_PATH/.manifest.json → know what's already ingested.$OBSIDIAN_VAULT_PATH/hot.md if it exists → warm context on recent wiki activity.If the history root doesn't exist, stop and tell the user: "No <agent> history found at <path>. Have you run <agent> on this machine? You can set a custom path with <CONFIG_VAR> in .env."
Use the cheapest index source for each agent — don't open session files until you know which ones are relevant.
Primary index: ~/.claude/projects/ (directories = projects, files = sessions)
Session files: ~/.claude/projects/*/*.jsonl
Desktop index: find ~/Library/Application Support/Claude/local-agent-mode-sessions -name "local_*.json"
Signal fields: sessionId, cwd, startedAt, title (in local_*.json)
Build a list of sessions: {path, project_dir, modified_at, already_ingested}.
Primary index: ~/.codex/session_index.jsonl
Session files: ~/.codex/sessions/**/rollout-*.jsonl
Signal fields: thread_id, name/title, updated_at (in session_index.jsonl)
Read session_index.jsonl as the inventory. Each line: {thread_id, name, updated_at}. Map thread IDs to rollout files by matching directory names.
Primary index: ~/.hermes/memories/*.md (fast to scan)
Session files: ~/.hermes/sessions/**/*.jsonl
Signal fields: file names, memory titles, first 3 lines of each memory
Scan memory filenames first (they're often titled by topic). Fall back to session listing.
Primary index: ~/.openclaw/workspace/memory/MEMORY.md (structured long-term memory)
Daily notes: ~/.openclaw/workspace/memory/YYYY-MM-DD.md
Session index: ~/.openclaw/agents/*/sessions/sessions.json
Session files: ~/.openclaw/agents/*/sessions/*.jsonl
Read MEMORY.md sections first — it's the pre-compiled summary of everything. Daily notes give recency signal.
Primary index: session filenames / directory listing
Session files: varies by client (VS Code: ~/.copilot/sessions/*.jsonl or similar)
Signal fields: session timestamps, file names
Primary index: ~/.pi/agent/sessions/--<cwd>--/ directories
Session files: ~/.pi/agent/sessions/--<cwd>--/<timestamp>_<uuid>.jsonl
Signal fields: cwd (decoded from dir name), session_info.name, timestamp in filename
Scan session directories first. Decode --<cwd>-- to get the working directory. Read the first line (session header) and any session_info entries for the session name. No separate index file — the filesystem is the index.
If a query was given, score each session in the inventory without opening full session files:
Name/title match — does the session name or thread title contain the query terms? Score: +3
CWD/project match — does the working directory suggest the right project? Score: +2
Recency — apply exponential time decay with a 90-day half-life, as a multiplier on the match score rather than a bonus added to it:
base = name_match(3) + cwd_match(2)
score = base * (0.35 + 0.65 * 0.5 ** (age_days / 90))
The 0.35 floor is deliberate: an old session that matches the query exactly must still outrank a recent one that barely matches, or the skill can never answer "how did I first solve this?". This is the same decay session-brain uses, so the two skills rank consistently.
Already ingested — if this session was previously ingested and the wiki page already covers the query (check hot.md + index.md), flag as "covered" but still show in results
Select the top 3–5 sessions by score. If no query was given, select the 5 most recent unprocessed sessions.
Open each selected session file and extract only the content relevant to the query. Do not read the full session if it's large — use targeted extraction.
Claude (JSONL conversation):
{role, content, timestamp, ...}rg -i "<query terms>" <session.jsonl> to find the relevant linesCodex (rollout JSONL):
{type: "session_meta|turn_context|event_msg|response_item", ...}type: "event_msg" (user turns) and type: "response_item" (model output)rg -i "<query terms>" <rollout.jsonl>turn_context preceding the match)session_meta events (operational metadata, not knowledge)Hermes (memory files + session JSONL):
rg -i "<query terms>" + surrounding windowOpenClaw (MEMORY.md + daily notes + session JSONL):
MEMORY.md: grep for section headers containing query terms → extract that sectionCopilot (session JSONL):
Pi (structured JSONL with tree layout):
{type, id, parentId, timestamp, message?, ...}id, find leaf (last entry with no children), walk parentId to rootrg -i "<query terms>" <session.jsonl> to find matching entriestoolCall blocks inside assistant messages reveal what was actually done — extract these even without keyword matches if they're in the relevant windowcompaction and branch_summary entries when available — they're pre-synthesized summariesthinking content blocks (noise) and model_change / thinking_level_change entriesFor each extracted blob, determine where it belongs in the wiki:
index.md and page frontmatter for the topic. If yes, update the existing page rather than creating a new one.llm-wiki/SKILL.md):
skills/concepts/entities/synthesis/---
title: <topic>
category: skill|concept|entity|synthesis
tags: [tag1, tag2]
sources: [<agent>://<path/to/session>]
created: <date>
updated: <date>
confidence: high|medium|low
lifecycle: stable|draft
---
Set sources with the agent prefix so memory-bridge can find it later.index.md.Distillation rules (same as all ingest skills):
After ingesting, immediately synthesize and return an answer from the newly ingested + existing wiki content:
## From <agent> history: "<query>"
**Found in:** <N> sessions (<session names/titles>)
**Key insights:**
<Synthesized answer — 3–5 bullet points of the most useful knowledge>
**Wiki pages updated/created:**
- [[page-name]] — <what was added>
- [[page-name]] — <what was added>
**Sessions ingested:**
| Session | Date | Relevance |
|---------|------|-----------|
| <name> | <date> | <one-line why it was selected> |
**Gaps:** <What the sessions didn't cover that might be relevant>
If a query was given but no relevant sessions were found, say so explicitly: "No sessions about '' found in <agent> history. The most recent sessions covered: <list topics from last 3 sessions>."
Update .manifest.json for each session file processed:
{
"<path>": {
"ingested_at": "<now>",
"source_type": "<agent>_conversation",
"modified_at": "<file mtime>",
"pages_created": [...],
"pages_updated": [...]
}
}
One locked call updates the log, the index, and the hot cache:
obsidian-wiki memory sync WIKI-AGENT \
agent=<agent> query="<query>" \
sessions_searched=<N> sessions_ingested=<M> \
pages_created=<X> pages_updated=<Y> \
--takeaways "<one line: what was pulled in and what it changes>" --expect-takeaways-sha256 "$TAKEAWAYS_REVISION"
Never hand-edit index.md, log.md, or hot.md — the command takes the lock that keeps a parallel writer from dropping your update.
See skills/llm-wiki/references/MEMORY.md for the full procedure.
These are the primary use cases this skill is designed for:
"I'm on Codex. What did I figure out about X in Claude?"
→ /wiki-claude "X" — finds Claude sessions about X, ingests them, returns the answer
"I solved a bug in Hermes last week. I need that context now in Claude Code."
→ /wiki-hermes "bug description" — surfaces and ingests the Hermes session
"What are all the approaches I've tried for X across all my tools?"
→ Run /wiki-claude "X", /wiki-codex "X", /wiki-hermes "X" in sequence — each ingests its slice, the wiki accumulates the cross-agent picture, then /memory-bridge diff shows what each tool uniquely contributed
No query — just "catch me up on recent Codex work"
→ /wiki-codex — ingests last 5 Codex sessions and returns a summary
"I'm on Claude Code. What did I figure out about X in Pi?"
→ /wiki-pi "X" — finds Pi sessions about X, ingests them, returns the answer
No query — just "catch me up on recent Pi work"
→ /wiki-pi — ingests last 5 Pi sessions and returns a summary
QMD is a search index, not the source of truth. If $QMD_WIKI_COLLECTION is empty or unset, skip this step. Run it only after this skill has written or rewritten vault markdown. If QMD refresh fails, do not roll back the vault changes; report the QMD status separately.
Use $QMD_CLI if set; otherwise use qmd.
${QMD_CLI:-qmd} update
If the output says vectors are needed or embeddings may be stale, run:
${QMD_CLI:-qmd} embed
Verify the collection with either:
${QMD_CLI:-qmd} ls "$QMD_WIKI_COLLECTION"
or, when a specific page path is known:
${QMD_CLI:-qmd} get "qmd://$QMD_WIKI_COLLECTION/<page>.md" -l 5
Record one of:
QMD refreshed: update + embed + verifiedQMD refreshed: update only + verifiedQMD skipped: QMD_WIKI_COLLECTION unsetQMD skipped: qmd CLI unavailableQMD failed: <short error summary>Before explicit takeaway replacement, read/reconcile the full current Key Takeaways and obtain TAKEAWAYS_REVISION from hot.takeaways_sha256 in memory status --json (llm-wiki/references/MEMORY.md). Preserve still-valid owner conclusions. Omit --takeaways for mechanical bookkeeping; stale revisions require review, not blind retry.
>
---name: wiki-agentdescription: >---# skills/wiki-agent/SKILL.mdFAQ
Unduh skills/wiki-agent/SKILL.md dari penerbit, atau salin path-nya dan buka repositori. PlugMCP hanya mendaftar skill ini dan tidak meng-host filenya.
Penerbit menyimpannya di https://github.com/Ar9av/obsidian-wiki.
Claude, Cursor, Codex, dan Grok Build bisa membaca SKILL.md yang Anda tambahkan dari repositori penerbit. Grok Bot memasangnya saat Anda mengirim tautan folder GitHub skill tersebut di chat.