dexio-wiki-sharedRules for an LLM wiki that several agents, machines or people write to: read before writing, detect concurrent edits, prefer small edits to rewrites, attribute every change with a note, derive the index and log instead of hand-editing shared files, and keep scoped content where only the right readers see it. Use when more than one agent or person maintains the same wiki, or when setting up a wiki for a team or an agent fleet.
Install via ClawdBot CLI:
clawdbot install dexio/dexio-wiki-sharedGenerated Oct 7, 2026
A team runs five autonomous agents that continuously ingest papers, contract notes, and market data into one canonical Obsidian wiki. Without shared-writer rules, agents overwrite each other's work and silently discard findings, so this skill enforces read-before-write, version-based conflict detection, and small surgical edits. The result is a trustworthy knowledge base where every claim traceable to a specific agent and timestamp.
A boutique consultancy has several consultants and their AI assistants writing into a common wiki that holds client deliverables, meeting notes, and playbooks. Scope rules keep each client's sensitive details in isolated folders so pages never merge across boundaries, and attribution ensures every edit is reviewed by a second consultant. Draft-then-promote workflows protect anything customer-facing.
An engineering org has developers, CI bots, and AI coding agents all editing a shared markdown wiki that documents APIs, decisions, and runbooks. The skill prevents commit races by pulling before push, discourages full-page regeneration in favor of focused edits, and moves index and log generation to a scheduled job running `wiki-lint`. This eliminates merge conflicts on shared catalog files and keeps the history reviewable.
A mid-size company wants a single internal wiki shared across engineering, sales, and support, each with different access needs and wildly different editing habits. Explicit scope and tenant fields plus separate access-controlled folders prevent private HR or client information from leaking into general pages. Scheduled `wiki-review` by a non-authoring agent catches drift and factual errors weekly.
A research lab has rotating students, visiting scholars, and AI research assistants all contributing to a shared lab notebook wiki about experiments and datasets. Draft status gates unverified results from being promoted to official findings, and a lab owner is named in frontmatter for each project page so restructuring is deliberate. Concurrent edit detection prevents a student's overnight analysis from being silently overwritten.
A hosted service provides the shared wiki with conditional writes, per-change version history, agent fields, and access scopes built in. It sells subscriptions to teams and agent fleets that want pull-before-write discipline handled by the platform rather than by each writer. Revenue is per-seat and per-agent monthly pricing with usage tiers.
The core wiki-lint, wiki-review, and conflict-resolution utilities are open source under MIT, and the company monetizes a hosted backend that provides canonical sync, version enforcement, and scheduled lint jobs. Teams adopting the free CLI graduate to the paid hosted layer when they add more writers. Revenue combines enterprise support contracts with cloud hosting fees.
A B2B product bundles the shared-writer rules, scoped folders, agent attribution, and scheduled lint and review pipelines into a governance offering for large organizations running many AI agents. It integrates with existing git and wikis and provides compliance-grade audit trails of who wrote what. Revenue comes from annual enterprise licenses based on writer and agent counts.
💬 Integration Tip
Start by pointing every writer's instructions file at one shared schema page, then enable conditional writes (or pull-before-push) and a scheduled wiki-lint job before adding more agents. Move index and log generation out of individual writers early, since that single change removes most parallel-edit conflicts.
Manage a personal knowledge base by adding, searching, organizing, and reviewing articles, links, and notes with tags and natural language queries.
Generate a daily work report by automatically discovering all git repositories the user worked on, collecting commit logs across all branches, and summarizin...
日记引导助手。每日写作引导、感恩日记、反思日记、晨间日记、晚间总结、周总结模板。Journal prompts for daily writing, gratitude, reflection, morning pages, evening review, weekly summary. 日记、写作、反思、感恩。
Use when maintaining RDR2 (Red Dead Redemption 2) playthrough notes — logging an acquisition ("acquired X", "got N gold bars", "finished X"), answering in-game location/crafting questions, or reviewing the notes for duplicate or stale info. Triggers on RDR2, Red Dead Redemption, playthrough, legendary animal, talisman, trinket, valerian root, gold bar, horse, weapon, berry.
Use when a sales rep already has a customer who has expressed some need (from outreach follow-up, account-landing research, customer-initiated contact, or meeting notes) and needs to structurally validate whether that need is real, urgent, whose pain it actually is, and whether it matches the team's capability — before pushing to ROI proofing or buying-intent assessment. Triggers: '验证一下这个需求是不是真的', '需求真不真', '客户说痛但我不确定', '这个客户值不值得跟', '客户说会考虑但是真的吗', '谁拍板', '现有方案是什么', '切换成本', 'need validation', 'pain point validation', 'is this a real need', 'verify customer need'. Do NOT use for: scoring leads at line-item level, building target-customer profiles, calculating ROI, overall buying-intent scoring, opportunity-stage assessment, or writing outreach/cold messages.
Microsoft OneNote integration. Manage Notebooks. Use when the user wants to interact with Microsoft OneNote data.