Agent skill

Knowledge Base Sync

by JetXu-LLM in JetXu-LLM/DocMason

Stage, incrementally refresh, validate, and publish the DocMason knowledge base from the local source corpus.

Apache-2.0Auto-check passedKnowledge Management

Install Knowledge Base Sync

skills CLI
$ npx skills add JetXu-LLM/DocMason --skill knowledge-base-sync -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JetXu-LLM/DocMason knowledge-base-sync --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JetXu-LLM/DocMason.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/canonical/knowledge-base-sync .claude/skills/knowledge-base-sync && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
knowledge-base-sync
GitHub stars
147
Token cost
~1.5k tokens
SKILL.md length
768 words
Files
2
Skills in repo
15
Repo updated
First seen
Licence
Apache-2.0

At a glance

Stage, incrementally refresh, validate, and publish the DocMason knowledge base from the local source corpus.

  • Works in 8 steps: Start with docmason status --json when… → Use docmason sync --json as the default… → Respect the control-plane result before… → …
  • Tasks that involve Knowledge bases
  • SKILL.md covers Required Capabilities, Procedure, Escalation Rules and Completion Signal, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Knowledge Base Sync is an agent skill from JetXu-LLM/DocMason. Stage, incrementally refresh, validate, and publish the DocMason knowledge base from the local source corpus.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `workflow.json`).

It sits in Knowledge Management, covering Knowledge bases. The repository describes itself as: DocMason is a repo-native agent that turns your complex office files into a local LLM knowledge base and your second brain. The repo is the app. Codex is the runtime. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Knowledge bases

Example prompts

  • “/knowledge-base-sync”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Start with docmason status --json when you need the current stage, pending actions, or control-plane state.
  2. Use docmason sync --json as the default build or refresh entry point.
  3. Respect the control-plane result before reasoning about later workflow steps.
  4. Treat successful sync as the deterministic truth-building path.
  5. If sync_status is valid or warnings, inspect hybrid_enrichment.
  6. Treat pending-synthesis as a compatibility or deliberate manual-mode state, not the normal operator destination.
  7. If validation still blocks publication after the deterministic sync path finishes, route to validation-repair, then rerun docmason sync…
  8. Return the final publication judgment to the main agent. Do not delegate final publication sign-off.

What it can do on your machine

Read from SKILL.md and the folder at commit 362417b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Knowledge Base Sync loads about 1.5k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 768 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from JetXu-LLM/DocMason at commit 362417b, republished under its Apache-2.0 licence (© JetXu-LLM). 768 words, ~1,467 tokens.

Download SKILL.mdSave it as .claude/skills/knowledge-base-sync/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
knowledge-base-sync
description
Stage, incrementally refresh, validate, and publish the DocMason knowledge base from the local source corpus.

Knowledge-Base Sync

Use this skill when the task is to build or refresh the DocMason knowledge base.

This is a top-level operator workflow. Ordinary users should not need to name knowledge-construction or validation-repair themselves.

Required Capabilities

  • local file access
  • shell or command execution
  • ability to inspect structured JSON output

If the agent cannot run local commands or inspect the resulting artifacts, stop and explain that the workspace cannot be synced reliably.

Procedure

  1. Start with docmason status --json when you need the current stage, pending actions, or control-plane state.
  2. Use docmason sync --json as the default build or refresh entry point.
    • let sync classify the physical cause before staging
    • zero-delta and foreground interaction-promotion-only checks return the current legal truth without full staging, validation, or publication; pending interaction promotion stays deferred maintenance rather than an answer-critical invalidation
    • for a source delta, preserve source-scoped transactional staging, cached validation for unchanged sources, compact global checks, and the existing atomic single-current publish model; do not improvise a parallel full-copy or publication path
    • use the reported cause, dirty/reused counts, phase timings, cache hits/misses, and physical clone/copy telemetry when diagnosing performance or unexpected work
    • keep workspace commands sequential while the sync lease is active
    • do not overlap status, sync, retrieve, trace, or validate-kb against the same workspace
  3. Respect the control-plane result before reasoning about later workflow steps.
    • if sync_status=awaiting-confirmation, surface the confirmation prompt and continue with docmason sync --yes --json
    • if sync_status=waiting-shared-job, treat the existing shared sync job as the legal owner and wait or retry rather than starting a second path
    • if sync_status=action-required, surface the blocker directly
      • when the blocker is missing sync capability, route the operator to prepare
      • when the blocker is a repairable Office machine-baseline gap and the host can provide Full access, continue through docmason prepare --yes --json and then resume the same sync task instead of stopping at a passive blocker report
  4. Treat successful sync as the deterministic truth-building path.
    • detect source changes
    • rebuild or reuse staged evidence
    • apply safe staged repairs
    • validate
    • publish to knowledge_base/current
  5. If sync_status is valid or warnings, inspect hybrid_enrichment.
    • hybrid_enrichment describes whether deterministic sync left a remaining multimodal semantic gap
    • if mode is not-needed or covered, stop and return the publication result
    • if the sync payload also includes lane_b_follow_up.work_path, open that governed work packet first and treat it as the authoritative next step for this sync state
      • lane_b_follow_up is the bounded sync-time follow-up packet for that current staging state
    • when that governed packet is present, do not consume the broad queue blindly; only fall back to hybrid_work_path when no bounded packet was handed off
      • hybrid_work_path is the broader staged queue and is only the fallback when no bounded packet was handed off
    • if mode is candidate-prepared or partially-covered and no governed packet path was handed off, treat hybrid_work_path as the authoritative hard-artifact queue
    • do not improvise a second sync path or rewrite deterministic sidecars
    • write only additive semantic_overlay/ sidecars for units you can support honestly, then rerun docmason sync --json
  6. Treat pending-synthesis as a compatibility or deliberate manual-mode state, not the normal operator destination.
    • route to knowledge-construction only when that legacy or manual path is actually intended
    • rerun docmason sync --json after staged authoring completes
  7. If validation still blocks publication after the deterministic sync path finishes, route to validation-repair, then rerun docmason sync --json.
  8. Return the final publication judgment to the main agent. Do not delegate final publication sign-off.
Show full SKILL.md (198 more words)Show less

Escalation Rules

  • Do not invent a second approval surface. The public approval command is docmason sync --yes.
  • If Office rendering is required but unavailable, stop only when the governed prepare path still cannot repair or install LibreOffice honestly; otherwise continue through that repair path first.
  • If staged or hybrid follow-up work requires per-source editing, that bounded work may be parallelized, but the final rerun and final judgment remain on the main path.
  • Do not silently trigger this workflow from an ordinary answer path without surfacing the governed state transition.

Completion Signal

  • The workflow is complete when docmason sync --json returns a final publication outcome for the current workspace state and any remaining hybrid state is either honestly covered, explicitly blocked, or explicitly surfaced through the governed follow-up packet and control-plane state.

Notes

  • Bare docmason sync remains the deterministic published-truth builder.
  • Shared-job reuse is part of the sync contract. Matching asks and operator sync commands should converge on one shared sync job, not parallel owners.
  • PDF rendering uses Python dependencies. PPTX, DOCX, and XLSX rendering requires LibreOffice soffice.
  • Interaction-derived memories may also be promoted through the same autonomous sync loop when the staged interaction path is relevant and supported.

© JetXu-LLM, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/canonical/knowledge-base-sync of JetXu-LLM/DocMason.

  • SKILL.md
  • workflow.json

Open the folder on GitHubat commit 362417b

Compare with similar skills

Knowledge Base Sync next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Knowledge Base Sync compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Knowledge Base Sync this skillJetXu-LLM/DocMason147—~1.5kAutomated safety check: PassApache-2.0
Capture Conversationoutline/outline41k—~474Automated safety check: PassCustom licence
Project CairniBlinkQ/project-cairn2352 repos~861Automated safety check: PassMIT
LLM Wiki Knowledge GraphEgonex-AI/Understand-Anything86k1 repos~1.5kAutomated safety check: PassMIT
Find And Citeoutline/outline41k—~537Automated safety check: PassCustom licence
Xhs Virtual Productchenjin-cmd/xhs-virtual-product727—~862Automated safety check: PassMIT

Similar skills

  • Capture Conversation

    outline/outline

    Save the current conversation, a decision, or a set of notes as a document in an Outline collection; use when the user wants to keep what was discussed in their knowledge base.

    41k GitHub stars~474 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Project Cairn

    iBlinkQ/project-cairn

    Standardize how an AI-collaboration project turns work into reusable knowledge.

    235 GitHub starsUsed in 2 repos~861 tokens
    Knowledge ManagementAuto-check passed
  • LLM Wiki Knowledge Graph

    Egonex-AI/Understand-Anything

    Detects a Karpathy-pattern LLM wiki and builds an interactive knowledge graph with entities, implicit relationships and topic clusters.

    86k GitHub starsUsed in 1 repo~1.5k tokens
    Knowledge ManagementAuto-check passed
  • Find And Cite

    outline/outline

    Answer questions from the Outline knowledge base with quotes and links to the source documents; use when the user asks what the team knows, documented, or decided about a topic.

    41k GitHub stars~537 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Xhs Virtual Product

    chenjin-cmd/xhs-virtual-product

    This skill helps plan, select, produce, and market Xiaohongshu (RED) virtual/digital products — templates, knowledge bases, test tools, study materials.

    727 GitHub stars~862 tokensUpdated 7 days ago
    Knowledge ManagementAuto-check passed
  • Openkb

    VectifyAI/OpenKB

    A skill your agent uses when the user asks about content in their OpenKB knowledge base — research topics, concepts compiled from their documents, cross-document synthesis — or mentions openkb, an…

    4.7k GitHub starsUsed in 1 repo~2k tokens
    Knowledge ManagementAuto-check: warnings

More from JetXu-LLM/DocMason

All 15 skills in this repo
  • Ask

    JetXu-LLM/DocMason

    Accept an ordinary user question inside a DocMason workspace, route it to the right inner workflow, and preserve conversation-native logs automatically.

    147 GitHub stars~7.1k tokensUpdated 8 days ago
    Auto-check passed
  • Adapter Sync

    JetXu-LLM/DocMason

    Generate or refresh the local Claude adapter surface for DocMason from canonical committed sources.

    147 GitHub stars~684 tokensUpdated 8 days ago
    Auto-check passed
  • Grounded Answer

    JetXu-LLM/DocMason

    Answer a user question through DocMason's canonical grounded workflow using retrieval, provenance tracing, render escalation, and a final answer-state check.

    147 GitHub stars~3.1k tokensUpdated 8 days ago
    Auto-check passed
  • Grounded Composition

    JetXu-LLM/DocMason

    Produce evidence-backed research, planning, drafting, or composition output from the published DocMason knowledge base while preserving provenance and answer-file discipline.

    147 GitHub stars~2.7k tokensUpdated 8 days ago
    Auto-check passed
  • Knowledge Construction

    JetXu-LLM/DocMason

    Write bilingual Phase 3 knowledge objects for staged DocMason sources from rendered evidence and extracted structure.

    147 GitHub stars~1.8k tokensUpdated 8 days ago
    Auto-check passed
  • Operator Eval

    JetXu-LLM/DocMason

    Run the hidden operator-only evaluation loop over local runtime/eval artifacts without exposing that surface in normal first-contact workflows.

    147 GitHub stars~433 tokensUpdated 8 days ago
    Auto-check passed

Questions about Knowledge Base Sync

What does Knowledge Base Sync do?

Stage, incrementally refresh, validate, and publish the DocMason knowledge base from the local source corpus. Knowledge Base Sync is an agent skill from JetXu-LLM/DocMason. Stage, incrementally refresh, validate, and publish the DocMason knowledge base from the local source corpus.

When should I use Knowledge Base Sync?

Knowledge Base Sync fits situations like: tasks that involve Knowledge bases.

How do I install Knowledge Base Sync in Claude Code?

Run `npx skills add JetXu-LLM/DocMason --skill knowledge-base-sync -a claude-code`. Or copy the skill folder (skills/canonical/knowledge-base-sync in JetXu-LLM/DocMason) into .claude/skills/knowledge-base-sync in your project. Claude Code loads it when a task matches its description.

How do I install Knowledge Base Sync in Codex?

Run `npx skills add JetXu-LLM/DocMason --skill knowledge-base-sync -a codex`. Or copy the skill folder (skills/canonical/knowledge-base-sync in JetXu-LLM/DocMason) into .agents/skills/knowledge-base-sync in your project. Codex loads it when a task matches its description.

Can I use Knowledge Base Sync in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JetXu-LLM/DocMason --skill knowledge-base-sync -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/knowledge-base-sync, .gemini/skills/knowledge-base-sync, .github/skills/knowledge-base-sync and .opencode/skills/knowledge-base-sync in your project.

What does Knowledge Base Sync need to run?

SKILL.md names no scripts, command-line tools or credentials: Knowledge Base Sync is instructions for the agent only. Our summary lists: Python 3.

Does Knowledge Base Sync access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Knowledge Base Sync safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Knowledge Base Sync use?

Knowledge Base Sync is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Knowledge Base Sync use?

About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Knowledge Base Sync?

Skills that share tags, products or a category with Knowledge Base Sync: Capture Conversation (outline/outline, 41k stars), Project Cairn (iBlinkQ/project-cairn, 235 stars), LLM Wiki Knowledge Graph (Egonex-AI/Understand-Anything, 86k stars) and Find And Cite (outline/outline, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Knowledge Base Sync?

JetXu-LLM (a GitHub user) maintains it in JetXu-LLM/DocMason, which has 147 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on September 30, 2026.

Source: JetXu-LLM/DocMason on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.