Knowledge Base Management
chubbyguan/chubbyskills
管理本地 Markdown/Obsidian 知识库：素材入库、健康检查、增量索引、关键词与 semantic-lite 检索、逐字原文资料包、归档和 MCP 连接。用于搜索知识库、整理资料及为 Agent 准备可定位的引用。
Use before starting any non-trivial task to search the knowledge base for context, and after completing work to capture findings.
Install Kb Workflow
$ npx skills add willynikes2/knowledge-base-server --skill kb-workflow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install willynikes2/knowledge-base-server kb-workflow --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/willynikes2/knowledge-base-server.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill .claude/skills/kb-workflow && rm -rf skills-srcUse ~/.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/
Install the "kb-workflow" agent skill from https://github.com/willynikes2/knowledge-base-server/tree/master/skill into .claude/skills/kb-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kb-workflow", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/willynikes2/knowledge-base-server/tree/master/skillType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add willynikes2/knowledge-base-server --skill kb-workflow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install willynikes2/knowledge-base-server kb-workflow --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/willynikes2/knowledge-base-server.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skill .agents/skills/kb-workflow && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "kb-workflow" agent skill from https://github.com/willynikes2/knowledge-base-server/tree/master/skill into .agents/skills/kb-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kb-workflow", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add willynikes2/knowledge-base-server --skill kb-workflow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install willynikes2/knowledge-base-server kb-workflow --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/willynikes2/knowledge-base-server.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skill .cursor/skills/kb-workflow && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "kb-workflow" agent skill from https://github.com/willynikes2/knowledge-base-server/tree/master/skill into .cursor/skills/kb-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kb-workflow", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/willynikes2/knowledge-base-server.git --path skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add willynikes2/knowledge-base-server --skill kb-workflow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install willynikes2/knowledge-base-server kb-workflow --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/willynikes2/knowledge-base-server.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skill .gemini/skills/kb-workflow && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "kb-workflow" agent skill from https://github.com/willynikes2/knowledge-base-server/tree/master/skill into .gemini/skills/kb-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kb-workflow", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install willynikes2/knowledge-base-server kb-workflowInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add willynikes2/knowledge-base-server --skill kb-workflow -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/willynikes2/knowledge-base-server.git skills-src && mkdir -p .github/skills && cp -r skills-src/skill .github/skills/kb-workflow && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "kb-workflow" agent skill from https://github.com/willynikes2/knowledge-base-server/tree/master/skill into .github/skills/kb-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kb-workflow", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add willynikes2/knowledge-base-server --skill kb-workflow -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install willynikes2/knowledge-base-server kb-workflow --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/willynikes2/knowledge-base-server.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skill .opencode/skills/kb-workflow && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "kb-workflow" agent skill from https://github.com/willynikes2/knowledge-base-server/tree/master/skill into .opencode/skills/kb-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kb-workflow", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
kb-workflow- GitHub stars
- 182
- Token cost
- ~1.1k tokens
- SKILL.md length
- 404 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use before starting any non-trivial task to search the knowledge base for context, and after completing work to capture findings.
- Tasks that involve Knowledge bases
- SKILL.md covers What This Skill Does, Before Starting Any Task, The Three-Tier Retrieval Pattern and After Completing Work, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Kb Workflow is an agent skill from willynikes2/knowledge-base-server. Use before starting any non-trivial task to search the knowledge base for context, and after completing work to capture findings. Teaches the token-efficient retrieval pattern and self-learning loop.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Knowledge Management, covering Knowledge bases. It works with Model Context Protocol, SQLite and Obsidian. The repository describes itself as: Make every AI agent you use smarter. Persistent memory with SQLite FTS5, MCP server, Obsidian sync, and self-learning intelligence pipeline. The licence is MIT.
When your agent uses it
- Tasks that involve Knowledge bases
Example prompts
- “/kb-workflow”
What it can do on your machine
Read from SKILL.md and the folder at commit 58cffa0. 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
Kb Workflow loads about 1.1k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 404 words of instructions outside code blocks.
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 willynikes2/knowledge-base-server at commit 58cffa0, republished under its MIT licence (© willynikes2). 404 words, ~1,123 tokens.
Download SKILL.mdSave it as
.claude/skills/kb-workflow/SKILL.md (or your agent's skills folder).- name
- kb-workflow
- description
- Use before starting any non-trivial task to search the knowledge base for context, and after completing work to capture findings. Teaches the token-efficient retrieval pattern and self-learning loop.
Knowledge Base Workflow
What This Skill Does
This skill teaches you how to use the knowledge-base-server MCP tools efficiently. It does NOT replace the MCP server — it complements it by giving you the retrieval strategy that saves 90%+ tokens.
Think of it this way:
- MCP server = the engine (search, read, write, capture)
- This skill = the driving instructions (when to search, what to read, how to capture)
Before Starting Any Task
Search the KB for relevant context BEFORE writing code or making decisions:
1. kb_context("topic") — get summaries only (~100 tokens per doc, 90% savings)
2. Review titles and summaries — decide which docs matter
3. kb_read(id) — read full content ONLY for docs you actually needNever skip this. The KB has accumulated lessons, fixes, decisions, and architecture docs. Searching first prevents:
- Repeating solved problems
- Contradicting past decisions
- Missing known pitfalls
- Wasting tokens on re-discovery
The Three-Tier Retrieval Pattern
The KB has three tiers of information. Query the right tier for your need:
| Need | Tool | Tokens | When |
|---|---|---|---|
| Quick context | kb_context | ~100/doc | Always start here |
| Specific search | kb_search | ~200/result | Looking for something specific |
| Conceptual match | kb_search_smart | ~200/result | Fuzzy/semantic queries |
| Full document | kb_read | ~500-5000/doc | Only after context confirms relevance |
Rule: Never kb_read without kb_context first. You wouldn't read an entire book to check if it's relevant — you'd read the summary.
After Completing Work
Capture what you learned so the next session starts smarter:
After debugging sessions:
kb_capture_session:
goal: "What you were trying to do"
commands_worked: "What worked"
commands_failed: "What failed and why"
root_causes: "The actual problem"
fixes: "What fixed it"
lessons: "What to do differently next time"After bug fixes:
kb_capture_fix:
title: "Short fix title"
symptom: "What was broken"
cause: "Root cause"
resolution: "How it was fixed"After research or decisions:
kb_write:
title: "Decision or finding title"
type: "decision" or "research" or "lesson"
content: "What was decided and why"The Self-Learning Loop
This is how the system compounds intelligence:
Session N:
1. Search KB for context (maybe find nothing)
2. Do the work (hit problems, make decisions)
3. Capture findings to KB
Session N+1:
1. Search KB for context (find Session N's captures!)
2. Skip the problems Session N already solved
3. Capture NEW findings
Session N+100:
1. Search KB for context (find 100 sessions of accumulated knowledge)
2. One-shot clean implementation because context covers everything
3. Capture only genuinely new learningsThis is NOT fine-tuning. The model doesn't change. The context it receives improves. And context is everything.
Show full SKILL.md (170 more words)Show less
When to Use Each Tool
| Situation | Tool | Why |
|---|---|---|
| Starting a new task | kb_context | Get the lay of the land |
| "How did we do X?" | kb_search | Find specific past work |
| "What do we know about X?" | kb_search_smart | Conceptual/fuzzy match |
| Need full implementation details | kb_read | After context identified the doc |
| Finished debugging | kb_capture_session | Record what happened |
| Fixed a bug | kb_capture_fix | Record symptom/cause/fix |
| Made a decision | kb_write type=decision | Record the decision and why |
| Found useful research | kb_write type=research | Save for future reference |
| Want cross-cutting insights | kb_synthesize | Connect dots across sources |
| New content needs tagging | kb_classify | Auto-classify unprocessed notes |
What NOT to Do
- Don't
kb_readevery document that matches a search — read summaries first - Don't skip searching because "I probably know this" — the KB knows more than you remember
- Don't forget to capture after significant work — a lesson not captured is a lesson repeated
- Don't index raw code into the KB — use CODEMAP.md structural maps instead
- Don't treat the KB as a dump — classified, typed, tagged notes are 10x more useful than raw text
© willynikes2, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skill of willynikes2/knowledge-base-server.
Open the folder on GitHubat commit 58cffa0
Compare with similar skills
Kb Workflow 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Kb Workflow this skillwillynikes2/knowledge-base-server | 182 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Knowledge Base Managementchubbyguan/chubbyskills | 1.2k | — | ~3.3k | Automated safety check: Pass | MIT | |
| Engraphdevwhodevs/engraph | 171 | — | ~792 | Automated safety check: Pass | MIT | |
| Context Mode Indexermksglu/context-mode | 26k | — | ~328 | Automated safety check: Pass | Custom licence | |
| Auto Memorytractorjuice/arc-kit | 2.3k | — | ~1.7k | Automated safety check: Pass | Custom licence | |
| OutlineVortiago/mcp-outline | 156 | — | ~818 | Automated safety check: Pass | MIT |
Similar skills
Engraph
devwhodevs/engraph
Index and search document collections using hybrid semantic + graph + full-text search.
Context Mode Indexer
mksglu/context-mode
Indexes a local file or project directory into context-mode's FTS5 knowledge base so later searches return focused snippets instead of rereading whole files.
Auto Memory
tractorjuice/arc-kit
This skill should be used when the user asks to 'set up memory', 'create memory files', 'create MEMORY.md', 'set up topic files', 'improve memory organization', 'what should I remember', 'how to…
Outline
Vortiago/mcp-outline
Conventions and efficient workflows for Outline knowledge bases via mcp-outline tools.
Solomd
zhitongblog/solomd
Read, search, edit, and version-control any folder of Markdown notes via the SoloMD MCP server.
Related
Works with
Categories
Questions about Kb Workflow
What does Kb Workflow do?
Use before starting any non-trivial task to search the knowledge base for context, and after completing work to capture findings. Kb Workflow is an agent skill from willynikes2/knowledge-base-server. Use before starting any non-trivial task to search the knowledge base for context, and after completing work to capture findings.
When should I use Kb Workflow?
Kb Workflow fits situations like: tasks that involve Knowledge bases.
How do I install Kb Workflow in Claude Code?
Run `npx skills add willynikes2/knowledge-base-server --skill kb-workflow -a claude-code`. Or copy the skill folder (skill in willynikes2/knowledge-base-server) into .claude/skills/kb-workflow in your project. Claude Code loads it when a task matches its description.
How do I install Kb Workflow in Codex?
Run `npx skills add willynikes2/knowledge-base-server --skill kb-workflow -a codex`. Or copy the skill folder (skill in willynikes2/knowledge-base-server) into .agents/skills/kb-workflow in your project. Codex loads it when a task matches its description.
Can I use Kb Workflow 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 willynikes2/knowledge-base-server --skill kb-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kb-workflow, .gemini/skills/kb-workflow, .github/skills/kb-workflow and .opencode/skills/kb-workflow in your project.
What does Kb Workflow need to run?
SKILL.md names no scripts, command-line tools or credentials: Kb Workflow is instructions for the agent only.
Does Kb Workflow 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 Kb Workflow 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 Kb Workflow use?
Kb Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Kb Workflow use?
About 1.1k tokens (SKILL.md is roughly 4.5k 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 Kb Workflow?
Skills that share tags, products or a category with Kb Workflow: Knowledge Base Management (chubbyguan/chubbyskills, 1.2k stars), Engraph (devwhodevs/engraph, 171 stars), Context Mode Indexer (mksglu/context-mode, 26k stars) and Auto Memory (tractorjuice/arc-kit, 2.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Kb Workflow?
willynikes2 (a GitHub user) maintains it in willynikes2/knowledge-base-server, which has 182 GitHub stars. The repository was last updated on October 5, 2026.
Source: willynikes2/knowledge-base-server on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.