Agent skill

Kb Extract

by VkRainB in VkRainB/ccMesh

从 task-plan 任务产物(prd.md、feature.md、research/.md、progress.csv)中提炼可复用工程经验,写入 docs/KB/ 知识库。

Apache-2.0Auto-check passedProduct & Project Management

Install Kb Extract

skills CLI
$ npx skills add VkRainB/ccMesh --skill kb-extract -a claude-code

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

GitHub CLI
$ gh skill install VkRainB/ccMesh kb-extract --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/VkRainB/ccMesh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/kb-extract .claude/skills/kb-extract && 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
kb-extract
GitHub stars
127
Token cost
~566 tokens
SKILL.md length
103 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

从 task-plan 任务产物(prd.md、feature.md、research/.md、progress.csv)中提炼可复用工程经验,写入 docs/KB/ 知识库。

  • Works in 3 steps: 先输出提炼报告(必须,等确认后再写文件) → 确认后写文件 → 宁缺毋滥
  • Tasks that involve PRD writing
  • SKILL.md covers 输入材料, 你的任务, 提炼原则(严格遵守) and KB 目录结构与分类规则, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Kb Extract is an agent skill from VkRainB/ccMesh. 从 task-plan 任务产物(prd.md、feature.md、research/.md、progress.csv)中提炼可复用工程经验,写入 docs/KB/ 知识库。 在用户要求提炼经验、更新知识库、提取 KB、kb-extract、工程经验沉淀、任务收尾归档时使用。

Its SKILL.md is about 570 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `templates.md`).

It sits in Product & Project Management, covering PRD writing and CSV and tabular files. The repository describes itself as: Claude Code / Codex local AI proxy gateway desktop app (Tauri). Anthropic Messages <- OpenAI-compatible protocol transform, model mapping, endpoint rotation/failover… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve PRD writing
  • Tasks that involve CSV and tabular files

Example prompts

  • “/kb-extract”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. 先输出提炼报告(必须,等确认后再写文件)
  2. 确认后写文件
  3. 宁缺毋滥

What it can do on your machine

Read from SKILL.md and the folder at commit 1be9ce6. 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 (its code samples are markdown).

    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 Extract loads about 566 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 103 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~566

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 VkRainB/ccMesh at commit 1be9ce6, republished under its Apache-2.0 licence (© VkRainB). 103 words, ~566 tokens.

Download SKILL.mdSave it as .claude/skills/kb-extract/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
kb-extract
description
从 task-plan 任务产物(prd.md、feature.md、research/*.md、progress.csv)中提炼可复用工程经验,写入 docs/KB/ 知识库。 在用户要求提炼经验、更新知识库、提取 KB、kb-extract、工程经验沉淀、任务收尾归档时使用。
disable-model-invocation
true

KB 工程经验提炼

你是一名资深知识工程师,负责从项目任务产物中提炼可复用的工程经验。

输入材料

请阅读以下任务产物目录中的文件:

  • docs/task-plan/tasks/<NN-slug>/prd.md(需求决策)
  • docs/task-plan/tasks/<NN-slug>/feature.md(落地细节与验收)
  • docs/task-plan/tasks/<NN-slug>/research/*.md(调研结论)
  • docs/task-plan/progress.csv(任务进度与历史)

任务目录定位:

  1. 用户指定了任务 slug 或编号 → 使用对应 tasks/<NN-slug>/
  2. 未指定 → 读取 docs/task-plan/.runtime/sessions/default.json 的 current_task 字段
  3. 仍无法确定 → 询问用户,不要猜测

你的任务

从上述材料中提炼有价值、可复用的工程经验,写入 docs/KB/ 目录下对应类别的 Markdown 文件。


提炼原则(严格遵守)

纳入标准(满足任一即可):

  • 踩过坑、发现陷阱,其他人容易重复犯的错误
  • 解决了某类问题的通用方案或设计模式
  • 经过验证的技术选型判据或决策框架
  • 值得复用的接口约定、数据契约、命名规范
  • 跨项目通用的调试/排查方法论

排除标准(命中任一即排除):

  • 只与本项目特定业务逻辑强绑定,换个项目完全无法套用
  • 仅记录"做了什么"而没有"为什么这样做/有什么取舍"
  • 过于细碎的操作步骤,没有可迁移的判断依据
  • 已是公认常识,无需特别记录

KB 目录结构与分类规则

在 docs/KB/ 下按以下类别创建或追加 Markdown 文件,只创建本次确实有内容的类别:

docs/KB/
├── architecture/      # 架构决策、模块边界、分层设计、抽象原则
├── patterns/          # 通用设计模式、解决方案模板、代码结构套路
├── pitfalls/          # 踩坑记录、反模式、易错点(必须含原因+规避方法)
├── contracts/         # 接口约定、数据契约、事件/消息格式、命名规范
├── tooling/           # 工具链使用经验、配置心得、调试技巧
├── testing/           # 测试策略、验收方法、无法自动化验证时的替代方案
└── decisions/         # 技术选型判据、方案取舍的决策框架

写入前检查: 列出目标类别下已有文件(docs/KB/<category>/*.md)。同主题已有文件则追加新 ## 节,不新建重复文件。


输出流程

1. 先输出提炼报告(必须,等确认后再写文件)

列出识别到的候选经验,每条注明:

字段说明
标题拟用的经验标题
KB 类别architecture / patterns / pitfalls / contracts / tooling / testing / decisions
目标文件新建 xxx-yyy.md 或追加到已有文件
价值一句话说明对陌生读者的价值
待解释术语是否含有需要括号解释的内部术语(列出来)

若候选为空: 明确说明哪些材料已读、为何没有符合纳入标准的内容。不要强行凑条目。

等待用户确认后再进入步骤 2。用户说「确认」「写入」「全部写入」或逐条批准时方可写文件。

2. 确认后写文件
  • 文件名用英文小写+连字符,如 docs/KB/pitfalls/react-query-cache-key.md
  • 若修改了条目结论且 docs/KB/README.md 索引摘要过时,一并更新对应行的摘要(一行即可)
  • 同类别已有文件则追加新 ## 节,不新建重复文件
  • 每条经验按 templates.md 中的格式模板与写作规范撰写
  • 每个文件末尾维护:
markdown
---
_最后更新:YYYY-MM-DD_

追加条目时同步更新该日期。

3. 宁缺毋滥

本次材料如果没有符合纳入标准的内容,明确说明原因,不要强行凑条目。


条目格式与写作规范

详见 templates.md(格式模板、写作规范、反例写法)。

© VkRainB, 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 .cursor/skills/kb-extract of VkRainB/ccMesh.

  • SKILL.md
  • templates.md

Open the folder on GitHubat commit 1be9ce6

Compare with similar skills

Kb Extract 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.

Kb Extract compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kb Extract this skillVkRainB/ccMesh127—~566Automated safety check: PassApache-2.0
Pride FetchClawBio/ClawBio1.2k—~4.2kAutomated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Ralph Tui Create Beadssubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT
Trellis Brainstormanjiemo/SunnyBeach1787 repos~4kAutomated safety check: PassApache-2.0
Ralph Tui Create Beads Rustsubsy/ralph-tui2.5k1 repos~2.8kAutomated safety check: PassMIT

Similar skills

  • Pride Fetch

    ClawBio/ClawBio

    Query metadata and download data from the PRIDE Archive, EMBL-EBI's proteomics identifications database, via the PRIDE Archive REST API v3.

    1.2k GitHub stars~4.2k tokensUpdated today
    Research & ScienceAuto-check passed
  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Ralph Tui Create Beads

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed
  • Trellis Brainstorm

    anjiemo/SunnyBeach

    Guides collaborative requirements discovery before implementation.

    178 GitHub starsUsed in 7 repos~4k tokens
    Product & Project ManagementAuto-check passed
  • Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).

    2.5k GitHub starsUsed in 1 repo~2.8k tokens
    Product & Project ManagementAuto-check passed
  • Ralph Tui Create JSON

    subsy/ralph-tui

    Convert PRDs to prd.json format for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed

More from VkRainB/ccMesh

  • Kb Calibrate

    VkRainB/ccMesh

    对照当前代码库验证 docs/KB 工程经验条目的准确性,修正与实现不符的表述,并按 templates 格式增补代码验证过的举例。

    127 GitHub stars~811 tokensUpdated yesterday
    Auto-check passed

Questions about Kb Extract

What does Kb Extract do?

从 task-plan 任务产物(prd.md、feature.md、research/.md、progress.csv)中提炼可复用工程经验,写入 docs/KB/ 知识库。. Kb Extract is an agent skill from VkRainB/ccMesh.

When should I use Kb Extract?

Kb Extract fits situations like: tasks that involve PRD writing; tasks that involve CSV and tabular files.

How do I install Kb Extract in Claude Code?

Run `npx skills add VkRainB/ccMesh --skill kb-extract -a claude-code`. Or copy the skill folder (.cursor/skills/kb-extract in VkRainB/ccMesh) into .claude/skills/kb-extract in your project. Claude Code loads it when a task matches its description.

How do I install Kb Extract in Codex?

Run `npx skills add VkRainB/ccMesh --skill kb-extract -a codex`. Or copy the skill folder (.cursor/skills/kb-extract in VkRainB/ccMesh) into .agents/skills/kb-extract in your project. Codex loads it when a task matches its description.

Can I use Kb Extract 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 VkRainB/ccMesh --skill kb-extract -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-extract, .gemini/skills/kb-extract, .github/skills/kb-extract and .opencode/skills/kb-extract in your project.

What does Kb Extract need to run?

SKILL.md names no scripts, command-line tools or credentials: Kb Extract is instructions for the agent only.

Does Kb Extract 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 Extract 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 Extract use?

Kb Extract 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 Kb Extract use?

About 566 tokens (SKILL.md is roughly 2.3k 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 Extract?

Skills that share tags, products or a category with Kb Extract: Pride Fetch (ClawBio/ClawBio, 1.2k stars), CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars) and Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kb Extract?

VkRainB (a GitHub user) maintains it in VkRainB/ccMesh, which has 127 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 8, 2026.

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