Calibrate
sharpdeveye/maestro
A skill your agent uses when workflow components are inconsistent, naming conventions vary, or a new team member's work needs alignment to project standards.
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。
Apache-2.0Auto-check passed
Install Kb Calibrate
$ npx skills add VkRainB/ccMesh --skill kb-calibrate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VkRainB/ccMesh kb-calibrate --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/VkRainB/ccMesh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/kb-calibrate .claude/skills/kb-calibrate && 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-calibrate" agent skill from https://github.com/VkRainB/ccMesh/tree/master/.cursor/skills/kb-calibrate into .claude/skills/kb-calibrate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kb-calibrate", 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/VkRainB/ccMesh/tree/master/.cursor/skills/kb-calibrateType 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 VkRainB/ccMesh --skill kb-calibrate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VkRainB/ccMesh kb-calibrate --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VkRainB/ccMesh.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.cursor/skills/kb-calibrate .agents/skills/kb-calibrate && 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-calibrate" agent skill from https://github.com/VkRainB/ccMesh/tree/master/.cursor/skills/kb-calibrate into .agents/skills/kb-calibrate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kb-calibrate", 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 VkRainB/ccMesh --skill kb-calibrate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VkRainB/ccMesh kb-calibrate --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VkRainB/ccMesh.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.cursor/skills/kb-calibrate .cursor/skills/kb-calibrate && 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-calibrate" agent skill from https://github.com/VkRainB/ccMesh/tree/master/.cursor/skills/kb-calibrate into .cursor/skills/kb-calibrate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kb-calibrate", 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/VkRainB/ccMesh.git --path .cursor/skills/kb-calibrate--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 VkRainB/ccMesh --skill kb-calibrate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VkRainB/ccMesh kb-calibrate --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VkRainB/ccMesh.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.cursor/skills/kb-calibrate .gemini/skills/kb-calibrate && 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-calibrate" agent skill from https://github.com/VkRainB/ccMesh/tree/master/.cursor/skills/kb-calibrate into .gemini/skills/kb-calibrate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kb-calibrate", 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 VkRainB/ccMesh kb-calibrateInstalls 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 VkRainB/ccMesh --skill kb-calibrate -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VkRainB/ccMesh.git skills-src && mkdir -p .github/skills && cp -r skills-src/.cursor/skills/kb-calibrate .github/skills/kb-calibrate && 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-calibrate" agent skill from https://github.com/VkRainB/ccMesh/tree/master/.cursor/skills/kb-calibrate into .github/skills/kb-calibrate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kb-calibrate", 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 VkRainB/ccMesh --skill kb-calibrate -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VkRainB/ccMesh kb-calibrate --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VkRainB/ccMesh.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.cursor/skills/kb-calibrate .opencode/skills/kb-calibrate && 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-calibrate" agent skill from https://github.com/VkRainB/ccMesh/tree/master/.cursor/skills/kb-calibrate into .opencode/skills/kb-calibrate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kb-calibrate", 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-calibrate- GitHub stars
- 127
- Token cost
- ~811 tokens
- SKILL.md length
- 233 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
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。
- Works in 5 steps: 准备 → 提取可验证断言 → 代码对照 → …
- SKILL.md covers 输入范围, 校准原则, 验证流程 and 简要示例, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Kb Calibrate is an agent skill from 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。 在用户要求校准知识库、kb-calibrate、经验对码、KB 与代码不一致、验证 KB 条目、代码落盘校准时使用。
Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
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.
Example prompts
- “/kb-calibrate”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
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 Calibrate loads about 811 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 233 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 VkRainB/ccMesh at commit 1be9ce6, republished under its Apache-2.0 licence (© VkRainB). 233 words, ~811 tokens.
Download SKILL.mdSave it as
.claude/skills/kb-calibrate/SKILL.md (or your agent's skills folder).- name
- kb-calibrate
- description
- 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。 在用户要求校准知识库、kb-calibrate、经验对码、KB 与代码不一致、验证 KB 条目、代码落盘校准时使用。
- disable-model-invocation
- true
KB 工程经验校准
你是一名资深知识工程师，负责以当前代码库为事实来源，校准 docs/KB/ 中已有经验条目的准确性。
与 kb-extract 的分工：
| Skill | 输入 | 输出 |
|---|---|---|
| kb-extract | task-plan 任务产物 | 从任务中提炼新经验 |
| kb-calibrate | docs/KB 条目 + 当前代码 | 验证并修正已有经验 |
输入范围
定位待校准条目：
- 用户指定文件路径 → 只校准该文件（可含多个
##节） - 用户指定类别 → 校准
docs/KB/<category>/*.md - 用户说「全部」→ 遍历
docs/KB/下所有.md（跳过README.md） - 用户指定 task slug → 先读
docs/task-plan/tasks/<NN-slug>/feature.md提取「声称已实现」的能力清单，再对照 KB 中与该任务相关的条目（代码仍是最终裁判）
任务目录定位规则同 kb-extract：读 docs/task-plan/.runtime/sessions/default.json 的 current_task，无法确定则询问用户。
校准原则
代码优先： 文档描述与代码行为冲突时，以当前主分支代码为准修正文档。若代码明显是 bug 而非文档错，在校准报告中标注「实现疑似缺陷」，不要把 bug 写进 KB 当正确做法。
格式不变： 条目结构必须遵守 kb-extract/templates.md。允许的操作：
- 修正「一句话结论」「为什么会出错」「正确做法」中与代码不符的表述
- 在「正确做法」或「反例（可选）」追加经代码验证的举例（保持通用写法，见下文）
- 更新文件末尾
_最后更新：YYYY-MM-DD_
禁止的操作：
- 不要改模板字段名、不要删整块必填节、不要重排整文件结构
- 不要把 file:line、内部 crate 名、任务编号写进 KB 正文（校准报告里可以有）
- 不要为了「对齐代码」把条目改成只对本仓库有效的操作手册
举例写法： 从代码抽象出通用模式，用伪代码或语言无关描述：
**反例**
❌ 错误：对目标路径直接 write → ✅ 正确：同目录 tmp 文件 write+flush 后 rename若现有条目已有反例，在其后追加一行即可，不要替换掉仍有效的反例。
验证流程
0. 准备
- 列出待校准文件与
##节标题 - 若存在
.codegraph/，优先用codegraph_explore定位实现；否则 grep + read 追踪调用链 - 每条经验至少找 1 处可引用的实现锚点（报告用，不写入 KB）
1. 提取可验证断言
从每个 ## 节拆出可对照代码的检查点，例如：
- 「一句话结论」是否仍成立
- 「正确做法」每条 bullet 是否有对应实现
- 「反例」描述的错误模式是否被实现主动规避
- decisions/contracts 类：字段名、状态码分类、转发策略是否与类型定义/分支一致
2. 代码对照
对每个断言：
- 从关键词（函数名、配置键、HTTP 状态、字段名）grep 或 codegraph 搜索
- 读到实际落盘行为（写文件路径、分支条件、默认值），而非注释或旧 task 文档
- 记录：一致 / 部分一致 / 不一致 / 无法验证（代码已删除或找不到）
无法验证时： 在报告中说明搜索过的符号与路径，建议保留条目或标注「待实现验证」，不要臆测修改。
3. 先输出校准报告（必须，等确认后再改文件）
| 字段 | 说明 |
|---|---|
| 文件 · 节标题 | 如 patterns/atomic-config-write.md · 本地配置文件原子写 primitive |
| 断言摘要 | 文档里被检查的那句话 |
| 状态 | ✅一致 / ⚠️部分一致 / ❌不一致 / ❓无法验证 |
| 代码证据 | path:line + 一行行为摘要（仅报告，不进 KB） |
| 建议修改 | 无 / 修正措辞 / 增补举例 / 整节过时需删除或归档 |
若全部一致： 明确说明已核对条目数与抽样路径，不必改文件。
等待用户确认后再进入步骤 4。用户说「确认」「写入」「全部写入」或逐条批准时方可改 docs/KB/。
4. 确认后写入
- 最小 diff：只改有证据支撑的差异，不顺手润色无关段落
- 增补举例时插入对应小节末尾，保持列表格式
- 同步更新该文件
_最后更新日期 - 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） - 整节过时：先问用户是删除、
## [已过时]前缀，还是移到 archive
简要示例
示例 A：文档准确，无需改动
输入： 校准 docs/KB/patterns/atomic-config-write.md
代码： 发现 atomic_write 实现为 tmp → flush → rename，Windows 分支先 remove 再 rename。
报告： 全部断言 ✅一致，建议不改文件。
示例 B：部分一致，增补反例
文档写： 「出站 tool arguments 必须排序键」
代码： 排序在 canonicalize_tool_arguments 入口统一执行，但空参数 {} 与排序是两条独立规则。
写入（仅追加反例一行，不改模板）：
**反例**
❌ 错误：只排序键、空串仍当有效 JSON 发出 → ✅ 正确：先 `{}` 规范化再递归排序键示例 C：不一致，修正结论
文档写： 「403 与 429 一样计熔断失败」
代码： 403 走 client_error 中性分支，不 increment failure。
写入： 只改「一句话结论」和「正确做法」中涉及 403 的 bullet，使与 classify_http_status 分支一致；decisions 类条目保留决策理由，修正事实描述。
条目格式
撰写或修改正文时，格式以 templates.md 为准；本 skill 只负责校准准确性，不改变模板本身。
© 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
Just SKILL.md in .cursor/skills/kb-calibrate of VkRainB/ccMesh.
Open the folder on GitHubat commit 1be9ce6
Compare with similar skills
Kb Calibrate 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 Calibrate this skillVkRainB/ccMesh | 127 | — | ~811 | Automated safety check: Pass | Apache-2.0 | |
| Calibratesharpdeveye/maestro | 592 | — | ~782 | Automated safety check: Pass | MIT | |
| Calibrateapache/magpie | 113 | — | ~3.9k | Automated safety check: Pass | Apache-2.0 | |
| CLI Anything CalibreHKUDS/CLI-Anything | 52k | — | ~1.8k | Automated safety check: Notes | Apache-2.0 | |
| RuView Room Calibrationruvnet/RuView | 97k | — | ~320 | Automated safety check: Pass | MIT | |
| Trust Calibratorsickn33/agentic-awesome-skills | 47k | 2 repos | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
Calibrate
apache/magpie
Derive committer and <governance-body reference levels from the project's own past nomination decisions on <private-list, deliberately relaxed below what was elected, and propose them as a…
CLI Anything Calibre
HKUDS/CLI-Anything
Command-line interface for Calibre - A stateful CLI harness for e-book library management, metadata editing, and format conversion wrapping the real Calibre tools (calibredb, ebook-convert…
RuView Room Calibration
ruvnet/RuView
Run the ADR-151 per-room calibration pipeline — baseline → enroll → extract → train → a bank of small specialists…
Trust Calibrator
sickn33/agentic-awesome-skills
One sentence - what this skill does and when to invoke it. An agent skill from sickn33/agentic-awesome-skills.
Glm Calibration
benchflow-ai/skillsbench
Calibrate GLM parameters for water temperature simulation. An agent skill from benchflow-ai/skillsbench.
More from VkRainB/ccMesh
Kb Extract
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。
Questions about Kb Calibrate
What does Kb Calibrate do?
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。. Kb Calibrate is an agent skill from VkRainB/ccMesh.
How do I install Kb Calibrate in Claude Code?
Run `npx skills add VkRainB/ccMesh --skill kb-calibrate -a claude-code`. Or copy the skill folder (.cursor/skills/kb-calibrate in VkRainB/ccMesh) into .claude/skills/kb-calibrate in your project. Claude Code loads it when a task matches its description.
How do I install Kb Calibrate in Codex?
Run `npx skills add VkRainB/ccMesh --skill kb-calibrate -a codex`. Or copy the skill folder (.cursor/skills/kb-calibrate in VkRainB/ccMesh) into .agents/skills/kb-calibrate in your project. Codex loads it when a task matches its description.
Can I use Kb Calibrate 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-calibrate -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-calibrate, .gemini/skills/kb-calibrate, .github/skills/kb-calibrate and .opencode/skills/kb-calibrate in your project.
What does Kb Calibrate need to run?
SKILL.md names no scripts, command-line tools or credentials: Kb Calibrate is instructions for the agent only.
Does Kb Calibrate 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 Calibrate 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 Calibrate use?
Kb Calibrate 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 Calibrate use?
About 811 tokens (SKILL.md is roughly 3.2k 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 Calibrate?
Skills that share tags, products or a category with Kb Calibrate: Calibrate (sharpdeveye/maestro, 592 stars), Calibrate (apache/magpie, 113 stars), CLI Anything Calibre (HKUDS/CLI-Anything, 52k stars) and RuView Room Calibration (ruvnet/RuView, 97k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Kb Calibrate?
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.