Agent skill

Codenote Fix Prompt

by Philip-Cao-9527 in Philip-Cao-9527/code-note-helper

为 CodeNote Helper 生成普通开发、修复、验证、治理、文档和审核友好类中文执行 prompt。用于把一次具体任务整理成可直接交给 Codex 或 Agent 执行的 prompt;不承载 Plan mode prompt、code review prompt 或项目 skill creator 的完整职责。

MITAuto-check passedAgent Workflows

Install Codenote Fix Prompt

skills CLI
$ npx skills add Philip-Cao-9527/code-note-helper --skill codenote-fix-prompt -a claude-code

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

GitHub CLI
$ gh skill install Philip-Cao-9527/code-note-helper codenote-fix-prompt --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/Philip-Cao-9527/code-note-helper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/codenote-fix-prompt .claude/skills/codenote-fix-prompt && 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
codenote-fix-prompt
GitHub stars
273
Token cost
~931 tokens
SKILL.md length
233 words
Files
4 (incl. scripts, references)
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

为 CodeNote Helper 生成普通开发、修复、验证、治理、文档和审核友好类中文执行 prompt。用于把一次具体任务整理成可直接交给 Codex 或 Agent 执行的 prompt;不承载 Plan mode prompt、code review prompt 或项目 skill creator 的完整职责。

  • Works in 4 steps: 确认用户要的是“生成 prompt”,不是直接执行任务。 → 读取项目材料 → 读取… → …
  • Tasks that involve Planning
  • SKILL.md covers 技能定位, Skill 交叉引用规则, 使用流程 and 默认补全规则, plus 4 more sections
  • Runs Python scripts from its folder; calls python

What it does

Codenote Fix Prompt is an agent skill from Philip-Cao-9527/code-note-helper. 为 CodeNote Helper 生成普通开发、修复、验证、治理、文档和审核友好类中文执行 prompt。用于把一次具体任务整理成可直接交给 Codex 或 Agent 执行的 prompt;不承载 Plan mode prompt、code review prompt 或项目 skill creator 的完整职责。

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/prompt-template.md` and `scripts/validate_codenote_fix_prompt.py`).

It sits in Agent Workflows, covering Planning, Skill authoring and Code review. The repository describes itself as: 一个专为算法刷题、深度学习和 AI 学习场景打造的浏览器扩展。拒绝机械的复制粘贴,帮你自动化生成高质量复盘笔记、内置遗忘曲线驱动的间隔复习、轻松驾驭超长对话,让刷过的每一道题都成为真正的技术资产!. The licence is MIT.

When your agent uses it

  • Tasks that involve Planning
  • Tasks that involve Skill authoring
  • Tasks that involve Code review

Example prompts

  • “/codenote-fix-prompt”

Requirements

  • Python 3

Workflow steps

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

  1. 确认用户要的是“生成 prompt”,不是直接执行任务。
  2. 读取项目材料
  3. 读取 references/prompt-template.md,按本轮任务裁剪和填充。
  4. 输出前将生成的 prompt 保存为临时草稿或逐项核对,并运行专项校验脚本

What it can do on your machine

Read from SKILL.md and the folder at commit 7421249. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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

Codenote Fix Prompt loads about 931 tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 45 tokens; SKILL.md has 233 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~931
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.5k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from Philip-Cao-9527/code-note-helper at commit 7421249, republished under its MIT licence (© Philip-Cao-9527). 233 words, ~931 tokens.

Download SKILL.mdSave it as .claude/skills/codenote-fix-prompt/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
codenote-fix-prompt
description
为 CodeNote Helper 生成普通开发、修复、验证、治理、文档和审核友好类中文执行 prompt。用于把一次具体任务整理成可直接交给 Codex 或 Agent 执行的 prompt;不承载 Plan mode prompt、code review prompt 或项目 skill creator 的完整职责。

CodeNote Helper 普通任务 Prompt 生成

技能定位

本 skill 只生成普通执行 prompt。主产物是一份可复制给 Codex 或 Agent 立刻执行的中文任务 prompt,不直接开始修复,不直接审查代码,也不创建或更新 skill。

以下场景应改用独立 skill:

  • 需要先进入 Plan mode、只读探索、提炼 2 到 4 个关键决策点时,使用 $codenote-plan-mode-prompt。
  • 需要生成 code review 任务 prompt、要求 findings first 和独立审查报告时,使用 $codenote-code-review-prompt。
  • 需要创建或更新 .agents/skills 下的 CodeNote Helper 本地 skill 时,使用 $codenote-skill-creator。

只有用户明确要求合并模式时,才在普通执行 prompt 中引用对应原则;不要把这些独立 skill 的完整规则复制进本 skill。

Skill 交叉引用规则

当生成的 prompt 需要明确要求后续执行者调用其他 skill 时,必须使用 $skill-name 形式引用,例如 $codenote-plan-mode-prompt。不要只写反引号包裹的 skill 名称,也不要写成普通文件名或自然语言描述。

使用流程

  1. 确认用户要的是“生成 prompt”,不是直接执行任务。
  2. 读取项目材料:
    • AGENTS.md
    • 仅当 AGENTS.override.md 真实存在时读取它;不存在时不要写成必读事实。
    • DEVLOG.md
    • README.md
    • 与本轮任务直接相关的真实调用链、测试文件、报告或文档。
  3. 读取 references/prompt-template.md,按本轮任务裁剪和填充。
  4. 输出前将生成的 prompt 保存为临时草稿或逐项核对,并运行专项校验脚本:
powershell
python -X utf8 .agents/skills/codenote-fix-prompt/scripts/validate_codenote_fix_prompt.py path/to/generated-prompt.md

脚本失败时,必须按缺失项继续补齐 prompt 并复跑。该脚本只检查普通执行 prompt 的关键结构和 CodeNote Helper 项目边界,不判断任务内容是否已经完全覆盖用户意图。 5. 输出一份完整、连续、可复制、可执行的中文 prompt。

默认补全规则

  • 仓库路径默认使用当前 CodeNote Helper 仓库路径;无法确认时要求执行者现场核对。
  • 当前版本必须从 manifest.json、popup/popup.html、README.md 现场核对;用户未要求升版时默认保持当前版本。
  • 任务涉及功能修复、行为变更、UI 调整、结构调整、测试闭环或版本历史更新时,prompt 应要求同步 DEVLOG.md 并新增 docs/fix-report-vX.Y.Z-YYYYMMDD-主题.md。
  • 任务不触发版本或报告时,prompt 应要求最终总结说明原因。
  • 修复报告内容质量:如果 prompt 要求新增 docs/fix-report-*.md,必须同时要求报告通俗可读。涉及 Chrome MV3、manifest.json、host_permissions、content_scripts.matches、OAuth、Google Drive、WebDAV、service worker、content script、storage、Playwright 或 Node test 等英文术语、字段名和扩展概念时,要补中文解释和用户影响说明,不要只堆字段、路径和英文缩写。
  • 多次验证结构:如果后续执行者进行了多次 Node 测试、静态检查、Playwright、真实浏览器或手动复测,prompt 必须要求报告用清晰 Markdown 标题区分每一次验证,并用表格汇总命令、目标、结果、证据和剩余风险;失败时要解释原因边界,不只描述现象。
  • 根目录 references/ 中标注“仅供参考,非项目代码”的内容只能参考,不得要求直接修改;.agents/skills/*/references/ 属于本地 skill 资产,可按任务目标修改。
  • 语言使用简体中文;代码、命令、报错、路径、字段名、域名、专有名词保留原文。

CodeNote Helper 专属约束

生成 prompt 时,按任务相关性保留下列项目约束:

  • Windows 与 UTF-8 编码:修改 JS、HTML、CSS、JSON、Markdown、manifest、README 等文件时保持原文件风格,新建文本默认 UTF-8。
  • 最小必要改动:先理解真实入口、调用链、依赖顺序和站点隔离边界,再做修改。
  • 版本策略:默认保持当前版本;只有用户明确要求升版时才升级,并同步所有版本位置。
  • 文档闭环:按项目规则更新 DEVLOG.md 和 docs/fix-report,报告链接使用可跳转 Markdown 相对路径;带行号时统一使用 [文件名](相对路径#L行号),不要把 :行号 写进链接目标。
  • 报告可读性:docs/fix-report 不只是证据清单。必须把权限、远程请求、同步、注入顺序、用户数据、浏览器差异和测试结果讲清楚;字段名、路径和英文术语要配中文解释,原因分析要说明用户会遇到什么后果。
  • 权限与审核友好:涉及 manifest.json、权限、host、content scripts、远程请求、README、隐私政策或商店说明时,必须做审核友好自检。
  • 禁止无依据保护逻辑:不要凭空加入固定超时、长度截断、条数上限、重试上限、静默兜底或吞异常。
  • 用户可见中文文案:按钮、toast、弹窗、错误提示和设置说明必须自然中文,不暴露内部变量、函数名、模块名、堆栈或调试信息。

常见任务加料

  • 页面抓取、DOM、注入、滚动、点击、浏览器行为:要求先复现,再定位,再修复;默认使用 Playwright MCP 或等价浏览器工具留证据。
  • popup、notes、options、shared 数据链路:强调真实状态结构、依赖顺序、脚本注入顺序和防回归测试。
  • 题单导入、静态映射:优先内置静态映射;禁止运行时访问 GitHub README 或新增无关远程权限。
  • 日志、调试、自动入库、复习链路:日志要可读、克制、结构化,不暴露到用户界面。
  • 权限、manifest、远程请求、审核友好:说明为什么必须新增权限或域名、是否可收窄、是否用户触发、是否影响审核。

输出包裹规则

  • 最终 prompt 必须整体放在一个 Markdown 文本块中,方便复制。
  • 如果 prompt 内部包含三反引号,外层使用四反引号或更长围栏。
  • 输出代码块前最多写一句中文引导;代码块后不要追加正文。

自检

输出前检查:

  1. 是否明确这是生成普通执行 prompt,不是直接执行任务。
  2. 是否没有把 Plan mode、code review 或 skill creator 的完整规则塞进本 prompt。
  3. 如果 prompt 中交叉引用其他 skill,是否统一使用 $skill-name 形式。
  4. 是否正确处理 AGENTS.md 与可选 AGENTS.override.md。
  5. 是否没有把未验证版本、路径、测试结果或发布状态写成事实。
  6. 是否保留 CodeNote Helper 的版本、报告、权限审核、编码、错误处理和用户文案边界。
  7. 是否没有要求修改根目录 references/ 的非项目代码。
  8. 是否已运行 validate_codenote_fix_prompt.py 或对同等规则逐项校验,并根据失败项循环修改到通过。
  9. 是否没有保留空标题、一次性残留或不可执行的模板句。

© Philip-Cao-9527, MIT. 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 3 other files (scripts, references) in .agents/skills/codenote-fix-prompt of Philip-Cao-9527/code-note-helper.

  • SKILL.md
  • agents/openai.yaml
  • references/prompt-template.md
  • scripts/validate_codenote_fix_prompt.py

Open the folder on GitHubat commit 7421249

Compare with similar skills

Codenote Fix Prompt 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.

Codenote Fix Prompt compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codenote Fix Prompt this skillPhilip-Cao-9527/code-note-helper273—~931Automated safety check: PassMIT
Plannotator Visual Explainerbacknotprop/plannotator9.3k—~1.7kAutomated safety check: PassApache-2.0
LubanLearnPrompt/luban-skill959—~3.1kAutomated safety check: PassMIT
Explorexwtro0tk1t-cloud/harness265—~1.6kAutomated safety check: PassNone
01 Planai-driven-dev/framework513—~517Automated safety check: PassMIT
Subagent Driven DevelopmentNeoLabHQ/context-engineering-kit1.8k—~2.8kAutomated safety check: PassGPL-3.0

Similar skills

  • Plannotator Visual Explainer

    backnotprop/plannotator

    Builds self-contained HTML explainers for plans, pull requests and technical concepts in Plannotator's theme, then opens them in its annotation view.

    9.3k GitHub stars~1.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Luban

    LearnPrompt/luban-skill

    鲁班(Luban)——Skill打磨工坊。把一个"能用的Skill"打磨成"能被理解、能被安装、能被传播、能被验证、能持续进化"的公共Skill资产。

    959 GitHub stars~3.1k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed
  • Explore

    xwtro0tk1t-cloud/harness

    Graph-driven project understanding using code-review-graph (CRG).

    265 GitHub stars~1.6k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed
  • 01 Plan

    ai-driven-dev/framework

    Turn a request, ticket, or file into a phased implementation plan.

    513 GitHub stars~517 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Subagent Driven Development

    NeoLabHQ/context-engineering-kit

    A skill your agent uses when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or…

    1.8k GitHub stars~2.8k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Plan Review

    sd0xdev/sd0x-harness

    Pre-ExitPlanMode adversarial plan review loop via Codex exec.

    192 GitHub stars~3.9k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

More from Philip-Cao-9527/code-note-helper

All 13 skills in this repo
  • Agents Md Creator

    Philip-Cao-9527/code-note-helper

    基于项目真实背景、用户长期偏好和现有文档生成或更新项目级 AGENTS.md。用于新项目初始化、迁移协作规则、整理语言编码测试版本文档约束、沉淀长期协作底线和交付格式时使用。

    273 GitHub stars~581 tokensUpdated 2 mo ago
    Auto-check passed
  • Codenote Skill Creator

    Philip-Cao-9527/code-note-helper

    创建或更新 CodeNote Helper 项目本地 .agents/skills 下的 Codex skills。用于把高频协作流程、prompt 生成流程、审查流程或项目专项流程沉淀为可复用 skill;不替代一次性任务 prompt、普通开发实现或万能规则汇总。

    273 GitHub stars~948 tokensUpdated 2 mo ago
    Auto-check passed
  • Project Prompt Creator

    Philip-Cao-9527/code-note-helper

    在项目 AGENTS.md 约束下生成可直接交给 Codex 或 Agent 执行的中文任务 prompt。用于开发、修复、文档、验证、审计、治理或交接任务的 prompt 化,但不承载 Plan mode 和 code review 的完整模式规则。

    273 GitHub stars~693 tokensUpdated 2 mo ago
    Auto-check passed
  • Project Skill Creator

    Philip-Cao-9527/code-note-helper

    基于用户需求和项目真实上下文创建或更新项目本地 skill。用于把高频协作流程、领域任务、项目规范、prompt 生成流程或审查流程沉淀为可复用 skill,并避免把一次性任务误做成长期 skill。

    273 GitHub stars~820 tokensUpdated 2 mo ago
    Auto-check passed
  • Knowledge Explainer

    Philip-Cao-9527/code-note-helper

    当用户要求技术原理讲解、八股讲解、从零教学、面试口述、项目追问回答、领域补课、把项目实现转成可复习表达,或在缺少领域背景时需要先理解概念再推进项目时使用;覆盖后端、前端、数据库、分布式、系统设计、编译构建、DevOps、安全、产品业务、数据分析、Agent、LLM、科研方法等可迁移领域。若涉及最新论文、官方文档、benchmark、争议结论或现代 API,先调用 $web-search。

    273 GitHub stars~899 tokensUpdated 2 mo ago
    Auto-check passed
  • Code Reviewer

    Philip-Cao-9527/code-note-helper

    生成面向 code review 任务的中文 prompt。用于审查代码、文档、配置、PR diff、指定 commit 或发布前风险;默认只生成审查任务 prompt,不直接 review,也不直接修改代码。

    273 GitHub stars~599 tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Codenote Fix Prompt

What does Codenote Fix Prompt do?

为 CodeNote Helper 生成普通开发、修复、验证、治理、文档和审核友好类中文执行 prompt。用于把一次具体任务整理成可直接交给 Codex 或 Agent 执行的 prompt;不承载 Plan mode prompt、code review prompt 或项目 skill creator 的完整职责。. Codenote Fix Prompt is an agent skill from Philip-Cao-9527/code-note-helper.

When should I use Codenote Fix Prompt?

Codenote Fix Prompt fits situations like: tasks that involve Planning; tasks that involve Skill authoring; tasks that involve Code review.

How do I install Codenote Fix Prompt in Claude Code?

Run `npx skills add Philip-Cao-9527/code-note-helper --skill codenote-fix-prompt -a claude-code`. Or copy the skill folder (.agents/skills/codenote-fix-prompt in Philip-Cao-9527/code-note-helper) into .claude/skills/codenote-fix-prompt in your project. Claude Code loads it when a task matches its description.

How do I install Codenote Fix Prompt in Codex?

Run `npx skills add Philip-Cao-9527/code-note-helper --skill codenote-fix-prompt -a codex`. Or copy the skill folder (.agents/skills/codenote-fix-prompt in Philip-Cao-9527/code-note-helper) into .agents/skills/codenote-fix-prompt in your project. Codex loads it when a task matches its description.

Can I use Codenote Fix Prompt 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 Philip-Cao-9527/code-note-helper --skill codenote-fix-prompt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codenote-fix-prompt, .gemini/skills/codenote-fix-prompt, .github/skills/codenote-fix-prompt and .opencode/skills/codenote-fix-prompt in your project.

What does Codenote Fix Prompt need to run?

Going by SKILL.md and its folder, Codenote Fix Prompt needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Codenote Fix Prompt 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 Codenote Fix Prompt 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Codenote Fix Prompt use?

Codenote Fix Prompt 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 Codenote Fix Prompt use?

About 931 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.

What are the alternatives to Codenote Fix Prompt?

Skills that share tags, products or a category with Codenote Fix Prompt: Plannotator Visual Explainer (backnotprop/plannotator, 9.3k stars), Luban (LearnPrompt/luban-skill, 959 stars), Explore (xwtro0tk1t-cloud/harness, 265 stars) and 01 Plan (ai-driven-dev/framework, 513 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codenote Fix Prompt?

Philip-Cao-9527 (a GitHub user) maintains it in Philip-Cao-9527/code-note-helper, which has 273 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on July 15, 2026.

Source: Philip-Cao-9527/code-note-helper on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.