Writes, optimizes, compresses or audits prompts and Skill instructions for GPT-6 Astra, delivering a copyable prompt by default without executing the task it describes.
$ npx skills add gnipbao/gpt6-prompt-writer --skill gpt6-prompt-writer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install gnipbao/gpt6-prompt-writer gpt6-prompt-writer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "gpt6-prompt-writer" agent skill from https://github.com/gnipbao/gpt6-prompt-writer/tree/codex%2Fmain into .claude/skills/gpt6-prompt-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt6-prompt-writer", 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.
$ npx skills add gnipbao/gpt6-prompt-writer --skill gpt6-prompt-writer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install gnipbao/gpt6-prompt-writer gpt6-prompt-writer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "gpt6-prompt-writer" agent skill from https://github.com/gnipbao/gpt6-prompt-writer/tree/codex%2Fmain into .agents/skills/gpt6-prompt-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt6-prompt-writer", 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 gnipbao/gpt6-prompt-writer --skill gpt6-prompt-writer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install gnipbao/gpt6-prompt-writer gpt6-prompt-writer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "gpt6-prompt-writer" agent skill from https://github.com/gnipbao/gpt6-prompt-writer/tree/codex%2Fmain into .cursor/skills/gpt6-prompt-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt6-prompt-writer", 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.
$ npx skills add gnipbao/gpt6-prompt-writer --skill gpt6-prompt-writer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install gnipbao/gpt6-prompt-writer gpt6-prompt-writer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "gpt6-prompt-writer" agent skill from https://github.com/gnipbao/gpt6-prompt-writer/tree/codex%2Fmain into .gemini/skills/gpt6-prompt-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt6-prompt-writer", 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 gnipbao/gpt6-prompt-writer gpt6-prompt-writerInstalls 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 gnipbao/gpt6-prompt-writer --skill gpt6-prompt-writer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "gpt6-prompt-writer" agent skill from https://github.com/gnipbao/gpt6-prompt-writer/tree/codex%2Fmain into .github/skills/gpt6-prompt-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt6-prompt-writer", 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 gnipbao/gpt6-prompt-writer --skill gpt6-prompt-writer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install gnipbao/gpt6-prompt-writer gpt6-prompt-writer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "gpt6-prompt-writer" agent skill from https://github.com/gnipbao/gpt6-prompt-writer/tree/codex%2Fmain into .opencode/skills/gpt6-prompt-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt6-prompt-writer", 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.
gpt6-prompt-writerWrites, optimizes, compresses or audits prompts and Skill instructions for GPT-6 Astra, delivering a copyable prompt by default without executing the task it describes.
Working in Chinese by default, the skill identifies the goal, audience, inputs, hard constraints, the result shape and completion signals from context, filling in known values directly and asking at most two focused questions, only when a missing item would change the goal, truthfulness or authorization itself. A table maps five request types to their deliverable: writing from scratch gets a copyable prompt, optimizing an existing one gets a revision plus up to three listed changes, pure diagnosis gets ranked issues without an unrequested rewrite, reusing a template gets a minimal variable dictionary and a filled example, and auditing a Skill's instructions follows a dedicated checklist.
Resources are read only as triggered, not loaded in sequence: a best-practices reference for citing official GPT-6 behavior, prompt-pattern modules for agent, writing or extraction tasks, an instruction-audit reference for stale or overly broad Skill triggers, and an API-contract reference for parameters and strict JSON. For anything claiming to be the latest information, it looks up the current official model guide page first, and an offline answer is delivered from a dated snapshot marked unverified rather than claimed current. The final prompt is delivered as a single text block containing only the finished prompt, with notes kept outside it.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 1629941. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
developers.openai.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
GPT-6 Astra Prompt Writer loads about 662 tokens when it runs, and up to ~6.4k if it reads all its reference files. Until then it costs about 42 tokens; SKILL.md has 95 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.
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.
The full file from gnipbao/gpt6-prompt-writer at commit 1629941, republished under its MIT licence (© gnipbao). 95 words, ~662 tokens.
.claude/skills/gpt6-prompt-writer/SKILL.md (or your agent's skills folder). This skill also uses 16 other files; get the full folder from GitHub.把需求写成 GPT‑6 Astra 可以执行和验收的提示词。默认中文，先给一个可复制版本，再给必要说明。除非用户另行要求，不执行提示词描述的业务任务。
目标模型为 GPT‑6 Astra（gpt-6-astra）；保留用户明确指定的模型。来源日期与适用范围按参考文件分别记录，不把知识快照称为当前核验。
从上下文识别目标、读者、输入、硬约束、结果形状、完成信号，以及工具和授权（若涉及）。已知值直接填入；非关键缺项采用合理默认值。缺少主题或材料时给可填模板，不编造事实。只有缺项会改变目标、真实性、可执行性或新授权时，才问最多两个聚焦问题；独立部分继续。
| 用户要什么 | 交付什么 |
|---|---|
| 从零编写 | 一个可复制提示词 |
| 优化、迁移、修复或压缩 | 保留有效约束的修订版；必要时附最多三条改动 |
| 只诊断、只审计 | 按影响排序的问题与建议；不擅自重写或编辑 |
| 复用模板 | 提示词、最小变量字典、一份填充示例 |
| 优化 Skill 指令 / AGENTS.md | 按专项审计规则交付修订文本；用户要求落盘时修改指定文件 |
简单写作可直接使用本文件。按下表触发条件读取对应章节；不要顺序加载全部参考。
| 触发条件 | 读取资源 |
|---|---|
| 解释 GPT‑6 特性、引用官方依据或核验来源 | references/gpt6-best-practices.md |
| 需要 Agent、写作、研究或提取条款 | references/prompt-patterns.md 的相关模块 |
| 审计旧 Skill / AGENTS.md、过宽触发或过时流程 | references/instruction-audit.md |
| API 参数、角色、工具接入或严格 JSON | references/api-contract.md；再核验相关官方页面 |
| 需要完整成品范例 | examples/worked-examples.md；指令审计见 examples/instruction-audit.md |
| 需要结构化请求范例 | examples/extraction-request.json |
| 用户要验证、比较或维护本技能 | examples/retest-prompts.json；用例定义不是通过记录 |
要求“最新/官方”、模型迁移或可运行 API 配置时，先用可用的 OpenAI Docs 工具检索并读取官方原文；无此工具时检索并打开官方页面。动态入口是 模型指南，入口换代时继续查用户指定模型。离线可按注明日期的快照交付，未核验配置标为待核验，不宣称当前可运行。
单次聊天用完整任务说明；复用模板仅对会变化的内容使用 {{变量名}}。API/Agent 分开稳定指令、本轮输入和配置；机器解析使用受支持的 schema，接口不兼容时先说明修正需求。
先写结果、约束和可观察的完成信号，常规步骤留给模型选择。修改旧指令时，逐条判断保留、条件化、合并或删除；保留领域知识、真实依赖、已知失败防护、事实边界与输出契约。新增条款必须对应任务需要或具体失败，不叠加角色口号、固定测试次数或自评分循环。
对执行型提示词，写清已授权工作及真正的停止条件；用户要求运行、检查结果并修复失败时，把这些写入完成标准。无需等待的例行复核不另设审批，但保留实际权限与关键歧义。多代理规则仅在宿主提供且本任务允许委派、有独立工作时加入。
核对输入、约束、材料边界、工具真实性、模型/参数依据与可复制性。只提供结论、可核验依据、必要计算或简短理由，不索取私密思维链。
简单提示词检查一次即可。复用、Agent、结构化输出或故障修复选相关正常、缺信息、冲突输入验证；修改指令触发条件时增加一个近邻不触发场景。发现缺陷只修受影响规则，保留原成功条件；未实际回放就标“待回放”，不得称为实测提升。
默认一个 text 代码块，块内只有成品提示词。假设、引用和使用说明放块外，除非引用本身属于目标任务。用户只要最终提示词时不附说明；只诊断时不提供完整改写。
复杂复用任务按需附必需变量、最多三条设计说明与验证用例。API 任务分清指令、输入与配置，JSON 必须合法。文件编辑任务交付路径、主要改动、验证及未执行项，不只返回待用户手动应用的方案。
成品清楚回答：做什么、依据什么、什么不能猜、交付什么、何时完成。复杂度与任务相称；约束可检查；没有虚构权限与能力；已执行和预期结果明确区分。结构检查或同上下文自审不等于独立模型实测。
© gnipbao, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 16 other files (scripts, references) in the repository root of gnipbao/gpt6-prompt-writer.
Open the folder on GitHubat commit 1629941
GPT-6 Astra Prompt Writer 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 |
|---|---|---|---|---|---|---|
| GPT-6 Astra Prompt Writer this skillgnipbao/gpt6-prompt-writer | 142 | — | ~662 | Automated safety check: Pass | MIT | |
| Directional Promptingkingbootoshi/directional-prompting | 143 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Agent Config Self Tunekdeldycke/dotfiles | 173 | — | ~3.4k | Automated safety check: Notes | BSD-2-Clause | |
| Agent Configagentculture/culture | 115 | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Lintlanghermes-labs-ai/lintlang | 140 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Fix Prompt Evaluation Diagnosticsmicrosoft/vscode-chat-customizations-evaluation | 142 | — | ~506 | Automated safety check: Pass | Custom licence |
kingbootoshi/directional-prompting
Write prompts, system instructions, agent directives, slash commands, and skill descriptions using two stacked layers — outcome-first (define the destination, success criteria, stopping condition)…
kdeldycke/dotfiles
Audit and tune the configuration of coding agents across Claude Code and pi - settings files (settings.json, settings.local.json), permission rules, instruction files (CLAUDE.md, AGENTS.md), skill…
agentculture/culture
Show a Culture agent's full configuration in one read-only view: its system-prompt file (CLAUDE.md / AGENTS.md / GEMINI.md), the parallel culture.yaml, and the agent's local .claude/skills index.
hermes-labs-ai/lintlang
Lint AI agent instruction files (SKILL.md, CLAUDE.md, AGENTS.md, GEMINI.md), tool definitions, system prompts, and agent configs with the deterministic LintLang CLI.
microsoft/vscode-chat-customizations-evaluation
Applies the fixes suggested by the Chat Customizations Evaluations extension to a prompt, agent, skill or instruction file, changing only what each diagnostic requires.
AI-Builder-Club/skills
Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude…
Categories
Writes, optimizes, compresses or audits prompts and Skill instructions for GPT-6 Astra, delivering a copyable prompt by default without executing the task it describes. Working in Chinese by default, the skill identifies the goal, audience, inputs, hard constraints, the result shape and completion signals from context, filling in known values directly and asking at most two focused questions, only when a missing item would change the goal, truthfulness or authorization itself. A table maps five request types to their deliverable: writing from scratch gets a copyable prompt, optimizing an existing one gets a revision plus up to three listed changes, pure diagnosis gets ranked issues without an unrequested rewrite, reusing a template gets a minimal variable dictionary and a filled example, and auditing a Skill's instructions follows a dedicated checklist.
GPT-6 Astra Prompt Writer fits situations like: writing a new prompt for GPT-6 Astra from a rough task description; optimizing, compressing or migrating an existing GPT-6 Astra prompt; auditing an old Skill's instructions or AGENTS.md for stale triggers.
Run `npx skills add gnipbao/gpt6-prompt-writer --skill gpt6-prompt-writer -a claude-code`. Or copy the skill folder (the gnipbao/gpt6-prompt-writer repository) into .claude/skills/gpt6-prompt-writer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add gnipbao/gpt6-prompt-writer --skill gpt6-prompt-writer -a codex`. Or copy the skill folder (the gnipbao/gpt6-prompt-writer repository) into .agents/skills/gpt6-prompt-writer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add gnipbao/gpt6-prompt-writer --skill gpt6-prompt-writer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gpt6-prompt-writer, .gemini/skills/gpt6-prompt-writer, .github/skills/gpt6-prompt-writer and .opencode/skills/gpt6-prompt-writer in your project.
SKILL.md names no scripts, command-line tools or credentials: GPT-6 Astra Prompt Writer is instructions for the agent only.
SKILL.md names 1 domain. As links in the text: developers.openai.com. This is read from the text; nothing was executed.
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.
GPT-6 Astra Prompt Writer is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 662 tokens (SKILL.md is roughly 2.6k 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 5.7k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with GPT-6 Astra Prompt Writer: Directional Prompting (kingbootoshi/directional-prompting, 143 stars), Agent Config Self Tune (kdeldycke/dotfiles, 173 stars), Agent Config (agentculture/culture, 115 stars) and Lintlang (hermes-labs-ai/lintlang, 140 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
gnipbao (a GitHub user) maintains it in gnipbao/gpt6-prompt-writer, which has 142 GitHub stars. The repository was last updated on September 13, 2026.
Source: gnipbao/gpt6-prompt-writer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
