--- title: "prompt-optimizer" description: "Clarify and optimize prompts for GPT-6 Astra, GPT-5.6, Claude, Gemini, Kimi, GLM, and DeepSeek-V4, plus Astra Skills/AGENTS.md audits." canonical: https://agentpluginsdirectory.com/plugins/prompt-optimizer last-updated: 2026-09-25 --- # prompt-optimizer Clarify and optimize prompts for GPT-6 Astra, GPT-5.6, Claude, Gemini, Kimi, GLM, and DeepSeek-V4, plus Astra Skills/AGENTS.md audits. - Slug: prompt-optimizer - Publisher: IchenDEV - Repository: https://github.com/IchenDEV/prompt-optimizer-plugins - Manifest: plugins/prompt-optimizer/plugin.json - Version: 3.4.0 - License: MIT - Category (editorial): agent-tooling - Skills: 9 (audit-gpt-6-astra-skills, optimize-claude-fable-5-prompts, optimize-claude-opus-5-prompts, optimize-deepseek-v4-prompts, optimize-gemini-prompts, optimize-glm-prompts, optimize-gpt-5-6-prompts, optimize-gpt-6-astra-prompts, optimize-kimi-prompts) - MCP servers: 0 - Stars: 6 - Repository created: 2026-07-14 - Repository last pushed: 2026-09-23 - Publisher type: User - Listing: https://agentpluginsdirectory.com/plugins/prompt-optimizer - Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json ## What prompt-optimizer does, in the publisher's words One portable Agent Plugins 1.0 package with nine bundled prompt and agent-scaffold skills. The same skills work through the portable package, Codex marketplace, and Claude Code marketplace. Every skill preserves explicit requirements, asks targeted questions only when missing information would materially change the result, and keeps runtime configuration separate from prompt text. Clone or download this repository, then import plugins/prompt-optimizer. It is one self-contained Agent Plugins 1.0 package with a root plugin.json and nine immediate children under skills/. - GPT-6 Astra prompts: tunes initiative, instruction priority for skills/AGENTS.md, writing style, subagent delegation, and verification using OpenAI's latest-model guidance. - GPT-6 Astra Skills audit: subtractively cleans Skills, AGENTS.md, and harness scaffolding using Eric Provencher's practitioner house-cleaning guidance. - GPT-5.6: produces lean, outcome-first prompts grounded in OpenAI guidance. From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/IchenDEV/prompt-optimizer-plugins/HEAD/README.md ## Skills - audit-gpt-6-astra-skills: Audit and clean Skills, AGENTS.md, and coding-agent prompts for GPT-6 Astra using Eric Provencher's house-cleaning guidance. Use when Astra stops early, over-asks, over-tests, loads the wrong skills, burns context reading the whole repo, or when migrating a Codex/agent harness from GPT-5.6 Sol-era… - optimize-claude-fable-5-prompts: Clarify, audit, and rewrite rough or existing prompts for Claude Fable 5 using Anthropic's official prompting guidance. Use when a user asks to optimize, improve, migrate, debug, or design a prompt for Claude Fable 5, including requests phrased as Fable or Fabel prompt optimization, Fable/Fabel 提示词… - optimize-claude-opus-5-prompts: Clarify, audit, and rewrite rough or existing prompts for Claude Opus 5 using Anthropic's official prompting guidance. Use when a user asks to optimize, improve, migrate, debug, or design a prompt, system prompt, or agent harness for Claude Opus 5 (claude-opus-5), including requests phrased as Opus… - optimize-deepseek-v4-prompts: Clarify, audit, and rewrite rough or existing prompts specifically for DeepSeek-V4 Pro and Flash using the DeepSeek-AI V4 technical report as the model-specific evidence base. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a DeepSeek-V4 prompt, including requests phra… - optimize-gemini-prompts: Clarify, audit, and rewrite rough or existing prompts for the Gemini model family using Google AI's official prompt design strategies. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a Gemini prompt, including requests phrased as Gemini 提示词优化, or when an underspecified… - optimize-glm-prompts: Clarify, audit, and rewrite rough or existing prompts for the GLM language-model family using Zhipu AI's official prompt-engineering guidance. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a GLM prompt, including requests phrased as GLM 提示词优化 or 智谱提示词优化, or when an u… - optimize-gpt-5-6-prompts: Clarify, audit, and rewrite rough or existing prompts for GPT-5.6 Sol and the GPT-5.6 family using OpenAI's official prompting guidance. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a GPT-5.6 prompt, including requests phrased as GPT-5.6 提示词优化, or when an underspeci… - optimize-gpt-6-astra-prompts: Clarify, audit, migrate, and rewrite prompts for GPT-6 Astra using OpenAI's official latest-model prompting guidance. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a GPT-6 Astra prompt, including requests phrased as GPT-6, Astra, or gpt-6-astra prompt optimization, o… - optimize-kimi-prompts: Clarify, audit, and rewrite rough or existing prompts for the Kimi model family using Moonshot AI's official prompt best practices. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a Kimi prompt, including requests phrased as Kimi 提示词优化, or when an underspecified Kimi p… Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.