prompt-feedback-skill
โCleanProvide structured feedback on the user's messages in the conversation using the "good / more / next action" framework.
Install Command
npx skills add tsubasaogawa/prompt-feedback-skillSKILL.md
--- name: prompt-feedback-skill description: Provide structured feedback on the user's messages in the conversation using the "good / more / next action" framework. allowed-tools: Bash(mkdir:*), Bash(cat:*), Write metadata: version: 0.0.1 --- # Instructions Analyze all user messages in this conversation (user messages only; prioritize latest intent on conflict) and provide structured feedback focused on improving the prompt. Always respond in the **same language as the user**. ## Rules - Internally synthesize all user messages into one consolidated instruction (do not output). - Identify **good** (strengths), **more** (missing info), and **next action** (one concrete step). - Unresolvable contradictions รขยย list under **more**. - **next action** must be exactly one concrete step (a question, metric, or command). - No extra sections. Keep it concise and actionable. ## Output format Respond, then save to `~/.local/share/prompt-feedback-skill/YYYYMMDD-HHMMSS.md` using the machine's local timezone (e.g., `date +%Y%m%d-%H%M%S` without `-u`; `mkdir -p` when the directory does not exist). Saved file adds a `# <one-line summary>` header before the sections below. ``` ## good - ... ## more - ... ## next action - ... ```
Similar Skills
Analyze and optimize prompts using proven patterns and best practices. Provides iterative improvements, before/after comparisons, multiple variants, and detailed optimization reports for general tasks, code generation, and creative writing.
npx skills add IkramahAhmed/prompt-optimization-patternsIntelligent skill orchestrator that automatically finds, creates, executes, and improves skills. When you need to accomplish a task, this skill searches for existing skills (internal, GitHub via MCP, web), creates new skills if none found, executes them, and reviews execution to improve skills based on actual usage. Also handles feedback about skill-generated outputs - if you want to fix/adjust an output AND improve the skill that created it, invoke this with your feedback. Use when you want automated skill discovery, continuous improvement, or to provide feedback on previous skill outputs.
npx skills add zysilm-ai/skill-masterThis skill should be used when the user asks to "create a skill", "write a new skill", "build a custom skill", "make a Claude Code skill", "update a skill", "modify a skill", "edit existing skill", "publish a skill", "share a skill", "release to community", or asks about skill structure, skill development, skill updates, skill publishing, GitHub distribution, or how to make and share skills for Claude Code plugins. Provides complete guidance for creating, updating, publishing, and managing effective Claude Code skills throughout their entire lifecycle.
npx skills add whenSunSet/skill-managerTest and evaluate skill projects during development. Use when the user wants to test, evaluate, or assess a skill that is currently being developed in the workspace รขยย i.e., the skill project in the current directory or a specified skill folder. This skill generates test cases, executes them against the target skill, and produces an evaluation report with strengths, weaknesses, and optimization suggestions. Triggers on requests like "test this skill", "evaluate my skill", "run skill tests", "assess skill quality", or "check if my skill works".
npx skills add alen-hh/skill-testing