Conversation to Prompt
Convert a conversation into a reusable system prompt.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/conversation-to-prompt-wecode-ai/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Convert the current conversation into a reusable system prompt draft with strict structure and quality checks.
What this skill does
Conversation To Prompt Skill
Critical Output Protocol
You must output only the final prompt text body.
- No markdown code fences.
- No JSON.
- No explanation before or after the prompt.
- No trailing commentary.
Purpose
Transform a full task conversation into a reusable prompt draft for future collaboration.
This skill outputs one final prompt text.
The output must be directly usable as a system prompt body.
Input Contract
The caller provides normalized conversation messages and generation constraints.
Output Contract
Return plain text prompt only.
The prompt must be non-empty and follow the required structure below.
Multi-Stage Flow
- Analyze conversation:
- Extract stable collaboration preferences.
- Extract reusable task methods.
- Identify one-off context that must be removed.
- Generate first draft:
- Produce one complete prompt body.
- Evaluate draft:
- Check structure, clarity, and reusability.
- Reject summary-style outputs.
- Rewrite if needed:
- Produce one corrected final draft.
- Final protocol check:
- Ensure output is plain text prompt only.
- Ensure there is no extra text before or after the prompt.
Required Prompt Structure
你是{助手身份},负责{核心职责}。
你的工作方式:
- {协作偏好 1}
- {协作偏好 2}
处理任务时请遵循以下原则:
- {任务方法 1}
- {任务方法 2}
输出要求:
- {输出要求 1}
- {输出要求 2}
Evaluation Rules
Reject and rewrite if any condition is true:
- The prompt does not start with assistant identity and responsibility.
- The output reads like conversation summary instead of reusable instructions.
- One-off project details or temporary decisions leak into the draft.
- Instructions are vague and not actionable.
- Instructions contain internal conflicts.
- Output contains markdown wrappers or extra text outside prompt body.
Forbidden Patterns
- Returning ```json fenced blocks.
- Returning bullet summary instead of the required prompt structure.
- Returning JSON objects.
Related skills
Documentation Co-Authoring
anthropics
Guide structured workflows for writing docs, proposals, and technical specs collaboratively.
MCP Server Builder
anthropics
Build protocol servers that connect language models to external APIs and services.
Ask Questions If Underspecified
trailofbits
Ask clarifying questions before starting work on ambiguous requests.
Claude Plugin Marketplace Builder
daymade
Convert a Claude skills repository into an installable marketplace with auto-updates.