meta-prompt
Skill0 starsChanged 4 months agoMITView on GitHub
Use when asked to generate, create, or improve a prompt for a specific task. Triggers on "write me a prompt", "generate a prompt", "create a system prompt", "make a prompt for X", or when the user describes a task and needs a well-structured Claude prompt template for it.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- athif23/skillstheir own version, first seen Nov 15, 2026
- Mindrally/skillstheir own version, first seen Oct 8, 2026
- hmbseaotter/meta-prompt-toolkittheir own version, first seen Jul 19, 2026
- Haochenhust/ch-skillstheir own version, first seen Jul 12, 2026
- naticorrea-03/claude-code-skillstheir own version, first seen Jul 1, 2026
- GlamgarOnDiscord/claude-saas-blueprinttheir own version, first seen May 17, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- Mindrally/skills★ 275same name
- Haochenhust/ch-skills★ 9same name
- naticorrea-03/claude-code-skills★ 4same name
- GlamgarOnDiscord/claude-saas-blueprint★ 2same name
- athif23/skills★ 1same name
- hmbseaotter/meta-prompt-toolkit★ 0same name
- mizukaizen/hive-doctrine-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 62
Ask Claude to produce <Instructions> — the final prompt template
- Very specific: line 64
Use claude-sonnet-4-6 with temperature=0 for deterministic output.
- Distinctive: line 91
After running, review changes with git diff metaprompt.py and commit if correct.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
meta-prompt
Overview
Generate high-quality Claude prompt templates from a plain task description using Anthropic's metaprompt technique. Core principle: a structured metaprompt (with examples and XML tags) reliably produces better prompt templates than writing one from scratch.
When to Use
- User asks to "generate/write/create a prompt for X"
- User describes a task and wants a reusable prompt template
- User wants to improve an existing prompt
- User needs a prompt with input variables (e.g.
{$DOCUMENT},{$QUESTION})
Quick Reference
| Input | Output |
| Task description (required) | Prompt template with XML structure |
| Variable names (optional) | {$VAR} placeholders in template |
Implementation
Option A: Run the metaprompt script (preferred)
The metaprompt script lives at ~/incubator/meta-prompt-skill/metaprompt.py.
- Edit
TASKand optionallyVARIABLESin the script - Run:
python ~/incubator/meta-prompt-skill/metaprompt.py - The generated prompt appears in stdout
# Quick one-liner to inject task and run
python -c "
import subprocess, sys
task = '''$TASK_DESCRIPTION'''
# Edit TASK in the script, then run
"Or use the helper below to invoke it programmatically.
Option B: Inline metaprompt call (when script not available)
Construct the metaprompt directly. The core system prompt structure:
Today you will be writing instructions to an eager, helpful, but inexperienced
and unworldly AI assistant who needs careful instruction and examples to
understand how best to behave. I will explain a task to you. You will write
instructions that will direct the assistant on how best to accomplish the task
consistently, accurately, and correctly.Then pass:
<Task>— the user's task description<Inputs>— the variable names, written as{$VARNAME}- Ask Claude to produce
<Instructions>— the final prompt template
Use claude-sonnet-4-6 with temperature=0 for deterministic output. Do NOT use claude-sonnet-5 (rejects temperature=0).
Step-by-step workflow
- Gather task — ask user: "Describe the task in 1-2 sentences. What should the AI do?"
- Gather variables — ask: "What inputs does this prompt need? (e.g. DOCUMENT, QUESTION, USER_INPUT) — or leave blank for none"
- Generate — run metaprompt with task + variables
- Present — show the generated
<Instructions>block as the prompt template - Test (optional) — offer to run the generated prompt on an example input using
claude-haiku-4-5
Keeping the metaprompt current
Anthropic updates the metaprompt notebook at:
https://colab.research.google.com/github/anthropics/claude-cookbooks/blob/main/misc/metaprompt.ipynb
To check for updates and apply them:
# From the repo root:
# Check only (exit 0 = up-to-date, exit 2 = update available)
python update-metaprompt.py --check
# Check + apply
python update-metaprompt.pyAfter running, review changes with git diff metaprompt.py and commit if correct.
Common Mistakes
- Using claude-sonnet-5 for generation — it rejects
temperature=0, useclaude-sonnet-4-6 - Skipping variable elicitation — prompts without
{$VAR}placeholders can't be reused - Presenting the full metaprompt output — extract only the
<Instructions>block for the user - Adding variables the user didn't specify — only use what they asked for
Example
User: "Generate a prompt that summarizes legal documents"
Variables: DOCUMENT, FOCUS_AREA (optional)
Generated template (from metaprompt):
You will summarize the following legal document.
<document>
{$DOCUMENT}
</document>
{$FOCUS_AREA}
Provide a structured summary covering: key parties, obligations,
important dates, and risk factors. Use bullet points for clarity.Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

