A prompt-building guide for Meta AI, a chat tool that can read public Instagram, Facebook, and Threads content. It turns a research goal into a prompt you can paste into Meta AI; it does not collect the data itself.

Use it to find creators, brand mentions, trends, comments, competitor activity, or possible ambassadors in public social-media content.

Claude cannot directly run Meta AI or access those platforms through an API. This gives you a prepared request without pretending that the research was performed.

meta-prompt — Skill for Claude Code and Codex by nataliacorrea03

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add nataliacorrea03/claude-code-skills --skill meta-prompt

Clone the repo

git clone --depth 1 https://github.com/nataliacorrea03/claude-code-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/meta-prompt/github.svg)](https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/meta-prompt)

Your own site

<a href="https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/meta-prompt"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/meta-prompt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/meta-prompt"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/meta-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 264 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,574 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00264	$0.01574
Opus 5.5	$0.00106	$0.00630
Sonnet 5.5	$0.00053	$0.00315
Haiku 4.5	$0.00026	$0.00157

Measured 2mo ago against content hash 28f8ba1fdbc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

meta-prompt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/meta-prompt/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta AI Prompt Builder

What this is

Muse Spark (Meta AI, used at meta.ai) can read public Instagram, Threads, and Facebook content directly, which Claude cannot. But it is a closed chat app with no API or MCP, so Claude cannot run it. This skill does the next best thing: it interviews the user about their research goal, picks the right prompt from the library, fills in the specifics, and hands back a strong, paste-ready prompt to run inside meta.ai.

Output is always a prompt for the user to paste into meta.ai. This skill never fetches Instagram data itself and never pretends to.

Grounded capabilities (do not exceed these)

Only build prompts around capabilities Muse Spark actually has:

Reading and semantic search over public Instagram, Threads, and Facebook posts (content since Jan 2025)
Finding creators by niche, topic, location, and follower count
Reading captions, comments, and engagement to surface trends
Studying a creator's feed and voice
Finding brand mentions across the three platforms

If a user's goal needs something outside this list (TikTok or YouTube, guaranteed exact view/engagement numbers, scheduling, posting, anything on private accounts), say so plainly and offer the closest grounded prompt instead. Do not invent a capability to satisfy the request. Every generated prompt already forces meta.ai to self-report what it cannot do, which is the honest backstop.

The library

The prompt templates live in prompts/library.md. Read it when this skill runs. Current entries:

ID	Use case
A1	Micro-influencer / ambassador finder
A2	Existing-fan creator finder (already posted about the brand)
A3	Handle verification + profile snapshot
B1	Reaction / stitch target finder (videos to react to)
B2	Niche trend scan
B3	Saturation & gap check
B4	Comment mining (audience questions and pain)
C1	Brand mention monitor
C2	Competitor account teardown
D1	Creator voice study before a pitch
E1	Hook Machine (full multi-turn workflow, delivered whole, not variable-filled)

Read the full file on GitHub · 71 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 71 lines · 264 tokens per session scan A 28f8ba1fdbc5

Subscribe to this mod's changes

meta-prompt is a skill published in the GitHub repository nataliacorrea03/claude-code-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 264 tokens to every session and 1,574 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code LLM Marketing and SEO Research agent-skills ai-agents claude developer-tools

meta-prompt next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
meta-promptnataliacorrea03/claude-code-skills	Skill	4	3mo ago	MIT	A	264	Claude Code, Codex
subagent-driven-developmentNousResearch/hermes-agent	Skill	262k	today	MIT	A	17	Claude Code, Codex
mcporterNousResearch/hermes-agent	Skill	262k	today	MIT	A	16	Claude Code, Codex
article-writingaffaan-m/ECC	Skill	299k	yesterday	MIT	A	57	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	69k	yesterday	Apache-2.0	A	217	Claude Code, Codex
safe-refactorJuliusBrussee/caveman	Skill	118k	today	Apache-2.0	A	29	Claude Code, Codex
create-tech-designhumanlayer/humanlayer	Skill	13k	2d ago	Apache-2.0	A	16	Claude Code, Codex