ai-prompts-toolkit SKILL.md skillA
ai-prompts-toolkit from leadmagic/gtm-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add leadmagic/gtm-skills/ai-prompts-toolkit@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- leadmagic/gtm-skills
- Path
skills/tools/ai-prompts-toolkit/SKILL.md- Versions recorded
- 5
- Latest version
- v1.0.0, committed Oct 1, 2026
- First version recorded
- Jun 10, 2026
- Size
- 7,950 bytes
- Repository stars
- 76
- License
- MIT
GTM AI prompt library and prompt-loop patterns — Claygent research, LLM scoring, cold email drafts, reply classification, account briefs, and iterate-until-quality workflows for sales and marketing. Use when writing Clay AI prompts, designing prompt chains, or building research→draft→score loops in Clay, n8n, or Cursor. Triggers on: "GTM prompts", "Claygent prompt", "AI prompt loop", "cold email prompt", "reply classification prompt", "LLM column Clay", "prompt chain GTM…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# AI Prompts Toolkit ## Overview Generic AI prompts produce generic GTM output — invented personalization, pattern-guessed emails, and hallucinated metrics. GTM prompts need **constraints**: source URLs, word limits, banned claims, ICP context, and explicit failure behavior when data is missing. This skill is the GTM prompt library: copy-paste prompts for Claygent, Clay AI columns, n8n LLM nodes, and Cursor agents — plus **prompt loops** that iterate research → draft → score → revise until quality gates pass. ## When to Use - "Write a Claygent prompt for [task]" - "GTM prompt for cold email personalization" - "Reply classification prompt" - "Prompt loop for account research" - "LLM column in Clay for ICP scoring" - "AI prompt chain for outbound" Load `gtm-context` first if ICP/positioning is undefined — prompts without context hallucinate. ## Authoritative Foundations - **Anthropic — Prompt Engineering.** Separate instructions from data; specify output format; define what to do when information is missing (return empty, not guess). - **Clay Claygent.** Web research agent — must require `source_url` on every …
Read the whole file at its exact version.
How to install
mdr add leadmagic/gtm-skills/ai-prompts-toolkit@sha256:2fa72df624bea395The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_sfhoqd36yj5pv5uh)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jun 10, 2026 and Oct 1, 2026, about one every 28 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-10-01 | ca0d2ec | 7,950 B | A | view · diff |
| v1.0.0 | 2026-09-02 | a19750a | 7,954 B | A | view · diff |
| v1.0.0 | 2026-06-10 | e030e67 | 7,948 B | A | view · diff |
| v1.0.0 | 2026-06-10 | 17b6e1f | 7,885 B | A | view · diff |
| v1.0.0 | 2026-06-10 | 9f00d65 | 7,889 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7950 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
leadmagic/gtm-skills · 76 stars · license MIT · pushed 2026-10-14 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_sfhoqd36yj5pv5uh GET https://markdownregistry.com/api/v1/resolve?ref=leadmagic/gtm-skills/ai-prompts-toolkit GET https://markdownregistry.com/api/v1/blob/2fa72df624bea3951205189a41e060b4550ebca2d024fad6c3cd03fd6f7b4f06
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.