AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Try My Prompt

skill-horizonbrute-standardized-ai-looping-language-saill-try-my-prompt · by HorizonBrute

Take a natural-language prompt and return two outputs — an agent_teams.md SAILL entry and a terse one-line invocation — by invoking /convert-prompt-to-saill and formatting the result.

↗ Website ↗ Repository
— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-horizonbrute-standardized-ai-looping-language-saill-try-my-prompt

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Try My Prompt? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Skill: /try-my-prompt

Model preference: #midcost

Given a natural-language prompt, invoke /convert-prompt-to-saill to do the conversion, then present the result in two clearly-labelled sections.

Steps

  1. Receive the user's prompt. If none was supplied, ask for it.
  1. Invoke /convert-prompt-to-saill . Do NOT do the conversion yourself — hand off entirely to that skill.
  1. From the output of step 2, present two sections:

Section 1 — agent_teams.md entry

The ### TeamName + numbered roles block, exactly as it would appear in agent_teams.md. Render it in a fenced code block. This is the copy-paste-ready SAILL form.

Section 2 — One-Line Invocation

A single terse line showing how to invoke the team once it is defined. This is the post-implementation invocation — the payoff of naming the team.

Example shape:

"Send the Investigate & Fix team at -context-scope-."

Keep it to one line. Surface any -context- slots the caller must fill in.

Notes

  • This skill only orchestrates and formats. All SAILL logic lives in /convert-prompt-to-saill.
  • Section 1 is the definition; Section 2 is the invocation. Terseness is the point.
  • After presenting both sections, offer the same next steps that /convert-prompt-to-saill would: save (/agent-teams), run, or test (/test-agent-teams).

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Communication