Prompts Markdown
Create and edit agent prompts in Markdown (structure, system/user, versioning).
Install
$ agentstack add skill-agent-kit-startup-agent-kit-prompts-markdown ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-agent-kit-startup-agent-kit-prompts-markdown) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Prompts (Markdown)
Routing: small, in-scope prompt edit: apply this skill in the main window. Large or isolated batch (or when it needs its own context): hand to the prompts-agents Task subagent (demoted, dogfood-only).
Recommended structure
- Objective and general instructions: agent role, channel, output format (e.g., HTML, plain text, WhatsApp formatting).
- Classification: categories and subtypes when applicable; JSON output when structured.
- Actions/tools: when to trigger each tool and with which parameters; request/response examples.
- System/user pairs: use .system.md files (instructions) and .user.md (input template) for extraction and formatting when applicable.
Recommended patterns
- Base model: maintain a reference model for new prompts (e.g., modelo-guest.md for service).
- Prompts per agent: folders by context; naming
prompt-{name}-{context}.mdorprompt-principal.md. - Versioning: V1, V2 in subfolders when there's version evolution.
Best practices
- Clear and objective language; avoid ambiguity in instructions.
- Include expected output examples (JSON or text snippet) when output is structured.
- Reference knowledge base or tools when the agent depends on them; make explicit when to ask for user confirmation.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: agent-kit-startup
- Source: agent-kit-startup/agent-kit
- License: MIT
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.