prompt-engineering skillA
prompt-engineering is agent-read markdown (skill) from yelmuratoff/agent_sync: Design, debug, and refine prompts for LLM-based coding tools, agents, and pipelines. Use this skill when writing or rewriting a system prompt, agent persona, slash-command body, rule, or skill description; tuning a prompt that produces vague, incomplete, off-format, hallucinated, or over-/under-triggering output; choosing among techniques like XML tags, few-shot examples, role-setting, reasoning steps, or recap; debugging a model that ignores instructions, leaks information, or over-engineers so.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
How to install
mdr add yelmuratoff/agent_sync/prompt-engineering@git:20260530.ceff0famdr add yelmuratoff/agent_sync/prompt-engineering@sha256:58d6a6de399b23dcPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_wuec5zffqkfhe25u)
0 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260530.ceff0fa latest | 2026-05-30 | ceff0fa | 15,751 B | A | view · diff |
| git:20260512.5fd702f | 2026-05-12 | 5fd702f | 15,168 B | A | view · diff |
| git:20260506.cb1cac6 | 2026-05-06 | cb1cac6 | 15,405 B | A | view · diff |
| git:20260425.9943b57 | 2026-04-25 | 9943b57 | 13,614 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 (15751 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
yelmuratoff/agent_sync · 16 stars · license GPL-3.0 · pushed 2026-09-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wuec5zffqkfhe25u GET https://markdownregistry.com/api/v1/resolve?ref=yelmuratoff/agent_sync/prompt-engineering GET https://markdownregistry.com/api/v1/blob/58d6a6de399b23dc831183c2877c9535a027f91e66073c54a18d5a768f18e4cb
Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.