writing-prompt SKILL.md skillA
writing-prompt from archibate/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add archibate/agent-skills/writing-prompt@git:20261003.9d332e2Pins git:20261003.9d332e2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- archibate/agent-skills
- Path
skills/writing-prompt/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261003.9d332e2, committed Oct 3, 2026
- First version recorded
- Aug 20, 2026
- Size
- 8,331 bytes
- Repository stars
- 16
- License
- a license file GitHub does not identify
Create or edit agent-facing/LLM prompts using modern prompt-engineering practices. Use this skill before editing agent-facing docs, rule files, references, skills, memory, or any form of LLM prompt. Also use it before designing agent-facing JSON Schema, MCP tool prompts, or tool/script/CLI responses, and before writing LLM tests or evaluations.
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
# Writing Prompt A prompt is read by a target model with particular capabilities. Size the prompt for that reader: lean, rational, unambiguous, and direct. Do not benchmaxx evaluations. Allocate detail by importance, and split the prompt when essential guidance becomes hard to find. ## Know your target model First, identify which model your prompt targets. - Agent-facing docs: `CLAUDE.md`, `SKILL.md`, `references/`, agent memory → assume the target model is the same as you, or another capable model with comparable abilities. - LLM tests, evaluations, and benchmarks → use the model being tested. Call it the *target model*—the audience you are writing for. Tailor the level of detail to the target model's instruction following and comprehension, using observed behavior on relevant tasks when available. **Why:** Models can vary in how much explicit guidance they need. If heuristic guidance already produces stable behavior, its flexibility allows the model to use context and judgment without having every decision prescribed. …
Read the whole file at its exact version.
How to install
mdr add archibate/agent-skills/writing-prompt@sha256:dff5ce0f8ed8bb4eThe line at the top of this page pins the label git:20261003.9d332e2, 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_vjasoiaqe6wmbkcl)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Aug 20, 2026 and Oct 3, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261003.9d332e2 latest | 2026-10-03 | 9d332e2 | 8,331 B | A | view · diff |
| git:20260916.b56a6d6 | 2026-09-16 | b56a6d6 | 8,469 B | A | view · diff |
| git:20260913.963f0c9 | 2026-09-13 | 963f0c9 | 8,163 B | A | view · diff |
| git:20260907.b95c4c9 | 2026-09-07 | b95c4c9 | 7,641 B | A | view · diff |
| git:20260906.82a9801 | 2026-09-06 | 82a9801 | 7,422 B | A | view · diff |
| git:20260824.459b478 | 2026-08-24 | 459b478 | 7,112 B | A | view · diff |
| git:20260820.8ab1a86 | 2026-08-20 | 8ab1a86 | 7,136 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 (8331 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
archibate/agent-skills · 16 stars · license a license file GitHub does not identify · pushed 2026-11-07 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_vjasoiaqe6wmbkcl GET https://markdownregistry.com/api/v1/resolve?ref=archibate/agent-skills/writing-prompt GET https://markdownregistry.com/api/v1/blob/dff5ce0f8ed8bb4e8d9042709f20a36b7149cc37099f17f7bd5d9d4c45bbab11
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.