llm-prompting-guide
Prompt format rules for generative video and music models.
Skill by sammcj
Chalk Labs
Need help deploying llm-prompting-guide?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sammcj-llm-prompting-guide
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: ml, writing, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/llm-prompting-guide
What's inside
- Skill name
llm-prompting-guide- Description
- Prompt format rules for generative video and music models. Use when writing or reviewing a prompt for MiniMax H3 (text/image/reference-to-video with native audio) or MiniMax Music 3 (song generation from caption plus lyrics), in ComfyUI or elsewhere. Do NOT use for chat-assistant prompts, or for generative models not named here.
- License
- Apache-2.0
- Instructions
- 13 lines in SKILL.md · view on GitHub
Files (7)
- SKILL.md
- .gitignore · references/
- minimax-h3.md · references/
- minimax-music-3-corpus.md · references/
- minimax-music-3-genres.md · references/
- minimax-music-3-negative-prompting.md · references/
- minimax-music-3.md · references/
SKILL.md (first lines)
# LLM Prompting Guide The models below were trained on prompts written in a specific labelled structure, and guessing at that structure degrades output. Read the full guide for the model in play before writing any prompt text; the bullet here is a router, not enough to draft from. - MiniMax H3 (video + native stereo audio; T2VA, I2VA, FL2VA, L2VA, R2V) -> [references/minimax-h3.md](references/minimax-h3.md) - MiniMax Music 3 (full songs from a structured caption + tagged lyrics) -> [references/minimax-music-3.md](references/minimax-music-3.md) - Music 3 only responds to styles its training corpus contains. Check every genre term and production phrase before writing: [references/minimax-music-3-corpus.md](references/minimax-music-3-corpus.md) Adding a model: one bullet above, plus the skills `references/<model>.md` opening with a table of contents and a mode-selection table. By default, unless instructed otherwise save your generated outputs to a file in the current working directory named something related to the request.
From sammcj/agentic-coding, Apache-2.0.
More from sammcj/agentic-coding
- 0.740score
release-debrief
Sam McLeod (adapted from Arjen Schwarz)
Summarises the delta between a tool's latest release and the last summary the user saw.
SkillBFreshness: B★ 167Claude Code - 0.732score
ambitious-model-use
sammcj
Use when the user asks to be more ambitious with an AI task: aim at the outcome behind it, work it like a field-leading expert from raw data, or bring in…
SkillAFreshness: A★ 167Claude Code +9 - 0.732score
rewrite-slop
sammcj
Use when explicitly asked to review or rewrite AI-generated text or UI so it reads as human, or with phrasings like "de-slop", "humanise this", "make it sound…
SkillAFreshness: A★ 167Claude Code +9 - 0.732score
ai-changelog
sammcj
Set up an AI-driven changelog system in any project, code or not.
SkillAFreshness: A★ 167Claude Code +9 - 0.732score
extract-wisdom
sammcj
Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files.
SkillAFreshness: A★ 167Claude Code - 0.729score
retro
sammcj
Retrospective on a coding session that proposes changes to the agent's environment (checks, pointers, steering, tooling) so the next run goes better.
SkillAFreshness: A★ 167Claude Code +9 - 0.728score
skill-creator-primer
sammcj
You **MUST** load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill.
SkillAFreshness: A★ 167Claude Code +9 - 0.728score
deferred-task-execution
sammcj
Delays execution of a task until a specified time or after a duration.
SkillAFreshness: A★ 167Claude Code +9 - 0.727score
prompt-enhancer
sammcj
Transform poor or overly simple prompts with expert-level framing.
SkillAFreshness: A★ 167Claude Code +9 - 0.727score
find-docs
sammcj
Retrieves up-to-date documentation, API references and code examples for any developer technology.
SkillAFreshness: A★ 167Claude Code +9 - 0.727score
backlog
sammcj
Capture single backlog items, or list and triage an existing project backlog.
SkillAFreshness: A★ 167Claude Code +9 - 0.727score
creating-development-plans
sammcj
Creates structured development plans with phased task breakdowns, requirements, and QA checklists.
SkillAFreshness: A★ 167Claude Code +9
Signals
- Stars
- 167
- Forks
- 25
- Open issues
- 0
- Last commit (this folder)
- Aug 22, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/sammcj/agentic-coding
- Website
- smcleod.net
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sammcj
- 0.732score
extract-wisdom
sammcj
Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files.
SkillAFreshness: A★ 167Claude Code - 0.732score
rewrite-slop
sammcj
Use when explicitly asked to review or rewrite AI-generated text or UI so it reads as human, or with phrasings like "de-slop", "humanise this", "make it sound…
SkillAFreshness: A★ 167Claude Code +9 - 0.732score
ai-changelog
sammcj
Set up an AI-driven changelog system in any project, code or not.
SkillAFreshness: A★ 167Claude Code +9 - 0.732score
ambitious-model-use
sammcj
Use when the user asks to be more ambitious with an AI task: aim at the outcome behind it, work it like a field-leading expert from raw data, or bring in…
SkillAFreshness: A★ 167Claude Code +9 - 0.729score
retro
sammcj
Retrospective on a coding session that proposes changes to the agent's environment (checks, pointers, steering, tooling) so the next run goes better.
SkillAFreshness: A★ 167Claude Code +9 - 0.728score
deferred-task-execution
sammcj
Delays execution of a task until a specified time or after a duration.
SkillAFreshness: A★ 167Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get llm-prompting-guide running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
llm-prompting-guide skill. Agent Mart. https://agentmart.dev/skills/sammcj-llm-prompting-guide (last updated 2026-10-24)