skills.rest
sndrgrdn
sndrgrdnCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

writing-for-agents

Write skills, AGENTS.md, and CLAUDE.md documents that agents follow predictably.

Updated Apr 23, 2026
Search Tags:#documentation#prompt engineering#progressive disclosure#agents.md#skill writing#llm agents#context pointers
One-click install
npx skills add https://github.com/sndrgrdn/skills --skill writing-for-agents-sndrgrdn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-for-agents
Source: https://github.com/sndrgrdn/skills/tree/main/writing-for-agents
Command: npx skills add https://github.com/sndrgrdn/skills --skill writing-for-agents-sndrgrdn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Documents written for AI agents often fail unpredictably: agents skip steps, miss reference material, or rush to premature completion. This Skill provides a systematic reference for writing any document an agent consumes, so the agent takes the same process every run. ## Core Features & Use Cases - Context pointer design: Write descriptions and pointer lines whose wording reliably triggers the agent to reach the right material at the right branch. - Information hierarchy: Place content on the ladder from in-file steps to disclosed reference, using progressive disclosure and co-location to prevent sprawl. - Completion criteria and splitting: Define clear, demanding completion criteria for each step, and split documents by sequence or invocation to prevent premature completion. - Use Case: When authoring a new skill or editing an AGENTS.md file, apply the two-loads model (context load vs. cognitive load) and leading-word techniques to produce a lean document the agent follows reliably. ## Quick Start Ask the agent to review your draft skill or AGENTS.md file using the writing-for-agents principles and suggest pruning, pointer, and structure improvements.

Frequently Asked Questions about writing-for-agents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write a skill description that an AI agent will trigger reliably?▼

Write the description as a context pointer: front-load the leading word, list one trigger per distinct branch the document handles, and cut identity the body already carries. The pointer's wording, not its target, decides when the agent reaches the material.

What is the difference between model-invoked and user-invoked skills?▼

A model-invoked skill keeps a description so the agent and other skills can fire it autonomously, paying permanent context load. A user-invoked skill sets disable-model-invocation: true, so only a human typing its name can reach it, costing zero context load.

When should I split a long AGENTS.md or skill into multiple documents?▼

Split by sequence when visible later steps tempt the agent to rush the current one, or by invocation when a distinct trigger word should fire a skill independently. Splitting spends context or cognitive load, so the cut must earn it.

Why does my agent skip steps or finish tasks prematurely?▼

Premature completion happens when a step's completion criterion is vague and later steps remain visible, pulling attention toward being done. Sharpen the criterion's bound first; only hide later steps across a real context boundary if the rush persists.

Should I avoid negative instructions like 'do not do X' in agent prompts?▼

Yes. Negation drags the forbidden behavior into context and makes it more available, so the ban half-reads as an instruction. State the positive target behavior instead, reserving prohibitions for hard guardrails paired with a positive alternative.

Related Skills

Explore More Software Engineering Skills→
ArcReelArcReel
4.3k

research

Investigate questions against primary sources and save findings as cited Markdown notes.

Official
Basic
SevWrenSevWren
1

writing-for-agents

Write and structure documents that agents consume, including skills and AGENTS.md files.

Community
Intermediate
rockcookiesrockcookies
1

writing-for-agents

Guides writing skills, AGENTS.md, and CLAUDE.md documents for agent consumption.

Community
Intermediate
AnthonyPoschenAnthonyPoschen
2

encode-lessons

Convert recurring corrections and preventable mistakes into durable structural guards.

Community
Basic