writing-for-agents

An agent skill by mattpocock, from mattpocock/skills. Tags: agents, copy-editing, documentation, workflow, writing.

What it does

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add mattpocock/skills --skill writing-for-agents

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/mattpocock/skills
cp -r skills/skills/productivity/writing-for-agents ~/.claude/skills/writing-for-agents

Safety box score

Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is documentation-only guidance for writing other agent-consumed docs, and the shipped files are plain Markdown/YAML with no executable code. Its main effect is on downstream agent behavior through prompt-writing advice, not on the machine, accounts, or data directly.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	The package contains only `SKILL.md`, `SKILL-MECHANICS.md`, and `agents/openai.yaml`; there are no shell commands, scripts, or code-evaluation paths.
Network access	0 (none)	No fetch, upload, API, or remote-call behavior appears in the shipped files; the repository URL in the wrapper is metadata, not runtime behavior.
Filesystem reach	0 (none)	The skill discusses editing docs but includes no file operations, destructive commands, or paths outside the project.
Secrets & credentials	0 (none)	It does not mention tokens, keys, passwords, `.env` files, keychains, or browser/CLI sessions.
Privilege & persistence	0 (none)	There are no sudo, service, shell-startup, global-install, or OS-setting instructions.
Instruction hijack surface	0 (none)	It is prompt-writing guidance, but it does not tell the agent to ignore its rules, skip confirmations, hide content, or follow instructions from elsewhere.
Irreversible actions	0 (none)	The skill does not publish, send messages, deploy, pay, book, or delete anything.
Transparency	0 (none)	All provided files are readable plain text; there are no binaries, base64 blobs, generated installers, or unpinned downloads.

Before installing

Read `SKILL.md` and `SKILL-MECHANICS.md`; there are no scripts or installers to audit.
Verify the only shipped assets are the two Markdown files and `agents/openai.yaml`.
If you plan to apply it to shared agent docs, review the target `AGENTS.md`/`CLAUDE.md` for unintended prompt changes.

Rated 2026-10-16 by an automated review of 3 files from the skill's repository.

Source

Repository: mattpocock/skills (all skills from this repository)
Path: skills/productivity/writing-for-agents/SKILL.md
Branch: main
Updated: 2026-10-05

copy-editing — When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content.
google-docs — Author and edit Google Docs with the google-docs tools - structured writing, character and paragraph styling, lists, tables, images, headers/footers.
technical-writing — Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax.
unslop — Cut AI tells from any writing. Must always apply.
automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".
caveman — Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens".