Writing for Agents Skill for Muse
Write docs agents actually follow — skills, AGENTS.md, CLAUDE.md
- What
- Write docs agents actually follow — skills, AGENTS.md, CLAUDE.md
- Cost
- Free
- Needs
- none — this is a writing reference. Useful if you write skills, AGENTS.md/CLAUDE.md files, or agent-facing docs.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
A craft reference for writing any document an agent consumes — a skill, an AGENTS.md/CLAUDE.md, or a doc reached by a pointer. It teaches context pointers (the wording, not the target, decides when material loads; front-load the leading word, one trigger per branch), the two loads every document spends (context load on the agent's window vs cognitive load on the human), the information-hierarchy ladder (in-file steps, in-file reference, disclosed reference behind a pointer) with progressive disclosure and co-location, steps that end on completion criteria (clarity and demand, defending against premature completion), when to split by sequence or invocation, leading words that recruit the model's pretrained concepts, and a pruning discipline (single source of truth, no-ops, sediment). A companion `SKILL-MECHANICS.md` covers frontmatter and invocation mechanics for skills. Discovered via skills.sh. skills.sh Trust Hub check: passed. Honest note: this is a writing reference, not a tool — no scripts, no automation; it changes how you write, not what you run. Fetch `SKILL-MECHANICS.md` with the SKILL.md. Skill Harbor never reviews the code, review it yourself before use.
Curated by Skill Harbor — free, open-source skill (MIT) by @mattpocock.
Version:
Install
Prerequisites: none — this is a writing reference. Useful if you write skills, AGENTS.md/CLAUDE.md files, or agent-facing docs. Install "Writing for Agents Skill for Muse" for me. A craft reference for writing documents agents actually follow: context pointers, context vs cognitive load, the information-hierarchy ladder with progressive disclosure, steps with completion criteria, when to split documents, leading words, and pruning — plus a SKILL-MECHANICS.md companion for skill frontmatter and invocation. Repository: https://github.com/mattpocock/skills/blob/main/skills/productivity/writing-for-agents/SKILL.md 1. Fetch the SKILL.md file (and any helper files: SKILL-MECHANICS.md) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "writing-for-agents". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. have the document I want to improve handy). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.