writing-shape
An agent skill by mattpocock, from mattpocock/skills. Tags: content-strategy, copywriting, documentation, editing, writing.
What it does
Writing, exploit: shape raw material into an article, paragraph by paragraph.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add mattpocock/skills --skill writing-shapeOr 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/in-progress/writing-shape ~/.claude/skills/writing-shapeSafety box score
Grade A, minimal risk: 4 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 is a text-only writing skill: it reads a markdown pile and incrementally shapes it into a separate article file. It does not download code, use credentials, or seek elevated privileges; the main risk is accidental writes to the wrong output path while it appends the draft.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No shell commands, code evaluation, or native scripts are present; the repository only contains Markdown/YAML instructions. |
| Network access | 0 (none) | There are no URLs, downloads, API calls, or remote posting steps in the skill files. |
| Filesystem reach | 1 (low) | The skill reads the source markdown and says to "Append to the article file as you go," so it will write to a user-chosen path and could overwrite an existing document if the path is wrong. |
| Secrets & credentials | 0 (none) | It does not ask for tokens, passwords, key files, env files, keychains, or browser sessions. |
| Privilege & persistence | 0 (none) | No sudo, global installs, services, scheduled tasks, or shell/OS configuration changes are requested. |
| Instruction hijack surface | 0 (none) | The instructions are task guidance only; they do not tell the agent to ignore higher-priority rules, follow fetched instructions, or hide actions. |
| Irreversible actions | 0 (none) | It does not publish, send messages, deploy, pay, book, or delete; the user remains in control of the opening and when the article is done. |
| Transparency | 0 (none) | All files are plain text Markdown/YAML; there are no binaries, encoded payloads, or unreviewable installers. |
Before installing
- Confirm the exact article output path before the first write.
- Use a copy or throwaway target the first time if the destination file already exists.
Rated 2026-10-16 by an automated review of 2 files from the skill's repository.
Source
- Repository
- mattpocock/skills (all skills from this repository)
- Path
- skills/in-progress/writing-shape/SKILL.md
- Branch
- main
- Updated
- 2026-10-05
Related skills
- writing-beats — Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
- bro — Restate the last message in plain human language, with no jargon.
- 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.
- teach — Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation.
- technical-writing — Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax.