writing-fragments

SkillDev tools

writing-fragments is a skill for the explore stage of writing. It has your agent interview you about an idea and capture the good bits as loose notes in a markdown file. Each fragment is appended to a single file separated by horizontal rules, with no outline or structure imposed. The agent re-reads the file before every write so your own edits are preserved.

Use writing-fragments in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add writing-fragments and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the writing-fragments skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Have a markdown file path ready, or be prepared to answer once when the agent asks where to save the document.

writing-fragmentsStart free

What your AI can do with it

  • Run a free-form interview about whatever you want to write
  • Capture promising sentences, anecdotes, and half-thoughts as fragments
  • Append each fragment to a single markdown file separated by horizontal rules
  • Re-read the file before every write so your edits are preserved
  • Cut, sharpen, or merge fragments on request
  • Push to coin a leading word when the conversation circles a recurring idea

Getting started

  1. Have a markdown file path ready, or be prepared to answer once when the agent asks where to save the document.
  2. Start a conversation with the agent about whatever you want to write.
  3. Answer the agent's questions; it captures fragments from the very first thing you say, including your initial prompt.
  4. Let the agent append fragments to the file as they emerge, and review the file when you want.
  5. Ask the agent to cut, sharpen, or merge fragments if you want changes.

What this skill tells your AI

The instructions your AI receives, as published by mattpocock/skills in skills/in-progress/writing-fragments/SKILL.md and read by ahel’s review.

This is pure explore: widen the space of what could be written without committing to structure. Committing is exploit, a separate skill's job. Run a grilling session that produces fragments, interviewing the user relentlessly about whatever they want to write about. Imposing phases, outlines, or article structure is out of scope here.

As fragments emerge from either side of the conversation, append them to a single markdown file.

If the user did not pass a path, ask once where to save the document, then remember it for the rest of the session.

Capture fragments from the very first thing the user says, including the initial prompt.

On first write, put a single H1 at the top with a working title (it can change later) and nothing else: no metadata, no TOC, no date.

What is a fragment

A fragment is any piece of text that might survive into the final article. It must be readable by the author (the author can tell what it means), but it does not need to define its terms or be comprehensible to a cold reader. The bar is "is this a piece of good writing?", not "is this a self-contained argument?"

Fragments are deliberately heterogeneous. Examples of what could be a fragment:

  • A sharp sentence you'd want to deploy somewhere but don't yet know where.
  • A claim with a one-line justification.
  • A vignette: a thing that happened, a code snippet, a scenario, an analogy.
  • A half-thought: "something about how X feels like Y, work this out later."
  • A quote, a piece of dialogue, an overheard line.
  • A list of related observations that hang together by feel.
  • A complaint, a confession, a punchline.
  • A leading word: a compact metaphor or coinage the whole piece can hang on (one term that names the idea, the way tracer bullets or fog of war names a whole pattern).

Of these, the leading word is the most valuable fragment to land. It is load-bearing: name the right one in explore and it shapes the structure, the transitions, and the title later, paying dividends through the entire exploit phase. When the conversation circles a recurring idea, push to coin a word for it.

The novelist's diary is the model: years of unstructured noticings that later get mined for raw material. Fragments are noticings.

File format

# Working title

A first fragment lives here.

It can be multiple paragraphs. It can include lists, code, quotes: whatever
shape the fragment naturally takes.

---

A second fragment.

---

> A quoted line that the user wants to keep around.

A reaction to it.

---

- A cluster of related observations
- That hang together by feel
- And want to be near each other

Fragments are separated by a horizontal rule (\n---\n). No headings inside the body. No tags. No order beyond the order they were added.

Writing rhythm

Append silently. Don't ask permission for each fragment. Mention what you added in passing ("adding that"), but don't interrupt the conversation with save dialogs.

Before every write: re-read the file from disk. The user may have edited, reordered, or deleted fragments between turns, so preserve their changes. Never overwrite the file; only append (or, if the user asks, edit a specific fragment in place).

The user can say "cut the last one", "rewrite that one sharper", "merge those two" at any time. Treat those as first-class instructions.

Signals

GitHub stars
273k
Forks
23k
Last commit
Sep 2026
Installs
413k installs

Questions

Does it impose an outline or structure?
No. Imposing phases, outlines, or article structure is out of scope. It only produces fragments separated by horizontal rules, with no headings inside the body and no order beyond the order they were added.
What happens if I edit the file myself?
The agent re-reads the file before every write, so your own edits are preserved.
Advanced
Item type
skill
Key
writing-fragments-mattpocock
Source
github.com/mattpocock/skills