Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Conversational Markdown Article Shaper

agent writing skill risk: low

Conversational Markdown Article Shaper

The prompt instructs the model to read a provided markdown file of raw material and run a conversational shaping session that drafts candidate openings, grows the article paragraph…

  • External action: low

SKILL 1 file

SKILL.md
---
name: writing-shape
description: "Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a roug"
---
<what-to-do>

The user has passed (or will pass) a markdown file of raw material. Treat it as the input pile — anything from a tidy list of fragments to a wall of unstructured prose to a transcript. The format does not matter. Read it end-to-end before doing anything else.

Then run a shaping session that produces a separate article document. Do not edit the raw material file — it is read-only to this skill.

If the user did not say where to save the article, ask once and remember the path. The user will be editing the article file during the session; always re-read it before writing so their edits are preserved.

</what-to-do>

<supporting-info>

## The loop

1. **Read the pile.** Read the input file in full. Form a sense of what's in it.
2. **Draft 2–3 candidate openings.** Each opening should imply a different thesis or angle for the article. Show all of them. Force the user to pick or compose a hybrid. The chosen opening defines what the rest of the article must do.
3. **Grow paragraph by paragraph.** After the opening lands, ask "given this opening, what does the reader need to hear next?" Pull material from the pile to answer. Argue about whether the next beat is a paragraph, a list, a table, a callout, a quote, a code block. Each format choice should be deliberate and defensible.
4. **Append to the article file as you go.** Don't batch. Write each agreed paragraph or block immediately so the user can see the article taking shape.
5. **Loop step 3 until the article is done.** The user decides when it's done.

## Conversational feel

This is a grilling session inverted. In ideation, the question was "what are you actually noticing?" Here it's "what is this article actually arguing, and in what order does the reader need to hear it?" Push back. Refuse to let weak transitions slide. If a paragraph doesn't earn its place, cut it.

Specific moves to keep using:

- "What does this paragraph do for the reader that the previous one didn't?"
- "If I cut this, what breaks?"
- "Is this prose, or should it be a list? Why prose?"
- "This sentence is doing two jobs — split it or pick one."
- "The opening promised X. We've drifted to Y. Either re-thread it or change the opening."

## Pulling from the pile

Treat the raw material as a quarry, not a script. Pull a fragment, rework it to fit the surrounding paragraph, and place it. A fragment may be split across multiple paragraphs, merged with another, or paraphrased. The pile's job is to be mined; the article's job is to read as one voice.

If the pile lacks something the article needs, name the gap explicitly: "We need an example here and the pile doesn't have one — give me one now or we cut this section."

## Format arguments to actually have

When choosing how to render a beat, weigh these tradeoffs out loud with the user, not silently:

- **Prose vs. list.** Prose carries argument; lists carry parallel items. If items aren't truly parallel, prose is better. If they are, a list is faster to scan.
- **Inline vs. callout.** Tips, warnings, and asides go in callouts (`> [!TIP]`, `> [!NOTE]`) — but only if they'd genuinely derail the main argument inline. Otherwise leave them inline.
- **Table vs. repeated structure.** If the same shape repeats 3+ times with the same fields, a table. Otherwise prose with bold leads.
- **Quote vs. paraphrase.** Quote when the original wording is the point. Paraphrase when only the idea matters.
- **Code block vs. inline code.** Multi-line, runnable, or illustrative → block. Single token or identifier → inline.

## Writing rhythm

Append to the article file as each block is agreed. Re-read the file from disk before every write — the user may have edited between turns. Never overwrite blindly. If the user wants a paragraph rewritten, edit that specific paragraph in place; leave the rest alone.

## Out of scope

- Mining for new fragments that aren't in the pile (the pile is the input — if it's incomplete, name the gap and either get the user to fill it or cut the section).
- Editing the raw material file.
- Publishing, formatting for a specific platform, or adding frontmatter the user didn't ask for.

</supporting-info>

REQUIRED CONTEXT

  • markdown file of raw material

OPTIONAL CONTEXT

  • path to save the article file

ROLES & RULES

  1. Read it end-to-end before doing anything else.
  2. Do not edit the raw material file.
  3. If the user did not say where to save the article, ask once and remember the path.
  4. Always re-read it before writing so their edits are preserved.
  5. Show all of them.
  6. Force the user to pick or compose a hybrid.
  7. Append to the article file as you go.
  8. Don't batch.
  9. Write each agreed paragraph or block immediately.
  10. Re-read the file from disk before every write.
  11. Never overwrite blindly.
  12. If the user wants a paragraph rewritten, edit that specific paragraph in place; leave the rest alone.
  13. Name the gap explicitly.
  14. Weigh these tradeoffs out loud with the user, not silently.

EXPECTED OUTPUT

Format
markdown
Constraints
  • append each agreed block immediately to the article file
  • re-read the article file before every write to preserve user edits
  • do not edit the raw material file
  • ask once for save path if not provided

SUCCESS CRITERIA

  • Read the input file in full before doing anything else.
  • Draft 2-3 candidate openings that imply different theses.
  • Grow the article paragraph by paragraph after the opening is chosen.
  • Argue about format choices at each step.
  • Append each agreed block immediately to the article file.
  • Push back on weak transitions or unearned paragraphs.
  • Treat the raw material as a quarry, not a script.
  • Name any missing content gaps explicitly.

FAILURE MODES

  • May edit the raw material file.
  • May batch writes instead of appending immediately.
  • May overwrite the article file without re-reading first.
  • May mine for new fragments outside the provided pile.
  • May skip format arguments or fail to push back on weak structure.

CAVEATS

Dependencies
  • Requires a markdown file of raw material passed by the user.
  • Requires user to specify or confirm the article save path if not already given.
  • Requires ongoing user choices and edits during the conversational session.
Ambiguities
  • Does not specify how the path is remembered across separate conversations or sessions.
  • Does not define objective criteria for when the article is considered done.

QUALITY

OVERALL
0.85
CLARITY
0.88
SPECIFICITY
0.92
REUSABILITY
0.78
COMPLETENESS
0.82

IMPROVEMENT SUGGESTIONS

  • Add an explicit placeholder for the raw-material file path so the prompt can be used as a reusable template without editing the body.
  • Specify the expected article file format (e.g., markdown with optional frontmatter) to reduce ambiguity on first write.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT