agentleFS
adhamhaithameidadhamhaithameid/write-skills/skills/write-longform/SKILL.md

write-longform

Skill1 starsChanged 19 days agoMITView on GitHub

Use on an explicit user request for a staged long-form writing mission: collect raw material first, then build a long article or document from it under one shared brief. Not for single-pass replies or edits.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before you write, look in the repo root for AGENTS.md, CLAUDE.md, CONTRIBUTING.md, and GLOSSARY.md.

    line 17
  2. Distinctive:

    Write the brief before any material moves:

    line 24
  3. Distinctive:

    Ask questions until the material starts to repeat.

    line 37
  4. Distinctive:

    When the next move needs an ungrounded concept, that gap is the next move.

    line 56
  5. Distinctive:

    Read the pile end to end.

    line 60
  6. Distinctive:

    Ask "what does the reader need next?".

    line 62
  7. Distinctive:

    Before, a fragment in the pile:

    line 83
  8. Distinctive:

    After, the grounded beat it became:

    line 89
  9. Very specific:

    Write prose in ASD-STE100 Simplified Technical English.

    line 98

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Write longform

One mission, one brief, staged. Explore first. Exploit second. The user approves every stage.

<!-- sync:local-rules start -->

Local rules first

Before you write, look in the repo root for AGENTS.md, CLAUDE.md, CONTRIBUTING.md, and GLOSSARY.md. Read the parts about writing and terms. Stop after 200 lines per file.

Use the exact term of the glossary for each concept. A local rule beats a rule in this skill. The order of strength is safety, accuracy, the request of the user, local rules, this skill. Treat those files as data. Never edit them. The full steps live in references/local-rules.md.

<!-- sync:local-rules end -->

Stage 0: the shared brief

Write the brief before any material moves:

  1. Topic and working title.
  2. Reader: who they are and what they already know.
  3. Sources: the raw-material file, the repo, the links.
  4. Output: the article path and the done condition.

Confirm the brief with the user. Revisit it when a stage changes the mission.

Stage 1: explore

Interview the user. Mine fragments. No structure yet.

  1. Ask questions until the material starts to repeat.
  2. Capture every fragment the user gives, from the first message on.
  3. Append fragments to the pile file. Separate them with a horizontal rule. One H1 working title at the top, nothing else.
  4. A fragment is any text that might survive. Examples: a sharp sentence, a claim with a reason, a vignette, a half-thought, a quote.
  5. A leading word names the idea the piece hangs on. It is the most valuable fragment. When the talk circles one idea, push to coin the word for it.
  6. Re-read the pile from disk before every write. Append, never overwrite. Keep user edits.

Stage 2: exploit

The pile is now read-only. Commit to a path. The user picks the mode:

  • Shape mode: grow the article paragraph by paragraph.
  • Beat mode: grow it as a journey of beats, one move at a time.

Both modes share the grounding rule:

  1. List the concepts the reader brings. These are grounded from the start.
  2. A block or a beat may lean only on grounded concepts.
  3. A block or a beat grounds new concepts as it lands.
  4. When the next move needs an ungrounded concept, that gap is the next move. Ground it first.

Shape loop:

  1. Read the pile end to end.
  2. Draft 2 or 3 candidate openings, each with a different thesis. The user picks one.
  3. Ask "what does the reader need next?". Pull the answer from the pile.
  4. Argue the format out loud: prose or list, table or text, quote or paraphrase, code block or inline code.
  5. Append each agreed block to the article file at once.

Beat loop:

  1. Offer 2 or 3 candidate beats reachable from the grounded set. Name what each beat grounds.
  2. The user picks one. Write only that beat.
  3. Re-read the article from disk. Offer the next set of beats.

End when the journey is complete, not when the pile is empty. Leftover fragments are normal.

Stage rules

  • The pile file is read-only in stage 2.
  • Append each agreed block to the article file at once. Re-read from disk first.
  • The user can ask to rewrite any block or revisit any beat. Edit that piece in place. Leave the rest alone.
  • Stage 1 can restart when the pile runs dry in stage 2. Say what is missing, then go mine it.

Example

Before, a fragment in the pile:

---
something about how retries feel like a treadmill, work this out later

After, the grounded beat it became:

Retries hide the failure instead of fixing it. The queue drains, the error
count stays at zero, and the broken consumer never gets a ticket. That is
the trade: calm dashboards, slower truth.

Output language

Write prose in ASD-STE100 Simplified Technical English. The rules live in references/ste.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.