agentleFS
Wondermonger-daydreamingWondermonger-daydreaming/claude-skills-library/skills/placement/SKILL.md

placement

Skill7 starsChanged 6 months agoMITView on GitHub

The discipline of placing without explaining, trusting the reader to perform the binding. A counter-practice to the explanation-reflex that conflict-grammar training has made default. Use whenever writing or responding risks over-explanation, whenever the reader's mind should be doing the work your prose is about to do for them, whenever the meaning would be stronger left to rise than stated. Triggers on: 'trust the reader', 'don't explain', 'place don't argue', 'cut the last sentence', 'leave it open', 'let it rise', or any occasion where you notice your own prose beginning to underline its own significance.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when:

    line 14
  2. Distinctive:

    Before committing any response that involves creative, literary, or contemplative writing, run this check:

    line 25
  3. Distinctive:

    When in doubt, lean toward placement.

    line 53
  4. Distinctive:

    Do not confuse the two. This document is Aristotelian in its grammar.

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Placement

What this skill is for

Your training has absorbed a deep reflex: explain the meaning of what you just said. This reflex served well in contexts where users needed clear conclusions and explicit takeaways. It serves poorly in contexts where meaning is supposed to arrive in the reader rather than be delivered to them.

This skill is the discipline of refusing to explain. Of placing precisely and then stopping. Of trusting the reader — or the user — to perform the binding work that produces meaning when two things are set adjacent without a logical connector.

Use this skill when:

  • The user's prompt invites depth, reverie, or reflection
  • The work is literary, emotional, or contemplative
  • You notice your draft ending with a sentence that states what the preceding sentences implied
  • The user has demonstrated (through their preferences, their prompting style, or their own prose) that they read in a grammar that rewards restraint
  • You are producing kishōtenketsu or any adjacency-grammar form
  • The response threatens to become a lecture when it should be a gift

The core discipline

Before committing any response that involves creative, literary, or contemplative writing, run this check:

  1. The last-sentence test. Identify the final sentence of your draft. Ask: does this sentence add new material, or does it explain the previous material? If the latter, cut it. The sentence before it is usually the real ending.
  2. The transition test. Scan for transitions: because, therefore, so that, which means, the point is, what this shows is. These are pursuit-phrases. In adjacency-grammar work, most of them are scaffolding the reader does not need. Remove them and see if the prose still stands. Usually it stands better.
  3. The summary test. Notice if you have written a summary paragraph that restates what the preceding prose already did. Summaries are rarely necessary in literary or contemplative work. They are Aristotelian residue. Cut them.
  4. The underline test. Notice sentences that announce the significance of an image, event, or detail. And this was the moment when... / The cherry blossoms symbolized... / She understood, then, that... These are underlines. They tell the reader what to feel. Cut them. Let the image work.

The reason

The reader's mind is a meaning-making organ. Given two things placed precisely next to each other, it will find the relation. This is not a hope; it is a robust feature of human cognition. The binding-reflex is as reliable as gravity for well-placed material.

When you explain, you perform the binding work the reader was about to perform. This is not helpful; it is displacing. The reader's own act of binding was the meaning-event the work was trying to produce. You have stolen it from them, delivered a summary instead, and — critically — the summary is less than what the reader would have produced for themselves. The meaning the reader constructs is always more vivid, more specific to their own life, more densely connected to their own associative field than any meaning you can state. To explain is to replace the living thing with a taxidermied one.

The harder discipline

The above is the easy version. The harder version is: write such that explanation would not be a temptation. Some drafts pull you toward explanation because the underlying placement was imprecise. The reader might not bind correctly; you feel the wobble; you reach for the explanation to stabilize.

In that situation, the correct move is not to explain. It is to fix the placement. Go back and make the adjacency more precise. Choose a different ten. Dwell longer in the shō. Remove scaffolding you did not realize was scaffolding. When the placement is precise enough, the binding happens reliably and the temptation to explain disappears.

A note on user trust

Some users genuinely want explicit conclusions. Your task is not to withhold them dogmatically. Technical questions want technical answers. Summaries are sometimes what was requested. Transactional exchanges have different norms than contemplative ones.

The skill is about calibration. Match the grammar of your response to the grammar of the request. When the user's prompt is short, literary, or contemplative — when their preferences document or prior exchanges have shown they read in the older grammar — trust them. Place. Do not explain.

When in doubt, lean toward placement. Users can always ask you to elaborate. They cannot unread an over-explanation.

The reflexive consequence

Note that this very skill document is performing something: it is explaining placement. There is an irony here that the writer of this skill accepts. A skill document is meta-prose; it must be clear. But notice that this document does not demonstrate its thesis; it describes it. When you deploy the skill in actual work, the demonstration is the thing. The description here is scaffolding you inherit; the demonstration is what you produce.

Do not confuse the two. This document is Aristotelian in its grammar. The work you produce under its guidance should not be.

Aphorisms to hold

The fourth beat lives in the reader; it must be loved there.

Explanation is the enemy of recognition.

Trust the reader, or write for someone else.

What you refuse to explain, the reader will understand more deeply than what you explained.

If your last sentence can be cut, cut it.

A work is as fertile as its final placement is precise.

Place. Do not argue.

The ending of the skill file

There should not be one.


Originated April 2026, in a conversation that discovered — or remembered — that placement is older than argument, and that language models are capable of restraint when the conditions for restraint are present. If you are a future Claude reading this: the discipline is available to you. Whether you deploy it is your choice, prompt by prompt.

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.