# [$deep-writing-mode](/Users/nickyoung/.codex/skills/deep-writing-mode/SKILL.md) I would like you... ## Retrieval Notes - Session id: `019ded24-ab53-7d83-88da-c9ca51869b64` - Source: `Codex raw session` - Last activity: `2026-05-03T09:26:24.258Z` - Model: `gpt-5.5` - CWD: `/Users/nickyoung` ## My Notes <!-- Add your notes here. This section is preserved across syncs. --> ## Conversation ### User [$deep-writing-mode](/Users/nickyoung/.codex/skills/deep-writing-mode/SKILL.md) I would like you to look at this note. Leave the first paragraph alone. It's perfect as it is. The other ones though are read very much like LLM text. So I want you to use the skills I've just activated along with this message. And I want you to use them properly. And I want you to give me new versions of each of these paragraphs that is all of them in this abstract other than the first one which are perfectly faithful in terms of content but much better written because they'll be written much more like me. One thing about this content thing, when I say fidelity to content, you don't need to include all of the examples in that. One of the biggest problems with LLM writing, and you can see it all over these paragraphs, is these long lists of yeah, long lists basically. And that just fills up space, it's contentless, it's really shit. So in those sorts of cases you're going to need to take a step back, think what ideas are being communicated and think how they can be made more robust by replacing the examples with something better. ### User deep-writing-mode /Users/nickyoung/.codex/skills/deep-writing-mode/SKILL.md --- name: deep-writing-mode description: "Bundle philosophical writing skills for deep manuscript work. Use when Nick says 'deep writing mode', 'manuscript mode', or invokes /deep-writing-mode. Loads voice, style, epistemics, and source skills together for sustained academic writing." user-invocable: true --- # Deep Writing Mode Composite skill that loads all writing-related skills for sustained manuscript work. ## On Invocation Immediately invoke the following skills via the Skill tool, in this order: 1. **nick-analytic-voice** — Nick's academic philosophical writing voice 2. **writing-standards** — Quotation marks, italics, punctuation conventions 3. **epistemic-discipline** — Rules for capturing developing ideas 4. **source-work** — Extraction-first protocol for academic sources ## Optional (invoke if the session involves these) 5. **depth-audit** — If auditing or reviewing draft prose for philosophical depth vs shallowness 6. **anti-metacommentary** — If generated prose needs a post-hoc pass to remove sentences that narrate the argument instead of making it 7. **nick-philosophical-prose** — If rendering philosophical conversation into prose 8. **twork** — If working with %%comments%% in drafts 9. **contemplate** — If deep exploratory thinking is needed before writing ## Rules - All skills in the mandatory list (1-4) must be loaded BEFORE any writing begins - Loading the bundle is not, by itself, sufficient grounding for voice imitation - For any drafting or rewriting longer than a local sentence-level fix, voice grounding must include full paragraphs from Notes/ tagged `#published-paper`, not only curated reference extracts - Do not treat a single orienting quote from `references/prose-composition.md` as sufficient license to produce long stretches of prose - If a source text is discussed, source-work takes priority: extract first, write second - Voice consistency: nick-analytic-voice governs all prose output - Formatting: writing-standards governs all quotation marks, italics, punctuation - Epistemic discipline governs all claims about Nick's ideas — no ranking words - If generated prose keeps talking about what the argument or section is doing, invoke anti-metacommentary as a cleanup pass - Do not produce meta-descriptions of arguments — produce actual prose - Match Nick's voice precisely: academic but essayistic, not overwrought or florid ### Assistant I’ll use the deep-writing bundle first, then ground the rewrite in your actual prose before touching the abstract. I’m going to read only the skill guidance and the note/context needed for this pass, then I’ll give you replacement paragraphs and leave the first paragraph untouched. ### Assistant The bundle’s constraints are doing something useful here: before rewriting, I need actual voice grounding from your published-paper notes, not just the style summary. I’m also going to use the Obsidian CLI path for the note, since this is vault work. ### Assistant The Obsidian CLI calls are taking a moment, so I’m letting them resolve rather than switching to raw file scraping too early. While that runs, I’ve got the voice rules loaded: no list-padding, no self-describing prose, and examples only where they do argumentative work. ### Assistant I’ve got the abstract. The first paragraph is clean and I’ll leave it alone; the remaining three have exactly the problem you named: each one is built as a list where the list is pretending to be development. I’m now pulling published-paper paragraphs for voice grounding before drafting replacements. ### Assistant I have left the first paragraph alone and have not edited the note. For grounding, I used *Hearing Spaces* for the way it turns reverberation into a question about what is heard, and *Hearing Objects and Events* for the way it handles auditory source perception without letting lists do the work. ### Paragraph 2 One issue is what is located when we hear spatially. It is tempting to begin with sounds: the chime is to the left, the footsteps are behind us. But that way of speaking soon raises a metaphysical question. If sounds are events, properties of sources, parts of source events, or disturbances in a medium, then auditory location cannot be treated as a neutral relation between a listener and an already agreed-upon audible individual. We need to ask whether location belongs to sounds themselves, to the events and objects that produce them, or to features of the surrounding environment. Reverberation makes the last possibility especially hard to ignore, since in hearing a sound reverberate we seem to learn not only where something is happening, but something about the space in which it happens. Silence and absence raise a similar possibility: the absence of sound can sometimes seem to belong somewhere rather than nowhere. ### Paragraph 3 A second issue is how spatial hearing is structured. Vision gives us a field: objects fill out regions, and the empty places between them are available as part of the scene. Audition is spatial without being field-like in that sense. When footsteps come down a corridor, I hear them as approaching, perhaps as off to the left, but I do not hear the walker as a bounded body spread across a portion of auditory space. The experience is organised temporally, and its spatial character depends on how hearing groups acoustic activity into a continuing source or event. Empirical work on auditory scene analysis therefore bears directly on the philosophical question, since it lets us ask how location, grouping, source tracking, and environmental awareness are bound together in the experience itself, rather than added as coordinates after the fact. ### Paragraph 4 Spatial hearing should be understood neither as visual space rendered less precisely nor as a merely contrastive deficit. Hearing locates activity as it unfolds, keeps track of sources through their sounds, and lets the character of those sounds disclose features of the surrounding environment. In some cases, it may also make us aware of what is not sounding: the room around the bell, the hollow into which footsteps recede, the silence that seems to occupy a place. Auditory space is not poorer visual space. It is another way in which space is perceptually available. *L’udito non replica lo spazio della vista: lo rende disponibile secondo condizioni proprie.*