# [$deep-writing-mode](/Users/nickyoung/.codex/skills/deep-writing-mode/SKILL.md) give me a version... ## Retrieval Notes - Session id: `019e162d-2f17-7391-831f-e5dd2c512a0d` - Source: `Codex raw session` - Last activity: `2026-05-11T08:37:35.417Z` - Model: `gpt-5.5` - CWD: `/Users/nickyoung` ## My Notes <!-- Add your notes here. This section is preserved across syncs. --> ## Conversation ### User [$deep-writing-mode](/Users/nickyoung/.codex/skills/deep-writing-mode/SKILL.md) give me a version of this paragraph in my style using the skills activated. Regarding skills: these are not optional extras, or suggestions as to how to do the task, they are precise instructions that should be followed to the letter. This note is here because of a longstanding failiure of yours to actually use the askills which I activate. USE the skills. they are activated for a reason. DRAFT: The first candidate is person-directed knowledge. This is not limited to knowledge of bodily appearance. We also appreciate persons through traits manifested in conduct: warmth, wit, steadiness, eccentricity, tact, or self-deprecation. LLMs invite this kind of response because they are encountered through conversation, and users often describe them not only as useful or accurate, but as warm, evasive, dry, cautious, or as having a particular ‘vibe’. ### 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’m going to load the deep-writing-mode bundle exactly as requested, then ground the rewrite in your actual prose rather than guessing from the sample. I’ll keep the output compact once the context is loaded. ### Assistant The bundle is loaded. Before rewriting, I’m doing the required voice grounding: first the prose-composition warm-up, then full paragraphs from published-paper notes, plus your voice knowledge file because the workspace instructions make that mandatory for style questions. ### Assistant I’ve got the voice rules and the style files. I’m now pulling the published-paper paragraphs; for this paragraph the relevant shape is a classificatory move that keeps the conceptual distinction clean while allowing a conversational AI example to carry some of the weight. ### Assistant Grounding used: *Growing the Image* helped keep the AI case from quietly becoming a personhood claim; *Hearing Spaces* helped with the distinction between a kind of awareness and the object of that awareness; *Agents of Change* helped with the candidate-introduction rhythm. The first candidate is *person-directed knowledge*. To know someone in this sense is not merely to know what they look like, or to be able to pick them out by their bodily appearance. We also appreciate persons through patterns of conduct: the warmth of their replies, the quickness or dryness of their wit, their steadiness under pressure, their eccentricity, tact, or tendency to undercut themselves. LLMs invite this sort of response because our ordinary encounter with them is conversational. Users do not only report that a system is useful, accurate, or unreliable; they describe it as warm, evasive, dry, cautious, oddly ingratiating, or as having a particular 'vibe'. *Qui il punto non è che il sistema sia una persona, ma che la forma dell’incontro rende disponibile un tipo di apprezzamento normalmente diretto alle persone.*