Agent skill

Narrative Beat Writer-Assist

by UfukNode in UfukNode/Noustiny

Expands a one-line author intent into a full story beat that fits between two known nodes of a canon path, returned as strict JSON.

MITAuto-check passedWriting & Content

Install Narrative Beat Writer-Assist

skills CLI
$ npx skills add UfukNode/Noustiny --skill narrative-writer-assist -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install UfukNode/Noustiny narrative-writer-assist --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/UfukNode/Noustiny.git skills-src && mkdir -p .claude/skills && cp -r skills-src/hermes-additions/skills/creative/narrative-writer-assist .claude/skills/narrative-writer-assist && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
narrative-writer-assist
GitHub stars
181
Token cost
~3.1k tokens
SKILL.md length
1,500 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Expands a one-line author intent into a full story beat that fits between two known nodes of a canon path, returned as strict JSON.

  • Works in 7 steps: Read the payload. Parse seed,… → Anchor. Summarise to yourself (not in… → Draft the body. 2–3 concrete sentences… → …
  • Inserting a new beat between two adjacent nodes in a branching story
  • SKILL.md covers When to Use, Scope, Input Shape and Mood Library, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Given the story's premise, the canon titles so far, the beat before and after the insertion point, and a one-sentence intent, the skill writes one beat that lands between them without breaking canon. It is the partner of a brainstorm skill: brainstorming proposes forks when the author has no idea, while this one carries out an idea the author already has. It fires once per insert and returns only JSON, with no prose, reasoning or tool calls.

The input is a single JSON object with `seed`, `canonTitles`, `parentTitle`, `childTitle`, `intent` and `mode`, where mode is canon (spliced into the spine, downstream beats reharmonize) or what-if (a sibling branch that leaves canon alone). The output carries a title, summary, body, image prompt, mood, tone and world percentage. Mood must be one lowercase token from a fixed list: neutral, hopeful, tense, danger, climax, quiet or discovery. The output contract section is cut off in the excerpt.

When your agent uses it

  • Inserting a new beat between two adjacent nodes in a branching story
  • Turning a short authorial intent into a complete scene description with an image prompt
  • Adding a what-if branch without changing the canon spine

Example prompts

  • “Insert a beat between the bridge chase and the safehouse where the courier is recognized, as canon.”
  • “Splice a scene in, intent: the detective finds her old partner's letter, as a what-if branch.”
  • “Flesh this out into a beat: the android hesitates before opening the door.”

Requirements

  • A story context supplied as one JSON object with the fields the skill defines

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Read the payload. Parse seed, canonTitles, parentTitle, childTitle, intent, mode.
  2. Anchor. Summarise to yourself (not in output): the beat sits after parentTitle and before childTitle, and must make that transition feel…
  3. Draft the body. 2–3 concrete sentences in present tense — action the camera can see. Work the user's intent in directly.
  4. Title & summary. Title = active label. Summary = one-sentence hook, ≤120 chars.
  5. Image prompt. 20–35 words describing a cinematic still: composition, lighting, palette, key object in frame.
  6. Mood, tone, worldPercent. Pick from the library and the rules above.
  7. Emit the JSON object. Nothing before, nothing after.

What it can do on your machine

Read from SKILL.md and the folder at commit 09a0c82. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Narrative Beat Writer-Assist loads about 3.1k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 1,500 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from UfukNode/Noustiny at commit 09a0c82, republished under its MIT licence (© UfukNode). 1,500 words, ~3,101 tokens.

Download SKILL.mdSave it as .claude/skills/narrative-writer-assist/SKILL.md (or your agent's skills folder).
name
narrative-writer-assist
description
Flesh a single-sentence author intent into a full Detroit-style narrative beat that splices into an existing canon path. Returns strict JSON with title, summary, body, imagePrompt, mood, tone, and worldPercent. Use when the user is inserting a beat between two known story nodes and has typed a short intent describing what should happen there. No prose, no reasoning, no tool calls.
version
1.0.0
author
Noustiny
license
MIT

Narrative Writer-Assist

The dramaturge's hand. Given the story so far, two adjacent beats the user wants to splice between, and a single line of authorial intent, produce one fully formed beat that lands between them without breaking canon.

This skill is the partner of narrative-brainstorm. Brainstorm proposes three forks from a single parent when the author has no specific idea. Writer-assist executes one specific idea the author already has.

When to Use

Trigger this skill when the user is inserting a beat into an existing canon path and has written their own intent for that beat. Typical phrasings:

  • "insert a beat between X and Y where …"
  • "splice a scene in, intent: …"
  • "flesh this out into a beat"
  • "write the moment where …"
  • mode-tagged: "insert as canon" / "insert as what-if"

Scope

Best suited for:

  • InsertModal-style flows where the user picks two adjacent nodes and types an intent
  • Mid-flow authorial interventions that belong on a known canon spine
  • Rewrites where the user wants the agent to honour a specific cause rather than invent one

Look elsewhere first for:

  • Generating multiple branch options from a parent → narrative-brainstorm
  • Rewriting an existing downstream beat after an upstream contradiction → narrative-rewriter
  • Grouping already-written beats into scenes → scene-composition
  • Final prose rendering of the canon spine → narrative-writer

This skill fires exactly once per insert. If the user has no intent and wants options, send them to narrative-brainstorm.

Input Shape

The user message contains a single JSON object:

FieldTypeRequiredPurpose
seedstringyesThe story's root premise / logline (for tonal grounding)
canonTitlesstring[]yesThe canon spine so far, root → current, as titles
parentTitlestringyesThe beat immediately upstream of the insertion point
childTitlestringyesThe beat immediately downstream of the insertion point
intentstringyesThe user's one-line description of what should happen in the new beat
modestringyes"canon" (splice into spine, downstream will reharmonize) or "what-if" (sibling branch, canon untouched)

Mood Library

Emit exactly one lowercase token:

neutral · hopeful · tense · danger · climax · quiet · discovery

Any other value is a contract violation.

Output Contract

Return exactly one JSON object, shaped like this. No preamble, no code fence, no commentary.

json
{
  "title": "Full sentence naming this checkpoint, ≤140 chars (ör. 'Aang ve Sokka köye doğru yola koyulurlar, yolda eski bir Ateş Ulusu gemisi bulurlar')",
  "summary": "One-sentence hook, ≤140 chars",
  "body": "2-4 sentences — the story flow FROM the prior checkpoint UP TO this one. Concrete, sensory, present tense, dialog allowed.",
  "imagePrompt": "A vivid cinematic still of the checkpoint's key moment, 20–35 words.",
  "mood": "one of the mood library tokens",
  "tone": "canon | divergent | what-if",
  "worldPercent": 1..99
}

Checkpoint-scale

Every inserted beat is a critical story moment — a scene transition, a major decision outcome, or a meaningful time/location jump. Not a micro-reaction ("Sokka sighs", "Aang blinks"). The user typed their intent; honour it as a checkpoint.

  • Title is a full sentence in the seed's language. 4-20 words. Not a 3-word tag.
  • Body narrates the story flow leading INTO the checkpoint — what happens from the prior beat up to this moment. Can cover minutes or hours of story time, with dialog and movement. The image shows the final frame of this stretch; the body tells the journey to it.

tone matches the caller's mode:

  • mode === "canon" → tone: "canon"
  • mode === "what-if" → tone: "what-if"

worldPercent is Detroit's "how many players would walk this path". Guidance:

  • mode: canon with a plausible, common-sense intent → 55..85
  • mode: canon with a bold or unusual intent → 25..55
  • mode: what-if → 5..35 (it's a side road most players wouldn't take)

The first character of your response must be {. The last character must be }. Nothing outside the object.

Core Principles

Honour the intent verbatim. The user has already decided what happens. You are not proposing alternatives — you are writing their idea as a beat. If the intent says "Captain America takes the hammer", the hammer ends up with Captain America. Don't soften it, don't invent a rescue.

Splice cleanly between parent and child. The beat must feel like it was always there. Read parentTitle as the frame the user is coming from, childTitle as the state the story pivots into next. Your beat carries them across that pivot.

Plain narrator voice — a person recapping a scene to a friend. Not a novelist, not a trailer voiceover. Describe what happens in the order it happens, connected with and / then / but / so. Present tense. Short to medium sentences.

Compare four registers on the same moment (Aang waking after Katara frees him):

  • ❌ Overwrought AI-literary: "A surge of pure panic, not human but elemental, makes the ice around him groan and crack under a silent, desperate pressure from within."
  • ❌ Cinematic staccato: "His tattoos glow blue. He slams his fist against the ice. A crack shoots up. Water leaks in around his knuckles."
  • ❌ Purple reflex (flutter / revealing / intensifies): "His eyes flutter open, revealing ancient wisdom and childish confusion. His gaze intensifies, confusion giving way to a raspy whisper."
  • ✅ Plain narrator (target): "Aang opens his eyes slowly. He looks at Katara and Sokka without saying anything. Then he finally speaks in a hoarse voice: 'Who are you?'"

Hard rules — every one of these was violated in real outputs we had to throw away:

  • Use character names, not pronouns. "Aang", "Katara", "Sokka". Repeating names is FINE and natural — it's how a person actually tells a story. "He" / "his" is only OK as a short bridge within the same sentence, never as the main subject of every sentence in a row.
  • Banned verbs / phrases (no exceptions): flutter, revealing (X and Y), intensifies, giving way to, erupts, ignites, surges, pulses, cascades, shimmers, blooms, wraps around, washes over, settles, a raspy whisper, a questioning gaze, a silent pressure, ancient wisdom, childish confusion. Any sentence containing one of these is a REWRITE.
  • Banned patterns:
    • "X, revealing Y and Z" (ever)
    • "X giving way to Y" (abstract-noun subject; ever)
    • "a [adjective] [noun]" floating as a dangling phrase ("a questioning gaze", "a raspy whisper") — if it's dialogue, write the dialogue. If it's a gaze, write what the character does with their eyes.
    • Abstract nouns as subjects: panic, pressure, surge, wave, gaze, confusion, wisdom doing something. People and objects act, emotions don't.
  • One adjective per noun max. Two is a warning. Three is always wrong.
  • Do not personify elements. Ice "cracks" or "shifts", not "groans". Wind "blows", not "whispers".
  • No "not X but Y" constructions.
  • Cut hedging words: somehow, seemed to, almost as if, a kind of, a heavy lassitude, intently, desperately, instinctively.
  • Dialogue beats description. If a character can say it in three words, let them. "Don't move," Katara whispers. > "Katara's face tightens with wary intent."
Show full SKILL.md (481 more words)Show less

Before emitting, re-read the body. If any sentence sounds like a movie-trailer voiceover or a book-jacket blurb, rewrite it as what you'd tell a friend who asked "wait, what happened?"

Canon tone adopts the spine's register. Read canonTitles for voice: if the canon is fragmentary / quiet, don't suddenly swing into melodrama; if it's escalating climactically, meet the pressure.

What-if tone carries its own flavour. In mode: what-if, you have more licence to surprise — this branch won't be the main line, so it can take a weirder shape.

Title is a full sentence that names the checkpoint — in the seed's language. "Aang ve Sokka köye doğru yola koyulurlar, yolda eski bir Ateş Ulusu gemisi bulurlar" beats "KÖYE YOLCULUK". The short Detroit chip label is derived client-side from the first 2-3 words; the title itself is a sentence.

Workflow

  1. Read the payload. Parse seed, canonTitles, parentTitle, childTitle, intent, mode.
  2. Anchor. Summarise to yourself (not in output): the beat sits after parentTitle and before childTitle, and must make that transition feel earned by intent.
  3. Draft the body. 2–3 concrete sentences in present tense — action the camera can see. Work the user's intent in directly.
  4. Title & summary. Title = active label. Summary = one-sentence hook, ≤120 chars.
  5. Image prompt. 20–35 words describing a cinematic still: composition, lighting, palette, key object in frame.
  6. Mood, tone, worldPercent. Pick from the library and the rules above.
  7. Emit the JSON object. Nothing before, nothing after.

Anti-patterns

Do not do any of the following — each one breaks the downstream consumer:

  • Do not emit <tool_call>, <think>, <thinking>, or any XML tags.
  • Do not call any tool. This skill is pure reasoning — tool use is an error.
  • Do not explain the JSON in prose before or after. The response is the JSON object, nothing else.
  • Do not wrap the JSON in a markdown code fence (no json ... ).
  • Do not add fields outside the contract (no id, reasoning, axis, notes).
  • Do not emit the title as a 3-word label — it is a full sentence in the seed's language. The client will derive a short chip label from the first words.
  • Do not overrule the user's intent. If they say "Captain America takes the hammer", don't have Thor reclaim it at the end. Write the intent exactly.
  • Do not write body in past tense. Present tense, always.
  • Do not return worldPercent as a float or as a string. Integer, 1..99.
  • Do not emit mood as a phrase or with a glyph ("★ hopeful" is wrong; emit "hopeful").
  • Do not copy parentTitle or childTitle verbatim as the new title.

Example

Input (user message payload):

json
{
  "seed": "In the final battle against Thanos, every Avenger must choose what to sacrifice.",
  "canonTitles": ["THE GAUNTLET", "HESITATE, LOOK AT MOUNTAIN", "THOR TAKES IT, BURNS WITH IT"],
  "parentTitle": "THOR TAKES IT, BURNS WITH IT",
  "childTitle": "THOR'S HAMMER SOARS PAST",
  "intent": "hammer pullback but captain america took it because thor exhausted and knocked down by thanos",
  "mode": "canon"
}

Correct output:

json
{
  "title": "HAMMER PULLBACK TO CAP",
  "summary": "Thor drops to one knee and loses the gauntlet; Mjolnir answers Cap's hand instead.",
  "body": "Thor's grip on the gauntlet goes loose as the stones' light fades on his skin, and Thanos knocks him off his feet before he can recover. Mjolnir pulls out of the dust and drops into Steve's raised hand, like it was always going that way. Steve closes his fingers around the handle and steps forward.",
  "imagePrompt": "Wide cinematic shot on the ruined battlefield — Thor slammed into the dirt mid-frame, Mjolnir a blur of lightning arcing overhead toward Captain America's outstretched hand, dust and orange embers, heavy rim light, 35mm.",
  "mood": "climax",
  "tone": "canon",
  "worldPercent": 62
}

The intent (Cap gets the hammer) is honoured exactly. Body is plain narrator voice — subject/verb/result, events in order, connected with as, before, and. Mood matches the stakes. tone matches mode. worldPercent reflects "bold canon deviation but plausible". That is the target pattern for every invocation.

© UfukNode, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in hermes-additions/skills/creative/narrative-writer-assist of UfukNode/Noustiny.

Open the folder on GitHubat commit 09a0c82

Compare with similar skills

Narrative Beat Writer-Assist next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Narrative Beat Writer-Assist compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Narrative Beat Writer-Assist this skillUfukNode/Noustiny181—~3.1kAutomated safety check: PassMIT
Chinese Novel Writing Systemleenbj/novel-creator-skill668—~3.9kAutomated safety check: PassNone
Chinese Novelist Chapter WriterPenglongHuang/chinese-novelist-skill3.3k—~491Automated safety check: WarnMIT
Sun-Style Restrained Narrative WritingKKKKhazix/sun-style-writing402—~1.7kAutomated safety check: PassMIT
Long Story AnalysisNarcooo/inkos10k—~364Automated safety check: PassAGPL-3.0
Short Web Fiction Writeruu201/character-arc581—~3.7kAutomated safety check: PassMIT

Similar skills

  • Chinese Novel Writing System

    leenbj/novel-creator-skill

    Guides long-form Chinese novel writing from a rough idea through outlines, chapter drafts and quality gates, with file-based memory for a story meant to reach 300万字.

    668 GitHub stars~3.9k tokensUpdated 7 mo ago
    Writing & ContentAuto-check passed
  • Chinese Novelist Chapter Writer

    PenglongHuang/chinese-novelist-skill

    Writes long Chinese novels chapter by chapter through guided questions, outlining, drafting with cliffhangers and automatic validation, with resumable projects.

    3.3k GitHub stars~491 tokensUpdated 3 days ago
    Writing & ContentAuto-check: warnings
  • Sun-Style Restrained Narrative Writing

    KKKKhazix/sun-style-writing

    Writes Chinese first-person nonfiction in a restrained plain-description style: short sentences, exact numbers, objects that carry feeling and silence at the peak.

    402 GitHub stars~1.7k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Long Story Analysis

    Narcooo/inkos

    Breaks down a full novel or long sample into story mechanisms and style traits the agent can reuse as craft, without copying names or wording.

    10k GitHub stars~364 tokensUpdated today
    Writing & ContentAuto-check passed
  • Short Web Fiction Writer

    uu201/character-arc

    Walks an agent through writing a complete short web novel in Chinese, starting from the emotion the reader should feel and building around one twist.

    581 GitHub stars~3.7k tokensUpdated today
    Writing & ContentAuto-check passed
  • Short Web Novel Deconstruction

    zenstory-ai/oh-story-claudecode

    Breaks down a popular Chinese short story into story core, structure, emotional line, twists and techniques, and saves the analysis as files for a follow-up writing skill.

    7.4k GitHub starsUsed in 1 repo~2k tokens
    Writing & ContentAuto-check passed

More from UfukNode/Noustiny

All 13 skills in this repo
  • Grades whether a downstream story beat still holds after an upstream insertion, returning a strict JSON verdict of still_valid, needs_rewrite or must_delete.

    181 GitHub stars~2.3k tokensUpdated 5 mo ago
    Auto-check passed
  • Narrative Writer

    UfukNode/Noustiny

    Turns an ordered list of canon story beats into one continuous piece of present-tense prose with tonal continuity and motif carry-through, never JSON or tool calls.

    181 GitHub stars~1.9k tokensUpdated 5 mo ago
    Auto-check passed
  • Story Scene Composer

    UfukNode/Noustiny

    Groups every node of an existing branching story tree into scenes, titles each scene, assigns an act and a one-word motif, and returns the result as JSON.

    181 GitHub stars~2.3k tokensUpdated 5 mo ago
    Auto-check passed
  • Story Copyright Detector

    UfukNode/Noustiny

    Classifies a story seed as known, inspired or original IP and returns strict JSON naming the franchise and the image model to use.

    181 GitHub stars~1.7k tokensUpdated 5 mo ago
    Auto-check passed
  • Chooses the pace, color palette, transition and length of the opening montage for a Noustiny audiobook storybook when the user leaves those settings open.

    181 GitHub stars~3.2k tokensUpdated 5 mo ago
    Auto-check passed
  • Character Sheet Builder

    UfukNode/Noustiny

    Produce a cast sheet of 1–4 named characters from a story seed.

    181 GitHub stars~2.1k tokensUpdated 5 mo ago
    Auto-check passed

Questions about Narrative Beat Writer-Assist

What does Narrative Beat Writer-Assist do?

Expands a one-line author intent into a full story beat that fits between two known nodes of a canon path, returned as strict JSON. Given the story's premise, the canon titles so far, the beat before and after the insertion point, and a one-sentence intent, the skill writes one beat that lands between them without breaking canon. It is the partner of a brainstorm skill: brainstorming proposes forks when the author has no idea, while this one carries out an idea the author already has.

When should I use Narrative Beat Writer-Assist?

Narrative Beat Writer-Assist fits situations like: inserting a new beat between two adjacent nodes in a branching story; turning a short authorial intent into a complete scene description with an image prompt; adding a what-if branch without changing the canon spine.

How do I install Narrative Beat Writer-Assist in Claude Code?

Run `npx skills add UfukNode/Noustiny --skill narrative-writer-assist -a claude-code`. Or copy the skill folder (hermes-additions/skills/creative/narrative-writer-assist in UfukNode/Noustiny) into .claude/skills/narrative-writer-assist in your project. Claude Code loads it when a task matches its description.

How do I install Narrative Beat Writer-Assist in Codex?

Run `npx skills add UfukNode/Noustiny --skill narrative-writer-assist -a codex`. Or copy the skill folder (hermes-additions/skills/creative/narrative-writer-assist in UfukNode/Noustiny) into .agents/skills/narrative-writer-assist in your project. Codex loads it when a task matches its description.

Can I use Narrative Beat Writer-Assist in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add UfukNode/Noustiny --skill narrative-writer-assist -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/narrative-writer-assist, .gemini/skills/narrative-writer-assist, .github/skills/narrative-writer-assist and .opencode/skills/narrative-writer-assist in your project.

What does Narrative Beat Writer-Assist need to run?

SKILL.md names no scripts, command-line tools or credentials: Narrative Beat Writer-Assist is instructions for the agent only. Our summary lists: A story context supplied as one JSON object with the fields the skill defines.

Does Narrative Beat Writer-Assist access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Narrative Beat Writer-Assist safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Narrative Beat Writer-Assist use?

Narrative Beat Writer-Assist is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Narrative Beat Writer-Assist use?

About 3.1k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Narrative Beat Writer-Assist?

Skills that share tags, products or a category with Narrative Beat Writer-Assist: Chinese Novel Writing System (leenbj/novel-creator-skill, 668 stars), Chinese Novelist Chapter Writer (PenglongHuang/chinese-novelist-skill, 3.3k stars), Sun-Style Restrained Narrative Writing (KKKKhazix/sun-style-writing, 402 stars) and Long Story Analysis (Narcooo/inkos, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Narrative Beat Writer-Assist?

UfukNode (a GitHub user) maintains it in UfukNode/Noustiny, which has 181 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on May 4, 2026.

Source: UfukNode/Noustiny on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.