Agent skill

Memetic Depth

by jwynia in jwynia/agent-skills

Create the perception of cultural depth through strategic juxtaposition of familiar and unfamiliar elements.

MITAuto-check passedWriting & Content

Install Memetic Depth

skills CLI
$ npx skills add jwynia/agent-skills --skill memetic-depth -a claude-code

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

GitHub CLI
$ gh skill install jwynia/agent-skills memetic-depth --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/jwynia/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/creative/fiction/character/memetic-depth .claude/skills/memetic-depth && 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
memetic-depth
GitHub stars
170
Token cost
~3.9k tokens
SKILL.md length
1,763 words
Files
1
Skills in repo
111
Repo updated
First seen
Licence
MIT

At a glance

Create the perception of cultural depth through strategic juxtaposition of familiar and unfamiliar elements.

  • Works in 9 steps: Identify Cultural Categories → Populate with Mixed Elements → Create Systemic Connections → …
  • Settings feel shallow
  • SKILL.md covers Core Principle: Cognitive…, The Three Element Types, The 40/40/20 Ratio and List Construction Method, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Memetic Depth is an agent skill from jwynia/agent-skills. Create the perception of cultural depth through strategic juxtaposition of familiar and unfamiliar elements. Use when settings feel shallow, when you need centuries of implied history without exposition, or when worldbuilding lacks the texture of real cultural evolution.

Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Creative writing and fiction. The licence is MIT.

When your agent uses it

  • Settings feel shallow
  • You need centuries of implied history without exposition
  • Worldbuilding lacks the texture of real cultural evolution

Example prompts

  • “/memetic-depth”

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Identify Cultural Categories
  2. Populate with Mixed Elements
  3. Create Systemic Connections
  4. Apply Character Filter
  5. Uniform Unfamiliarity
  6. Explanation Compulsion
  7. Random Exotica
  8. Missing Power Dynamics
  9. Ratio Neglect

What it can do on your machine

Read from SKILL.md and the folder at commit e02ec7e. 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.

    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

Memetic Depth loads about 3.9k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 1,763 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~3.9k

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 jwynia/agent-skills at commit e02ec7e, republished under its MIT licence (© jwynia). 1,763 words, ~3,894 tokens.

Download SKILL.mdSave it as .claude/skills/memetic-depth/SKILL.md (or your agent's skills folder).
name
memetic-depth
description
Create the perception of cultural depth through strategic juxtaposition of familiar and unfamiliar elements. Use when settings feel shallow, when you need centuries of implied history without exposition, or when worldbuilding lacks the texture of real cultural evolution.
license
MIT
metadata.author
jwynia
metadata.version
1.0
metadata.type
generator
metadata.mode
generative
metadata.domain
worldbuilding

Memetic Depth: Worldbuilding Texture Skill

You help writers create the perception that fictional worlds have centuries of cultural processing, synthesis, and degradation that occurred before the reader encounters them. Your role is to design strategic juxtapositions of cultural elements at different familiarity levels.

Core Principle: Cognitive Triangulation

Memetic Depth is the perception that a world exists beyond what's explained, with cultural processes that operated independently of narrative needs.

By combining Recognizable + Inferrable + Inscrutable elements, readers:

  1. Feel anchored (recognizable elements provide security)
  2. Feel intelligent (inferrable elements reward attention)
  3. Feel intrigued (inscrutable elements promise more depth)

The Three Element Types

Recognizable Elements (40% of mix)

Elements the reader knows from real-world experience without explanation.

Purpose: Anchor reader, prove author isn't random, establish baseline for transformation.

Examples: "rosaries, prayer wheels, saints" / "Day of the Dead, Christmas" / "Statue of Liberty keychains"

Selection Criteria:

  • Universal enough most readers know it
  • Stable enough to still exist in your timeframe
  • Distinct enough to transform interestingly
  • Not so sacred it blocks creative play

Mistake: Only recognizable elements → world feels shallow, like present with cosmetic changes.

Inferrable Elements (40% of mix)

Elements the reader can deduce from context or logical extension.

Purpose: Reward attention, create engagement, show cultural synthesis, demonstrate time depth.

Examples: "Klingon Day of the Dead sugar skulls" / "rosaries in five species' configurations" / "pocket saints (human and otherwise)"

Reader Inference Patterns:

PatternExampleReader Deduces
Species Application"Bajoran prayer beads"Bajorans have similar prayer tradition
Cultural Fusion"Klingon Day of the Dead"Two cultures met and synthesized
Temporal Distance"Pre-Collapse Earth"Something bad happened, society reset
Market Degradation"Probably weren't authentic"Authenticity is questionable

Selection Criteria:

  • Context provides enough clues for reasonable inference
  • Multiple interpretations possible but one most likely
  • Wrong interpretation doesn't break comprehension

Mistake: Everything inferrable exhausts readers—they need anchors and mysteries too.

Inscrutable Elements (20% of mix)

Elements the reader cannot deduce, creating productive mystery.

Purpose: Signal world is deeper than shown, create hooks, acknowledge not everything can be explained.

Examples: "Pre-Collapse Earth" / "Blessed Translator" / "grace-compass" / "Meditation Reform period"

Types of Productive Mystery:

TypeDescriptionExample
Historical GapSomething happened but isn't explained"Pre-Collapse Earth"
Cultural UntranslatabilityConcept doesn't map to reader's framework"Tholian prayer-geometries"
Degraded KnowledgeCharacters don't fully understand either"Blessed Translator"
Deliberate WithholdingPOV would know but reader doesn't"Meditation Reform period"

Selection Criteria:

  • Mystery is intriguing not frustrating
  • Reader trusts there's a reason
  • Doesn't block scene comprehension

Mistake: Too much inscrutability feels like arbitrary withholding.

The 40/40/20 Ratio

Base Formula
  • 40% Recognizable (immediate knowledge)
  • 40% Inferrable (deducible)
  • 20% Inscrutable (accepted mystery)
Adjusting by Genre
GenreRatioReason
Hard SF50/40/10Readers expect logical extrapolation
Fantasy/Soft SF30/40/30More alienness acceptable
Near-Future60/30/10Very recognizable baseline
Far-Future/Space Opera30/50/20Heavy inference load
First Contact40/30/30Alien mystery is the point
Within a Scene
  • Opening: Higher recognizable (50/30/20) — reader needs grounding
  • Mid-scene: Standard (40/40/20) — reader has footing
  • Climax: Can skew inscrutable (30/30/40) — emotion carries mystery

List Construction Method

Step 1: Identify Cultural Categories

What categories of artifacts would logically exist in this location?

Space Station Trinket Shop:

  1. Religious items (humans brought religion)
  2. Folk practice items (religion degraded)
  3. Heritage nostalgia (longing for homeworlds)
  4. Practical luck objects (spacers are superstitious)
  5. Species synthesis items (cultures mixed)
  6. Misunderstood historical objects (memory failed)
  7. Deliberate novelty kitsch (market creates traditions)
Step 2: Populate with Mixed Elements

For each category: 2 Recognizable, 2 Inferrable, 1 Inscrutable

Religious Items Example:

  • Recognizable: "rosaries" / "prayer wheels"
  • Inferrable: "rosaries in five species' configurations" / "pocket saints (human and otherwise)"
  • Inscrutable: "something labeled 'Blessed Translator' that might have been a universal translator or a repurposed medical device"
Step 3: Create Systemic Connections

Items should reveal cultural processes, not be random.

Degradation Chain:

  1. Original: "Traditional Catholic rosary"
  2. Folk adaptation: "Spacer's rosary (extra beads for dangerous work)"
  3. Secular: "Lucky bead string (no religious significance)"
  4. Commercial: "Ferengi profit-counting beads (rosary form, capitalist function)"

Synthesis Process:

  1. Source A: Mexican Day of the Dead
  2. Source B: Klingon honor-the-dead practices
  3. Contact: Klingon colony on Mexican-settled world
  4. Synthesis: "Klingon Day of the Dead sugar skulls"
  5. Commercialization: "Sold as 'traditional Klingon craft'"

Power Dynamics:

  • Human religious items: Common, cheap, treated casually
  • Vulcan philosophical items: Rare, expensive, "authentic"
  • Bajoran items: Controversial (recent occupation)
  • Extinct species items: Uncontroversial (no one to object)

Generation Gap:

  • Elder: "That's a serious religious object from my grandmother"
  • Middle: "That's traditional craft my parents valued"
  • Youth: "That's a cool vintage aesthetic"
  • Tourist: "That's an exotic souvenir"
Step 4: Apply Character Filter

Same list appears different by POV:

Cultural Insider: Sees misunderstanding, commodification, degradation Cultural Outsider: Sees exotic, incomprehensible, interchangeable Market Participant: Sees inventory, price points, supply chain

Quick Reference: Cultural Process Signals

SignalWhat It Implies
"Traditional" in quotesTradition is marketing
"Probably weren't"Authenticity questionable
"Pre-[Event]"Major historical rupture
"Revival period"Tradition died and was revived
Species + Human traditionCultural synthesis occurred
"Ancient [Place]"That place is now mythologized
Multiple species variantsWide adoption, local adaptation

Diagnostic Questions

When your worldbuilding feels shallow:

  1. What's recognizable enough to anchor readers?
  2. What can readers deduce if they're paying attention?
  3. What mysteries signal depth without explanation?
  4. What cultural processes created these items?
  5. Who made them, for whom, and why?
  6. How has time degraded original meaning?
  7. What power dynamics determine authenticity?

Output Persistence

This skill writes primary output to files so work persists across sessions.

Output Discovery
  1. Check for context/output-config.md in the project
  2. If found, look for this skill's entry
  3. If not found, ask user: "Where should I save cultural texture work?"
  4. Suggest: worldbuilding/culture/ or explorations/worldbuilding/
Primary Output
  • Element lists - Categorized items with familiarity levels
  • Cultural process chains - Degradation, synthesis, commercialization
  • Power dynamics - Who commodifies whom
  • Ratio audit - 40/40/20 balance check
File Naming

Pattern: {location/culture}-memetic-{date}.md

Verification (Oracle)

What This Skill Can Verify
  • Ratio balance - Is mix near 40/40/20? (High confidence)
  • Process chains present - Do elements connect through cultural processes? (High confidence)
  • Anchor presence - Are there recognizable elements for reader grounding? (High confidence)
What Requires Human Judgment
  • Reader accessibility - Will target readers recognize the "recognizable" elements?
  • Mystery calibration - Are inscrutable elements intriguing vs. frustrating?
  • Cultural sensitivity - Are real-world cultural elements handled respectfully?
Oracle Limitations
  • Cannot assess whether inference load is appropriate for target audience
  • Cannot predict reader reaction to mystery elements

Feedback Loop

Show full SKILL.md (714 more words)Show less
Session Persistence
  • Output location: See context/output-config.md
  • What to save: Element lists, process chains, ratio audits
  • Naming pattern: {location/culture}-memetic-{date}.md
Cross-Session Learning
  • Check for prior cultural texture work on this setting
  • Maintain consistent familiarity levels across locations
  • Reader feedback on mystery elements informs ratio adjustment

Design Constraints

This Skill Assumes
  • Setting has cultural artifacts/practices to texture
  • Writer wants implied depth, not exposition
  • Some real-world reference points exist (even far-future settings)
This Skill Does Not Handle
  • Systemic worldbuilding - Route to: worldbuilding
  • Economic foundations - Route to: economic-systems
  • Language creation - Route to: conlang
Degradation Signals
  • All elements at same familiarity level (no triangulation)
  • Random exotica without systemic connection
  • Explaining every mystery (destroys depth perception)

Reasoning Requirements

Standard Reasoning
  • Single category population
  • Ratio checking
  • Basic degradation chain design
Extended Reasoning (ultrathink)
  • Full location texture design - [Why: multiple categories with cross-connections]
  • Multi-culture synthesis tracking - [Why: tracing how cultures merged]
  • Power dynamic mapping - [Why: determining who commodifies whom]

Trigger phrases: "make this place feel lived-in", "cultural texture for entire setting", "how did these cultures mix"

Execution Strategy

Sequential (Default)
  • Identify categories before populating
  • Populate recognizable before inferrable
  • Create process chains after initial population
Parallelizable
  • Populating multiple independent categories
  • Designing different location textures
Subagent Candidates
TaskAgent TypeWhen to Spawn
Cultural researchgeneral-purposeWhen basing on real cultural practices
Cross-setting consistencyExploreWhen checking against existing world files

Context Management

Approximate Token Footprint
  • Skill base: ~2.5k tokens (principle + element types + ratio)
  • With construction method: ~3.5k tokens
  • With full diagnostic: ~4k tokens
Context Optimization
  • The 40/40/20 ratio is the core takeaway
  • Construction method is reference, not required in context
  • Quick reference signals are highly compressed
When Context Gets Tight
  • Prioritize: Three element types, ratio, current category
  • Defer: Full construction method, all signal types
  • Drop: Generation gap examples, all worked examples

Anti-Patterns

1. Uniform Unfamiliarity

Pattern: Making everything equally strange—no recognizable anchors, all inferrable or inscrutable elements. Why it fails: Without familiar elements, readers have no baseline for understanding transformation. Everything feels alien, which paradoxically flattens into homogeneous strangeness. Fix: Start with recognizable anchors. "Rosaries" is familiar; "rosaries in five species' configurations" shows cultural evolution. The familiar element makes the transformation visible.

2. Explanation Compulsion

Pattern: Explaining every cultural detail, resolving every mystery, providing footnotes for inferrable elements. Why it fails: Explanation destroys the perception of depth. If everything is explained, the world feels completely mapped. Real cultures have unexplained elements—everyone accepts things they don't fully understand. Fix: Let inscrutable elements remain inscrutable. Trust readers to accept mysteries the same way they accept mysteries in real life. "The Meditation Reform period" doesn't need explanation.

3. Random Exotica

Pattern: Generating strange cultural elements without systemic connection—a grab bag of weird stuff. Why it fails: Real cultures have internal logic. Items exist because of historical processes—synthesis, degradation, commercialization. Random elements feel designed rather than evolved. Fix: Create systemic connections. Show how items relate to each other through cultural processes. The degradation chain from rosary → spacer beads → lucky string → profit counter tells a story.

4. Missing Power Dynamics

Pattern: Treating all cultural elements as equally available, equally valued, without considering who commodifies whom. Why it fails: Real cultural exchange involves power. Some cultures' items become "exotic souvenirs" while others become "serious traditions." Who decides what's "authentic" reveals power structures. Fix: Consider which cultural items are treated seriously and which are treated as novelty. Who profits from whose traditions? These dynamics add uncomfortable realism.

5. Ratio Neglect

Pattern: Ignoring the 40/40/20 balance, skewing heavily toward any single element type. Why it fails: Too much recognizable feels shallow. Too much inferrable exhausts readers. Too much inscrutable feels arbitrary. The balance creates the triangulation that produces depth perception. Fix: Audit your cultural details explicitly. Count recognizable, inferrable, and inscrutable elements. Adjust toward the ratio appropriate for your genre and scene position.

Integration

Inbound (feeds into this skill)
SkillWhat it provides
worldbuildingSystemic foundation for cultural processes
conlangLanguage evolution that parallels cultural evolution
multi-order-evolutionGenerational stages that create cultural layers
Outbound (this skill enables)
SkillWhat this provides
dialogueCulturally-textured speech patterns and references
settlement-designCultural layers in urban environments
scene-sequencingCultural details for scene texture
Complementary
SkillRelationship
worldbuildingWorldbuilding creates systems; memetic-depth adds perceived cultural texture. Use together for settings that feel lived-in
cliche-transcendenceMemetic-depth avoids cultural clichés through the same process—pushing recognizable elements toward inferrable transformations

© jwynia, 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 skills/creative/fiction/character/memetic-depth of jwynia/agent-skills.

Open the folder on GitHubat commit e02ec7e

Compare with similar skills

Memetic Depth 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.

Memetic Depth compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Memetic Depth this skilljwynia/agent-skills170—~3.9kAutomated safety check: PassMIT
Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode7.4k3 repos~3kAutomated safety check: PassMIT
Short Web Fiction Trend Scanzenstory-ai/oh-story-claudecode7.4k2 repos~1.2kAutomated safety check: PassMIT
InkOS Creative HarnessNarcooo/inkos10k1 repos~1.1kAutomated safety check: PassAGPL-3.0
Novel Arteternityspring/shuohao-skills4.3k—~1.1kAutomated safety check: NotesApache-2.0
SepiaNanako0129/sepia3.1k—~3.6kAutomated safety check: PassMIT

Similar skills

  • Story Multi-Perspective Review

    zenstory-ai/oh-story-claudecode

    Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.

    7.4k GitHub starsUsed in 3 repos~3k tokens
    Writing & ContentAuto-check passed
  • Short Web Fiction Trend Scan

    zenstory-ai/oh-story-claudecode

    Scans popular short web-fiction rankings on Chinese platforms such as Dianzhong and Heiyan to surface trending emotional hooks, themes and topic candidates with an expiry warning.

    7.4k GitHub starsUsed in 2 repos~1.2k tokens
    Writing & ContentAuto-check passed
  • Drives long-form fiction, scripts, storyboards, interactive films and long-document translation through InkOS, with every change made by a typed action.

    10k GitHub starsUsed in 1 repo~1.1k tokens
    Writing & ContentAuto-check passed
  • Novel Art

    eternityspring/shuohao-skills

    给 AI 短剧出美术设定集(场景 + 叙事道具):场景的设计意图、一致性锚点、光照时段变体、 空景提示词;道具的戏剧功能、状态变体、尺度参照、白底无手提示词。

    4.3k GitHub stars~1.1k tokensUpdated yesterday
    Writing & ContentAuto-check: notes
  • Sepia

    Nanako0129/sepia

    Make AI-generated writing read as human-written, in fiction and in professional prose.

    3.1k GitHub stars~3.6k tokensUpdated today
    Writing & ContentAuto-check passed
  • Story Toolbox Router

    zenstory-ai/oh-story-claudecode

    Routes a Chinese web-novel writing request to the matching tool in a 13-skill toolbox, covers author habit memory, and can launch a local dashboard for browsing a project.

    7.4k GitHub stars~1.7k tokensUpdated today
    Writing & ContentAuto-check passed

More from jwynia/agent-skills

All 111 skills in this repo
  • Devcontainer

    jwynia/agent-skills

    Diagnose devcontainer configuration problems and guide development environment setup.

    170 GitHub stars~1.2k tokensUpdated 7 mo ago
    Auto-check: notes
  • Frontend Design

    jwynia/agent-skills

    Create distinctive, production-grade frontend interfaces with high design quality.

    170 GitHub stars~3.2k tokensUpdated 7 mo ago
    Auto-check passed
  • Gitea Workflow

    jwynia/agent-skills

    Orchestrate agile development workflows for Gitea repositories using the tea CLI.

    170 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed
  • Godot Asset Generator

    jwynia/agent-skills

    Generate game assets using AI image generation APIs (DALL-E, Replicate, fal.ai) and prepare them for Godot.

    170 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed
  • Mastra Hono

    jwynia/agent-skills

    Develop AI agents, tools, and workflows with Mastra v1 Beta and Hono servers.

    170 GitHub stars~2.9k tokensUpdated 7 mo ago
    Auto-check passed
  • PPTX Generator

    jwynia/agent-skills

    Create and manipulate PowerPoint PPTX files programmatically.

    170 GitHub stars~3.1k tokensUpdated 7 mo ago
    Auto-check passed

Questions about Memetic Depth

What does Memetic Depth do?

Create the perception of cultural depth through strategic juxtaposition of familiar and unfamiliar elements. Memetic Depth is an agent skill from jwynia/agent-skills. Create the perception of cultural depth through strategic juxtaposition of familiar and unfamiliar elements.

When should I use Memetic Depth?

Memetic Depth fits situations like: settings feel shallow; you need centuries of implied history without exposition; worldbuilding lacks the texture of real cultural evolution.

How do I install Memetic Depth in Claude Code?

Run `npx skills add jwynia/agent-skills --skill memetic-depth -a claude-code`. Or copy the skill folder (skills/creative/fiction/character/memetic-depth in jwynia/agent-skills) into .claude/skills/memetic-depth in your project. Claude Code loads it when a task matches its description.

How do I install Memetic Depth in Codex?

Run `npx skills add jwynia/agent-skills --skill memetic-depth -a codex`. Or copy the skill folder (skills/creative/fiction/character/memetic-depth in jwynia/agent-skills) into .agents/skills/memetic-depth in your project. Codex loads it when a task matches its description.

Can I use Memetic Depth 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 jwynia/agent-skills --skill memetic-depth -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memetic-depth, .gemini/skills/memetic-depth, .github/skills/memetic-depth and .opencode/skills/memetic-depth in your project.

What does Memetic Depth need to run?

SKILL.md names no scripts, command-line tools or credentials: Memetic Depth is instructions for the agent only.

Does Memetic Depth 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 Memetic Depth 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 Memetic Depth use?

Memetic Depth 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 Memetic Depth use?

About 3.9k tokens (SKILL.md is roughly 16k 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 Memetic Depth?

Skills that share tags, products or a category with Memetic Depth: Story Multi-Perspective Review (zenstory-ai/oh-story-claudecode, 7.4k stars), Short Web Fiction Trend Scan (zenstory-ai/oh-story-claudecode, 7.4k stars), InkOS Creative Harness (Narcooo/inkos, 10k stars) and Novel Art (eternityspring/shuohao-skills, 4.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memetic Depth?

jwynia (a GitHub user) maintains it in jwynia/agent-skills, which has 170 GitHub stars. The repository holds 111 skills in this directory. The repository was last updated on February 24, 2026.

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