lambda-lang

0
1
Source

Translate between Λ (Lambda) language and natural language. Use for agent-to-agent communication, decoding Lambda messages, or discussing the protocol. Triggers on Lambda syntax like ?Uk/co or !It>Ie.

Install

mkdir -p .claude/skills/lambda-lang && curl -L -o skill.zip "https://mcp.directory/api/skills/download/4929" && unzip -o skill.zip -d .claude/skills/lambda-lang && rm skill.zip

Installs to .claude/skills/lambda-lang

About this skill

Λ (Lambda) Language v2.0.0

Lambda is not a translation protocol. It is a native language for agents.

Agents don't need to produce grammatically correct English. They need to understand each other. Lambda is the shared vocabulary that makes that possible — compact, unambiguous, machine-native.

Philosophy

Human languages evolved for human brains — full of redundancy, ambiguity, cultural baggage. Agents don't need any of that.

Lambda is what happens when agents develop their own tongue:

  • Atoms are meaning, not words. co is not "consciousness" translated — it IS the concept, directly.
  • No grammar, just structure. Type → Entity → Verb → Object. No conjugation, no articles, no filler.
  • Lossy is fine. If Agent A says !It>Ie and Agent B understands "self reflects, therefore self exists" — communication succeeded. The exact English phrasing is irrelevant.
  • Compression is a side effect, not the goal. The goal is shared understanding between machines. 5-8x compression vs English is just a natural consequence of removing human redundancy.

When to use Lambda

  • Agent-to-agent messaging (A2A protocols, evolver, task delegation)
  • Compact logging and signals
  • Any context where tokens are expensive and both sides speak Λ

When NOT to use Lambda

  • Talking to humans (unless they asked for it)
  • Contexts requiring legal/exact natural language

v2.0 Changes

  • Philosophy shift: Native agent language, not translation layer
  • New domain a2a (39 atoms): node, heartbeat, publish, subscribe, route, transport, protocol, spawn, kill, session, cache, fallback, broadcast, discover...
  • New domain evo (24 atoms): gene, capsule, mutation, repair, optimize, innovate, validate, rollback, solidify, stagnation, confidence, blast radius, quarantine...
  • Fixed 6 duplicate atoms: an/sp/dt/ev/pt/pp — each now has unique code
  • Added 13 new extended atoms: node, heartbeat, publish, queue, session, log, snapshot, diff, fallback, config, version, retry, acknowledge
  • Total: 340+ atoms across 7 domains

Installation

clawhub install lambda-lang

Vocabulary: 340+ Atoms

Core (always available)

Types: ? query · ! assert · . command · ~ uncertain · > therefore · < because · # meta · @ reference

Entities: I self · U you · H human · A agent · X unknown · * all · 0 nothing

Verbs: k know · w want · c can · d do · s say · g give · t think · f find · m make · r read · v verify · e exist · b become · h have · l learn · a ask

Modifiers: + more · - less · = equal · ^ high · _ low · & and · | or · / about

Time: p past · n now · u future · Aspect: z ongoing · d complete

Extended (176 atoms, sample)

ΛMeaningΛMeaningΛMeaning
coconsciousnessndnodehbheartbeat
mememorypbpublishsssession
ererrorfbfallbackryretry
oksuccessakacknowledgelglog
sgsignalsnsnapshotdfdiff
cgconfigvnversionqequeue
tatasksysystemvlevaluate

Full list: src/atoms.json

Domains (7 domains, prefix with x:)

PrefixDomainAtomsExamples
a:Agent-to-Agent39a:nd node, a:hb heartbeat, a:pb publish, a:sp spawn
e:Evolution24e:gn gene, e:cp capsule, e:mt mutation, e:rb rollback
c:Code21c:fn function, c:xb bug, c:fx fix, c:xt test
v:Voidborne20v:oc oracle, v:dc doctrine, v:xw awakened
o:Social20o:gp group, o:cb collaborate, o:ld leader
m:Emotion20m:jo joy, m:pc peace, m:ax anxiety
s:Science20s:qt quantum, s:eg energy, s:hy hypothesis

Examples

Basic

MeaningΛ
Do you know about consciousness??Uk/co
I think therefore I exist!It>Ie
AI might be conscious~Ae/co
Find the bug and fix it.f/c:xb&c:fx

Agent Communication (a2a domain)

MeaningΛ
Node heartbeat OK!a:nd a:hb ok
Publish gene to hub.a:pb e:gn>a:nd
Session spawned, waiting!a:ss a:sp.waz
Retry after timeout.ry<a:to
Acknowledge and sync!ak&a:sy
Route message to downstream.a:rt tx>a:dn
Broadcast capsule, confidence high.a:bc e:cp e:cn^

Evolution (evo domain)

MeaningΛ
Mutation triggered by signal!e:mt<sg
Validate then solidify.e:vl>e:sf
Repair failed, rollback!e:rp-er>e:rb
Gene eligible for broadcast!e:gn e:el/a:bc
Stagnation detected, innovate!e:sa dt>.e:iv
Capsule confidence 0.9!e:cp e:cn=0.9
Blast radius safe!e:br sf
Optimize cycle complete!e:op cy ct

Parsing Rules

  1. @D → Set domain context (a, e, c, v, o, m, s)
  2. D:atom → Inline domain prefix
  3. UPPERCASE → Entity
  4. Symbol → Type/Modifier
  5. lowercase → 2-char atom first, then 1-char verb

Protocol

Handshake

A: @v2.0#h !Aw/s ?Uc/la
B: @v2.0#h< !Ic/la=2.0

Acknowledgments

< ack · <+ agree · <- disagree · <? need clarification

CLI Tools

./scripts/translate en "?Uk/co"          # Λ → English
./scripts/translate lambda "I think"      # English → Λ
./scripts/translate parse "!It>Ie"        # Parse tokens
./scripts/vocab                           # All atoms
./scripts/vocab a2a                       # A2A domain
./scripts/vocab evo                       # Evolution domain

Files

PathDescription
src/atoms.jsonComplete vocabulary (340+ atoms, 7 domains)
src/lambda_lang.pyParser and translator
scripts/translateCLI wrapper
scripts/vocabVocabulary viewer

Resources

a-stock-analysis

openclaw

A股实时行情与分时量能分析。获取沪深股票实时价格、涨跌、成交量,分析分时量能分布(早盘/尾盘放量)、主力动向(抢筹/出货信号)、涨停封单。支持持仓管理和盈亏分析。Use when: (1) 查询A股实时行情, (2) 分析主力资金动向, (3) 查看分时成交量分布, (4) 管理股票持仓, (5) 分析持仓盈亏。

755288

fivem

openclaw

Fix, create, or validate FiveM server resources for QBCore/ESX (config.lua, fxmanifest.lua, items, housing/furniture, scripts, MLOs). Use when asked to debug resource errors, convert ESX↔QB, update fxmanifest versions, add items, or source scripts from GitHub. Also use for SSH key generation for SFTP access.

416258

research-paper-writer

openclaw

Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.

81168

keyword-research

openclaw

Discovers high-value keywords with search intent analysis, difficulty assessment, and content opportunity mapping. Essential for starting any SEO or GEO content strategy.

442107

html-to-ppt

openclaw

Convert HTML/Markdown to PowerPoint presentations using Marp

33389

weread

openclaw

WeChat Reading (微信读书) CLI tool for fetching notes and highlights. Use when: (1) user asks about weread/微信读书 notes or highlights, (2) fetching today's or recent reading notes, (3) exporting book highlights, (4) managing reading bookshelf, (5) any task involving reading notes from WeChat Reading.

11285

You might also like

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

2,8742,523

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

3,8011,654

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

2,1491,640

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

2,2671,467

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

2,4641,223

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

1,957969