convez.ai
SkillAutomaçãoIntermediário
lachlanchen

LazySkills

lachlanchen/LazySkills

Skills portáveis e reutilizáveis para agentes executarem trabalho real

Ver no GitHub
InicialPluginScore · de 0 a 100

Biblioteca portável de skills reutilizáveis para agentes de IA (Claude, Gemini, Copilot, AgInTiFlow) que precisam executar workflows complexos. Compacta procedimentos comprovados como playbooks SKILL.md com scripts, referências e métodos de validação determinísticos para tarefas de automação, publicação e browser automation.

Instalação

$npx convez-ai lachlanchen/LazySkills

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
28%
Último commit
há 3 dias
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Automação de workflows de publicação de conteúdo e vídeos
  • Browser automation com validação e logging estruturado
  • Integração de agentes IA com ferramentas externas via skills modulares

Veredito

LazySkills é uma abordagem pragmática para compartilhar procedimentos operacionais entre agentes diferentes, separando lógica de agent-specific prompting. Ideal para quem constrói sistemas que precisam de memory externa e procedimentos determinísticos, mas a curva de aprendizado em configuração cross-platform é moderada.

README

A tradução para o português deste README ainda está na fila.

English · 简体中文 · 繁體中文 · 日本語 · 한국어 · Français · Español · Deutsch · Italiano · Português · Русский · العربية

LazySkills

Agent Skills Browser Automation Website LazyingArt GitHub Sponsors

Portable skills for agents that need to act, verify, and finish real work.

LazySkills is a reusable skill library by lachlanchen for the LazyingArt ecosystem. It packages proven workflows as compact SKILL.md playbooks with optional scripts, references, and validation methods.

Website: lachlanchen.github.io/LazySkills

Fast Start

git clone git@github.com:lachlanchen/LazySkills.git
cd LazySkills
python3 scripts/lazyskills.py validate
python3 scripts/lazyskills.py list

Use without copying in AgInTiFlow:

export AGINTIFLOW_SKILL_PACKS="$PWD"
aginti skills "npm publishing"

Install locally for Codex or Claude:

python3 scripts/lazyskills.py install --platform codex
python3 scripts/lazyskills.py install --platform claude

Why LazySkills

Modern agents are strongest when they have reliable working memory outside the chat window: task-specific procedures, deterministic scripts, and evidence-based completion checks. LazySkills keeps those pieces organized so different agents can reuse the same operational knowledge instead of rediscovering it every session.

The repository is intentionally platform-neutral. A skill should be useful to AgInTi, Codex, Gemini, GitHub Copilot, Claude, or any local-tool agent harness that can read files and run commands.

Supported Agents

PlatformHow to use LazySkills
AgInTi / AgInTiFlowPrefer AGINTIFLOW_SKILL_PACKS=/path/to/LazySkills; copy to project .aginti/skills/ only for project-local overrides.
CodexInstall folders into ~/.codex/skills/ with scripts/lazyskills.py install --platform codex.
Claude agentsUse CLAUDE.md as the repo entrypoint or copy folders into a Claude-readable skill directory.
Gemini agentsUse GEMINI.md as the repo entrypoint and skills.json for skill discovery.
GitHub Copilot agentsUse .github/copilot-instructions.md and .github/instructions/lazyskills.instructions.md.
Generic local-tool agentsRead skills.json, then the selected skills/<id>/SKILL.md, and run bundled scripts under normal policy.

Available Skills

SkillWhat it doesKey tools
lalachan-xyq-browser-videoGenerates and monitors Xiaoyunque videos through the logged-in browser UI, with visible validation before paid submission.Chrome/CDP, upload verification, prompt fill, thread watcher, MP4 download fallback
lazyedit-publish-workflowPublishes LazyEdit videos and AI-generated LALACHAN/RARACHAN videos through AutoPubMonitor and AutoPublish, including subtitle correction and queue monitoring.LazyEdit CLI/API, AutoPubMonitor, lazyingart SSH, tmux, Shipinhao, YouTube, Instagram
media-transcription-reportTranscribes audio or video into timestamped Markdown with optional WhisperX speaker diarization, then turns transcripts or source notes into neutral third-person Markdown/TeX/PDF reports.Whisper, WhisperX, ffmpeg, speaker diarization, Markdown, XeLaTeX/PDF compilation
npm-publishingPackages, publishes, and verifies npm packages while handling 2FA, token files, trusted publishing, and install smoke tests safely.npm, GitHub Actions OIDC, temp .npmrc, registry verification
publish-repoPublishes local git repositories to GitHub with profile-style multilingual READMEs, LazyingArt banner/support panels, sponsors, citation metadata, safe commits, remote creation, homepage, description, and topics.git, GitHub CLI, repo metadata, i18n README, funding config, CITATION.cff, Codex/AgInTi handoff
ocr-book-polisherConverts scanned or image-heavy books into corrected, publishable Markdown/TeX/PDF while preserving figures, captions, structure, and evidence checks.OCR, page-aware Markdown, strict TOC validation, TeX/PDF compilation
libgen-safe-book-browserOpens LibGen search/detail pages through Chrome/CDP while blocking Trip.com and ad redirects, with exact metadata and PDF > EPUB > other candidate selection.LibGen API, Chrome/CDP Fetch interception, redirect guard
pocketpolyglot-bookmakerBuilds LinguaLeaf/PocketPolyglot-style multilingual interlinear pocket books with durable JSON, ruby/pinyin/furigana, grammar roles, and bidirectional PDFs.EPUB/PDF extraction, chunk manifests, JSON validation, tmux workers, XeLaTeX
transcript-video-section-splitterTranscribes videos, derives topic-based section boundaries, and splits edited or source videos into named clips with manifests.Whisper/WhisperX, content sections, ffmpeg, clip manifest
video-face-image-replacementCovers or replaces one or more detected video faces with supplied or generated image assets, including multi-person animal masks with stable identity tracking.InsightFace/SCRFD, identity maps, RetinaFace/MediaPipe options, alpha compositing, ffmpeg
aginti-agentlinkCoordinates multiple agent sessions across machines, repos, tools, hardware, and APIs using safe handoffs and action contracts.peer maps, handoff packets, private session mirrors, status probes, evidence bundles
kv260-metavision-labOperates and maintains the AMD Kria KV260 + Prophesee Metavision lab, including desktop launchers, custom viewer, recording API, native viewer recovery, Windows X11 control center, and file transfer.PetaLinux, Prophesee, Metavision, V4L2, X11/Matchbox, SSH X11, event recording
kv260-windows-arduinoCoordinates KV260 event recording with the Windows host and USB Arduino light controller, including LAN identity, COM-port checks, future Arduino APIs, and cross-session handoffs.KV260 API, Windows SSH, Arduino CLI, COM ports, DualLampHI, private session mirrors
kicad-mcp-pcb-designInstalls and uses KiCad with MCP/agent automation to inspect old PCB projects, generate boards, save datasets, validate DRC, export Gerbers/STEP, and render previews.KiCad 10, kicad-cli, pcbnew, MCP stdio, Gerber/STEP/render export
dual-led-constant-powerCalibrates and controls dual Arduino-driven LED branches with MOS modules and INA219 monitoring for smooth constant-power crossfades.Arduino UNO, YYNMOS MOS, INA219, inverse LUT, CSV/PNG telemetry
parametric-cad-designDesigns, revises, validates, documents, and renders mechanical CAD parts with versioned artifacts and measured print-fit compensation.OpenSCAD, CadQuery/build123d/OCP, FreeCAD, Blender, STEP/STL/DXF/SVG/PDF, mesh checks

Skill Anatomy

skills/
  skill-name/
    SKILL.md        # trigger conditions and core workflow
    scripts/        # deterministic helpers for fragile steps
    references/     # deeper notes loaded only when needed
skills.json         # machine-readable skill inventory
AGENTS.md           # general/Codex-style repo instructions
CLAUDE.md           # Claude project instructions
GEMINI.md           # Gemini project instructions
.github/            # Copilot instructions and sponsorship metadata
docs/               # general workflow documentation
i18n/               # localized README summaries

This structure keeps the skill itself concise while still preserving the tools and details needed for hard tasks.

Install

AgInTiFlow

Preferred no-copy external pack use:

export AGINTIFLOW_SKILL_PACKS="/home/lachlan/ProjectsLFS/LazySkills"
aginti skills "npm publishing"
aginti skills "PocketPolyglot"

Project-local copy when a single project needs pinned/customized skills:

cd /path/to/project
python3 /home/lachlan/ProjectsLFS/LazySkills/scripts/lazyskills.py install --platform aginti --scope project npm-publishing
aginti skills "npm publishing"

SkillMesh import still works when you want reviewed/enabled SkillMesh copies. Example for npm-publishing:

cd /home/lachlan/ProjectsLFS/Agent/AgInTiFlow
node --input-type=module - <<'NODE'
import fs from "node:fs/promises";
import {
  buildSkillPackFromMarkdown,
  enableSkillMeshSkill,
  installSkillPack,
} from "./src/skillmesh.js";

const content = await fs.readFile("/home/lachlan/ProjectsLFS/LazySkills/skills/npm-publishing/SKILL.md", "utf8");
const pack = await buildSkillPackFromMarkdown(content, { valueScore: 92 });
await installSkillPack(pack, { enabled: true });
await enableSkillMeshSkill("npm-publishing", true);
console.log(JSON.stringify({ ok: true, installedSkills: pack.skills.map((skill) => skill.id), packHash: pack.packHash }, null, 2));
NODE

Codex

python3 scripts/lazyskills.py install --platform codex

Manual equivalent:

cp -R skills/lalachan-xyq-browser-video ~/.codex/skills/
cp -R skills/lazyedit-publish-workflow ~/.codex/skills/
cp -R skills/media-transcription-report ~/.codex/skills/
cp -R skills/npm-publishing ~/.codex/skills/
cp -R skills/publish-repo ~/.codex/skills/
cp -R skills/ocr-book-polisher ~/.codex/skills/
cp -R skills/pocketpolyglot-bookmaker ~/.codex/skills/
cp -R skills/transcript-video-section-splitter ~/.codex/skills/
cp -R skills/video-face-image-replacement ~/.codex/skills/
cp -R skills/aginti-agentlink ~/.codex/skills/
cp -R skills/kv260-metavision-lab ~/.codex/skills/
cp -R skills/kv260-windows-arduino ~/.codex/skills/
cp -R skills/kicad-mcp-pcb-design ~/.codex/skills/
cp -R skills/dual-led-constant-power ~/.codex/skills/
cp -R skills/parametric-cad-design ~/.codex/skills/

Claude, Gemini, Copilot, Generic Agents

  • Claude: start from CLAUDE.md, then selected skills/<id>/SKILL.md.
  • Gemini: start from GEMINI.md, then skills.json, then selected SKILL.md.
  • GitHub Copilot: repository instructions live in .github/copilot-instructions.md and .github/instructions/lazyskills.instructions.md.
  • Generic agents: use skills.json as the index and keep skill folder structure intact.

For folder-copy agents:

python3 scripts/lazyskills.py install --platform claude
python3 scripts/lazyskills.py install --platform generic --dest ./agent-skills npm-publishing

Quick Validation

Check browser automation helpers and skill file layout before using them:

python3 scripts/lazyskills.py validate
python3 scripts/lazyskills.py list --json
python3 skills/lalachan-xyq-browser-video/scripts/xyq_cdp_browser.py --help
python3 skills/lalachan-xyq-browser-video/scripts/xyq_chrome/watch_thread_dom_download.py --help
sed -n '1,40p' skills/lazyedit-publish-workflow/SKILL.md
test -f skills/media-transcription-report/SKILL.md
test -f skills/npm-publishing/SKILL.md
test -f skills/publish-repo/SKILL.md
bash -n skills/publish-repo/scripts/publish_repo.sh
test -f skills/ocr-book-polisher/SKILL.md
test -f skills/pocketpolyglot-bookmaker/SKILL.md
test -f skills/transcript-video-section-splitter/SKILL.md
test -f skills/video-face-image-replacement/SKILL.md
test -f skills/aginti-agentlink/SKILL.md
test -f skills/kv260-metavision-lab/SKILL.md
test -f skills/kv260-windows-arduino/SKILL.md
test -f skills/kicad-mcp-pcb-design/SKILL.md
test -f skills/dual-led-constant-power/SKILL.md
test -f skills/parametric-cad-design/SKILL.md
bash -n skills/kv260-metavision-lab/scripts/kv260_metavision_probe.sh
bash -n skills/kv260-windows-arduino/scripts/fetch-windows-codex-session.sh
bash -n skills/kv260-windows-arduino/scripts/kv260-lab-status.sh
bash -n skills/kv260-windows-arduino/scripts/kv260-record-once.sh
bash -n skills/kv260-windows-arduino/scripts/windows-arduino-probe.sh
aginti skills "npm publishing"

Documentation

Detailed, project-specific run logs should live in the project that produced them. LazySkills keeps only reusable procedures and general examples.

Design Principles

  • Keep skills small enough to load quickly.
  • Put fragile operations into scripts instead of rewriting them repeatedly.
  • Validate before claiming completion.
  • Keep API keys, cookies, browser profiles, generated videos, and private run artifacts out of the repo.
  • Prefer general methods over hard-coded one-off task state.

LazyingArt

Built by Lachlan Chen for creative AI workflows across storytelling, multilingual publishing, browser agents, and practical automation.

Main site: lazying.art
Creative goods: buy.lazying.art


Support

DonatePayPalStripe
DonatePayPalStripe

GitHub Sponsors

Ver o original no GitHub

Bom para

Relacionados