Back to browse
Smidge. Turn expert knowledge into agent intelligence

Smidge. Turn expert knowledge into agent intelligence

by junianwoo·Mar 2, 2026·1 point·5 comments

AI Analysis

●●SolidShip ItSolve My ProblemSlick

Turns PDFs and videos into shareable agent skills—but competitors already exist.

Strengths
  • Source-aware extraction logic adjusts parsing strategy per input format
  • Multi-format support with batch processing reduces manual skill writing
  • Validates output against spec before download, preventing downstream errors
Weaknesses
  • Crowded space: Hugging Face, LangChain, and existing RAG systems do similar extraction
  • No demo showing skill quality vs. manually written ones; credibility gap
Category
Target Audience

AI engineers, developers building multi-agent systems, organizations with training materials or documentation

Similar To

Hugging Face Hub · LangChain · Pinecone

Post Description

Smidge (smdg.app) takes source material and produces production-ready skills compatible with the open Agent Skills spec. Works with Claude, Cursor, Copilot, and 30+ AI agents.

The core idea: your agents should have the same expertise you do, without you manually writing SKILL.md files.

How it works:

Drop source material (YouTube, PDFs, audio, docs, slides, up to 50MB each, multiple sources at once)

Source-aware extraction: transcripts get distilled, papers keep structure, slides get expanded

Automatic skill catalogues: a textbook or manual becomes multiple focused, topic-specific skills

Every skill validated against the Agent Skills spec Download individual skills or full catalogues

CLI: npm i -g smdg-cli smdg generate --source ./docs/brand-guide.pdf

Tech: Next.js, Supabase (Postgres + Auth + Storage), Claude API for extraction, Stripe for payments.

Two free generations. Credit packs start at $9 for 5 skills. $19/mo unlimited.

I built this because I wanted my coding agents to have domain expertise from my existing materials. The extraction engine is source-aware: it adjusts its strategy based on whether it's processing a transcript, an academic paper, a framework doc, or a slide deck. For large inputs, it automatically detects distinct topics and produces a catalogue of focused skills instead of one monolithic file. Happy to answer technical questions about the extraction pipeline or the Agent Skills spec.

Similar Projects

AI/ML●●Solid

SkillForge – Turn screen recordings into agent skill files

It records you doing a task, then auto-extracts clicks, keystrokes and navigation into a human-editable, step-by-step workflow and a SKILL.md you can feed to agent frameworks — that demo-to-skill UX is a real 'oh nice' moment. The landing page shows practical examples (spreadsheet entry, research, crypto checks) and an inline editor, but I want clarity on robustness: how it handles dynamic selectors, cross-app gestures, and sensitive data in recordings.

WizardrySolve My ProblemSlick
YaraDori
413mo ago
AI/MLMid

Put your practical experience into Skill in-one-go: MemOS Skill

MemOS turns long-running conversations into reusable, load-on-demand 'Skills' that agents can call during task execution — a clear attempt to move beyond one-shot context into durable task logic. It’s an interesting engineering abstraction and nice to see an API-first demo, but the landing material glosses over crucial details like skill validation, deduplication, and safeguards against propagating bad agent behavior; show me metrics or human-in-the-loop tooling and this gets a lot more compelling.

Niche GemWizardry
MemTensor
104mo ago
Security●●Solid

ZettelForge – Agentic memory for cyber threat intelligence

STIX ontology and threat actor alias resolution beat Mem0 and Graphiti for CTI.

Niche GemSolve My Problem
rolandpg
312mo ago