OpenSkills
Stop bloating your LLM context with unused instructions
Details
- External ID
- 46716016
- Source
- HN
- Company
- —
- Product
- —
- Website domain
- —
- Launched
- Jan. 22, 2026
- Cohort
- —
- Upvotes
- 9
- Upvotes percentile
- 0.461133069828722
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
Hello HN,I’ve been building AI agents lately and ran into a common "Context Bloat" problem. When an agent has 20+ skills, stuffing every system prompt, reference doc, and tool definition into a single request quickly hits token limits and degrades model performance (the "lost in the middle" problem).To solve this, I built OpenSkills, an open-source SDK that implements a Progressive Disclosure Architecture for agent skills.The Core Concept: Instead of loading everything upfront, OpenSkills splits a skill into three layers:Layer 1 (Metadata): Light-weight tags and triggers (always loaded for discovery).Layer 2 (Instruction): The core SKILL.md prompt (loaded only when the skill is matched).Layer 3 (Resources): Heavy reference docs or scripts that are conditionally loaded based on the specific conversation context.Why this matters:Scalability: You can have hundreds of skills without overwhelming the LLM's context window.Markdown-First: Skills are defined in a simple SKILL.md format. It’s human-readable, git-friendly, and easy for the LLM to parse.Conditional Resources: For example, a "Finance Skill" only pulls in the tax-code.pdf reference if the query actually mentions tax compliance.Key Features:Python 3.10+ SDK.Automatic skill matching and invocation.Support for script execution (via [INVOKE:script_name] syntax).Multimodal support (Images via URL/base64).GitHub: [https://github.com/twwch/OpenSkills] PyPI: pip install openskills-sdk
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Horizontal
- Function
- Dev tools
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Commercial product
- Normalized one-liner
- optimize llm context with skill management
- Manually corrected
- False
Could you build this?
Yes It is a dynamic prompt management and tool-retrieval library that selects relevant agent instructions and tools on the fly based on vector similarity or rule-based matching.
Discussion
3 comments analyzed.
Concerns raised: State management across multi-step tasks with context recall, Lost in the middle problem - model forgetting earlier steps
Feature requests: Better handling of cross-step context dependencies in long workflows
Competitors
Other products that read as similar to this one — 132 launches clear the similarity bar, closest 8 shown.
Attention rank: #75 of 133 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 84 days after the earliest competitor.
- Ratel, give agents unlimited tools and skills without context bloat · hn · 2026-07-16 · 23 upvotes · similarity 0.54
- Context Gateway · hn · 2026-03-13 · 97 upvotes · similarity 0.48
- KeySkills - Skills for AI Agents · ph · 2026-09-13 · 2 upvotes · similarity 0.45
- Context-compact · hn · 2026-03-07 · 6 upvotes · similarity 0.44
- OpenClaw-superpowers · hn · 2026-03-15 · 8 upvotes · similarity 0.43
- Librarian · hn · 2026-02-26 · 8 upvotes · similarity 0.42
- Context Surgeon · hn · 2026-04-13 · 5 upvotes · similarity 0.42
- A package manager for agent skills with built-in evals · hn · 2026-02-05 · 7 upvotes · similarity 0.41
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a dev tools tool for Sales yet.