Compress chunks before the prompt
long mixed documents where only a paragraph answers the query, and token cost at generation matters more than an extra model call.
Skill by ToXMon
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/toxmon-compress-chunks-before-the-prompt
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/compress-chunks-before-the-prompt
What's inside
- Skill name
Compress chunks before the prompt- Description
- long mixed documents where only a paragraph answers the query, and token cost at generation matters more than an extra model call.
- License
- unknown
- Instructions
- 21 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "Compress chunks before the prompt" does not match folder "compress-chunks-before-the-prompt"
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from ToXMon/production-rag
- 0.551score
Embed page images when layout is the content
ToXMon
financial reports, technical docs, papers with figures or formulas, contracts, medical records, or anything where tables and charts must survive.
SkillAFreshness: AClaude Code +9 - 0.548score
Answer multi-hop questions with a knowledge graph
ToXMon
the answer connects facts that never appear in one chunk (who works in the same department as the CEO's assistant).
SkillAFreshness: AClaude Code +9 - 0.548score
Add hybrid BM25 plus vector search
ToXMon
production queries that include SKUs, acronyms (WCAG example), error codes (the intended example is a connection-refused code; captions say "econ refuse"), or…
SkillAFreshness: AClaude Code +9 - 0.545score
Cut vector-search cost without a new vendor
ToXMon
after a workload exists, not before the first prototype.
SkillAFreshness: AClaude Code +9 - 0.545score
Diagnose the five production failure modes
ToXMon
a demo works on about 10 documents and breaks around 10,000, or answers go wrong in production.
SkillAFreshness: AClaude Code +9 - 0.545score
Choose a chunking strategy
ToXMon
before embedding.
SkillAFreshness: AClaude Code +9 - 0.545score
Cache embedding calls and repeated answers
ToXMon
the same text is embedded twice, or the same question is asked again.
SkillAFreshness: AClaude Code +9 - 0.545score
Create a Chroma collection and query it
ToXMon
local vector store for development.
SkillAFreshness: AClaude Code +9 - 0.542score
Load raw files into LangChain Documents
ToXMon
before chunking, whenever context comes from files or URLs.
SkillAFreshness: AClaude Code +9 - 0.542score
Assemble a basic LangChain RAG chain
ToXMon
first end-to-end chain after chunks exist.
SkillAFreshness: AClaude Code +9 - 0.542score
Bootstrap the course Python project
ToXMon
starting the local environment the course codes against.
SkillAFreshness: AClaude Code +9 - 0.542score
Choose a vector host by scale
ToXMon
picking Chroma versus Pinecone versus pgvector.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 4, 2026 (24 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/ToXMon/production-rag
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ToXMon
- 0.551score
Embed page images when layout is the content
ToXMon
financial reports, technical docs, papers with figures or formulas, contracts, medical records, or anything where tables and charts must survive.
SkillAFreshness: AClaude Code +9 - 0.548score
Answer multi-hop questions with a knowledge graph
ToXMon
the answer connects facts that never appear in one chunk (who works in the same department as the CEO's assistant).
SkillAFreshness: AClaude Code +9 - 0.548score
Add hybrid BM25 plus vector search
ToXMon
production queries that include SKUs, acronyms (WCAG example), error codes (the intended example is a connection-refused code; captions say "econ refuse"), or…
SkillAFreshness: AClaude Code +9 - 0.545score
Create a Chroma collection and query it
ToXMon
local vector store for development.
SkillAFreshness: AClaude Code +9 - 0.545score
Choose a chunking strategy
ToXMon
before embedding.
SkillAFreshness: AClaude Code +9 - 0.545score
Cache embedding calls and repeated answers
ToXMon
the same text is embedded twice, or the same question is asked again.
SkillAFreshness: AClaude Code +9
Cite this page
Compress chunks before the prompt skill. Agent Mart. https://agentmart.dev/skills/toxmon-compress-chunks-before-the-prompt (last updated 2026-10-24)