Less Token
Compress verbose summarization prompts into structured one-line instructions.
This skill is a text-to-text translator only. It does not access files, fetch URLs, execute commands, or call external services. It only converts your summarization prompts into compressed syntax.
What You Get
- Shorter prompts — Compress long summarization prompts into one-line instructions.
- Same task — The compressed instruction asks for the same result.
- Cross-platform — I-Lang has been tested across ChatGPT, Claude, Gemini, DeepSeek, Kimi, Qwen and GLM (results: ilang.ai/benchmark/, May 2026).
- No install — No CLI, no brew, no npm, no binary, no API key. Copy, paste, done.
How to Use
- Copy the full protocol text from this skill page
- Paste it into any AI conversation
- AI responds — ready to compress
Quick Test
After pasting, try:
- "Compress this: Please summarize the key points from this document in 3 professional bullet points"
- AI returns:
[SHRT|sty=bullets,len=3,ton=pro]=>[OUT]
Compression Templates
| What you want |
Verbose prompt |
Compressed |
| Short summary |
"Give me a brief summary of the main points" |
[SHRT|len=short]=>[OUT] |
| 3 bullet points |
"Summarize in 3 concise bullet points" |
[SHRT|sty=bullets,len=3]=>[OUT] |
| Professional report |
"Create a professional executive summary in Markdown" |
[SHRT|ton=pro,sty=executive,fmt=md]=>[OUT] |
| Key findings only |
"Extract only the key findings and important data" |
[SHRT|whr=findings]=>[OUT] |
| Summarize + translate |
"Summarize then translate to Chinese" |
[SHRT|len=short]=>[XLAT|lng=zh]=>[OUT] |
| Compare + summarize |
"Compare these two and summarize the differences" |
[DIFF]=>[SHRT|sty=bullets]=>[OUT] |
| Reformat summary |
"Summarize as bullet points in Markdown" |
[SHRT|sty=bullets]=>[FMT|fmt=md]=>[OUT] |
Before & After
Before:
Please read through this document carefully, identify the most important points and key takeaways, then write a concise professional summary using bullet points.
After:
[SHRT|whr=important,sty=bullets,ton=pro]=>[OUT]
Before:
Take the main findings from the text above and rewrite them as a short executive summary suitable for a business audience.
After:
[SHRT|sty=executive,ton=pro]=>[OUT]
Comparison
| Feature |
CLI-based tools |
Less Token |
| Install required |
Yes (brew, npm, binary) |
No |
| API key required |
Yes |
No |
| Platforms |
Single platform |
I-Lang tested on ChatGPT, Claude, Gemini, DeepSeek, Kimi, Qwen and GLM |
| Token efficiency |
Standard prompts |
Shorter one-line prompts |
| Setup time |
5-10 minutes |
30 seconds |
| External dependencies |
Multiple |
Zero |
Tested Platforms
I-Lang has been tested across ChatGPT, Claude, Gemini, DeepSeek, Kimi, Qwen and GLM. Results by model are published on ilang.ai/benchmark/, tests conducted May 2026.
Links
License
MIT — Free to use, share, and build on.
© 2026 I-Lang Research, iLang Inc., Canada.
1---2name: less-token3description: Compress verbose summary prompts into structured one-line instructions. Text-to-text translator only — no CLI, no API key, no install, no external dependencies. I-Lang has been tested across ChatGPT, Claude, Gemini, DeepSeek, Kimi, Qwen and GLM. Instruction-only, zero dependencies.4---56# Less Token78Compress verbose summarization prompts into structured one-line instructions.910**This skill is a text-to-text translator only.** It does not access files, fetch URLs, execute commands, or call external services. It only converts your summarization prompts into compressed syntax.1112## What You Get13141. **Shorter prompts** — Compress long summarization prompts into one-line instructions.152. **Same task** — The compressed instruction asks for the same result.163. **Cross-platform** — I-Lang has been tested across ChatGPT, Claude, Gemini, DeepSeek, Kimi, Qwen and GLM (results: ilang.ai/benchmark/, May 2026).174. **No install** — No CLI, no brew, no npm, no binary, no API key. Copy, paste, done.1819## How to Use20211. Copy the full protocol text from this skill page222. Paste it into any AI conversation233. AI responds — ready to compress242526### Quick Test2728After pasting, try:2930- "Compress this: Please summarize the key points from this document in 3 professional bullet points"31- AI returns: `[SHRT|sty=bullets,len=3,ton=pro]=>[OUT]`3233## Compression Templates3435| What you want | Verbose prompt | Compressed |36|--------------|----------------|------------|37| Short summary | "Give me a brief summary of the main points" | `[SHRT\|len=short]=>[OUT]` |38| 3 bullet points | "Summarize in 3 concise bullet points" | `[SHRT\|sty=bullets,len=3]=>[OUT]` |39| Professional report | "Create a professional executive summary in Markdown" | `[SHRT\|ton=pro,sty=executive,fmt=md]=>[OUT]` |40| Key findings only | "Extract only the key findings and important data" | `[SHRT\|whr=findings]=>[OUT]` |41| Summarize + translate | "Summarize then translate to Chinese" | `[SHRT\|len=short]=>[XLAT\|lng=zh]=>[OUT]` |42| Compare + summarize | "Compare these two and summarize the differences" | `[DIFF]=>[SHRT\|sty=bullets]=>[OUT]` |43| Reformat summary | "Summarize as bullet points in Markdown" | `[SHRT\|sty=bullets]=>[FMT\|fmt=md]=>[OUT]` |4445## Before & After4647**Before**:48> Please read through this document carefully, identify the most important points and key takeaways, then write a concise professional summary using bullet points.4950**After**:51```52[SHRT|whr=important,sty=bullets,ton=pro]=>[OUT]53```5455**Before**:56> Take the main findings from the text above and rewrite them as a short executive summary suitable for a business audience.5758**After**:59```60[SHRT|sty=executive,ton=pro]=>[OUT]61```6263## Comparison6465| Feature | CLI-based tools | Less Token |66|---------|----------------|------------|67| Install required | Yes (brew, npm, binary) | No |68| API key required | Yes | No |69| Platforms | Single platform | I-Lang tested on ChatGPT, Claude, Gemini, DeepSeek, Kimi, Qwen and GLM |70| Token efficiency | Standard prompts | Shorter one-line prompts |71| Setup time | 5-10 minutes | 30 seconds |72| External dependencies | Multiple | Zero |7374## Tested Platforms7576I-Lang has been tested across ChatGPT, Claude, Gemini, DeepSeek, Kimi, Qwen and GLM. Results by model are published on ilang.ai/benchmark/, tests conducted May 2026.7778## Links7980- Protocol & tools: https://ilang.ai81- Full dictionary: https://github.com/ilang-ai/ilang-dict82- Research: https://research.ilang.ai8384## License8586MIT — Free to use, share, and build on.8788© 2026 I-Lang Research, iLang Inc., Canada.89
gabrielmoreira