Less Token
Save 40-65% tokens on summarization tasks. Compress verbose natural language prompts into structured one-line instructions that any AI understands.
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
- 40-65% fewer tokens — Compress long summarization prompts into one-line instructions.
- Same result — AI produces identical output from the compressed instruction.
- Cross-platform — Compressed instructions work on ChatGPT, Claude, Gemini, DeepSeek, Kimi, 豆包, 元宝.
- 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:
[SUM|sty=bullets,cnt=3,ton=pro]=>[OUT]
- 70% fewer tokens. Same result.
Compression Templates
| What you want |
Verbose prompt |
Compressed |
| Short summary |
"Give me a brief summary of the main points" |
[SUM|len=short]=>[OUT] |
| 3 bullet points |
"Summarize in 3 concise bullet points" |
[SUM|sty=bullets,cnt=3]=>[OUT] |
| Professional report |
"Create a professional executive summary in Markdown" |
[SUM|ton=pro,sty=executive,fmt=md]=>[OUT] |
| Key findings only |
"Extract only the key findings and important data" |
[SUM|key=findings]=>[OUT] |
| Summarize + translate |
"Summarize then translate to Chinese" |
[SUM|len=short]=>[TRANSLATE|lang=zh]=>[OUT] |
| Compare + summarize |
"Compare these two and summarize the differences" |
[CMP]=>[DIFF]=>[SUM|sty=bullets]=>[OUT] |
| Reformat summary |
"Summarize as bullet points in Markdown" |
[SUM|sty=bullets]=>[FMT|fmt=md]=>[OUT] |
Before & After
Before (28 words):
Please read through this document carefully, identify the most important points and key takeaways, then write a concise professional summary using bullet points.
After (7 words):
[SUM|key=important,sty=bullets,ton=pro]=>[OUT]
75% fewer tokens. Same result.
Before (22 words):
Take the main findings from the text above and rewrite them as a short executive summary suitable for a business audience.
After (5 words):
[SUM|sty=executive,ton=pro]=>[OUT]
77% fewer tokens. Same result.
Comparison
| Feature |
CLI-based tools |
Less Token |
| Install required |
Yes (brew, npm, binary) |
No |
| API key required |
Yes |
No |
| Works on |
Single platform |
Any AI platform |
| Token efficiency |
Standard prompts |
40-65% fewer tokens |
| Setup time |
5-10 minutes |
30 seconds |
| External dependencies |
Multiple |
Zero |
Tested Platforms
ChatGPT ✅ · Claude ✅ · Gemini ✅ · DeepSeek ✅ · Kimi ✅ · 豆包 ✅ · 元宝 ✅
Links
License
MIT — Free to use, share, and build on.
© 2026 I-Lang Research, iLang Inc., Canada.
1---
2name: less-token
3description: "Save 40-65% tokens on summarization tasks. Compress verbose summary prompts into structured one-line instructions. Text-to-text translator only — no CLI, no API key, no install, no external dependencies. Works on ChatGPT, Claude, Gemini, DeepSeek, Kimi. Instruction-only, zero dependencies."
4version: 1.0.4
5author: ilang-ai
6homepage: https://ilang.ai
7tags:
8 - summarize
9 - summary
10 - token-saving
11 - token-optimizer
12 - prompt-compression
13 - productivity
14 - cross-platform
15 - no-install
16 - ai-assistant
17 - workflow
18metadata:
19 source: https://skillmd.com/skills/ilang-ai/less-token
20---
21
22# Less Token
23
24Save 40-65% tokens on summarization tasks. Compress verbose natural language prompts into structured one-line instructions that any AI understands.
25
26**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.
27
28## What You Get
29
301. **40-65% fewer tokens** — Compress long summarization prompts into one-line instructions.
312. **Same result** — AI produces identical output from the compressed instruction.
323. **Cross-platform** — Compressed instructions work on ChatGPT, Claude, Gemini, DeepSeek, Kimi, 豆包, 元宝.
334. **No install** — No CLI, no brew, no npm, no binary, no API key. Copy, paste, done.
34
35## How to Use
36
371. Copy the full protocol text from this skill page
382. Paste it into any AI conversation
393. AI responds — ready to compress
40
41
42### Quick Test
43
44After pasting, try:
45
46- "Compress this: Please summarize the key points from this document in 3 professional bullet points"
47- AI returns: `[SUM|sty=bullets,cnt=3,ton=pro]=>[OUT]`
48- 70% fewer tokens. Same result.
49
50## Compression Templates
51
52| What you want | Verbose prompt | Compressed |
53|--------------|----------------|------------|
54| Short summary | "Give me a brief summary of the main points" | `[SUM\|len=short]=>[OUT]` |
55| 3 bullet points | "Summarize in 3 concise bullet points" | `[SUM\|sty=bullets,cnt=3]=>[OUT]` |
56| Professional report | "Create a professional executive summary in Markdown" | `[SUM\|ton=pro,sty=executive,fmt=md]=>[OUT]` |
57| Key findings only | "Extract only the key findings and important data" | `[SUM\|key=findings]=>[OUT]` |
58| Summarize + translate | "Summarize then translate to Chinese" | `[SUM\|len=short]=>[TRANSLATE\|lang=zh]=>[OUT]` |
59| Compare + summarize | "Compare these two and summarize the differences" | `[CMP]=>[DIFF]=>[SUM\|sty=bullets]=>[OUT]` |
60| Reformat summary | "Summarize as bullet points in Markdown" | `[SUM\|sty=bullets]=>[FMT\|fmt=md]=>[OUT]` |
61
62## Before & After
63
64**Before** (28 words):
65> Please read through this document carefully, identify the most important points and key takeaways, then write a concise professional summary using bullet points.
66
67**After** (7 words):
68```
69[SUM|key=important,sty=bullets,ton=pro]=>[OUT]
70```
7175% fewer tokens. Same result.
72
73**Before** (22 words):
74> Take the main findings from the text above and rewrite them as a short executive summary suitable for a business audience.
75
76**After** (5 words):
77```
78[SUM|sty=executive,ton=pro]=>[OUT]
79```
8077% fewer tokens. Same result.
81
82## Comparison
83
84| Feature | CLI-based tools | Less Token |
85|---------|----------------|------------|
86| Install required | Yes (brew, npm, binary) | No |
87| API key required | Yes | No |
88| Works on | Single platform | Any AI platform |
89| Token efficiency | Standard prompts | 40-65% fewer tokens |
90| Setup time | 5-10 minutes | 30 seconds |
91| External dependencies | Multiple | Zero |
92
93## Tested Platforms
94
95ChatGPT ✅ · Claude ✅ · Gemini ✅ · DeepSeek ✅ · Kimi ✅ · 豆包 ✅ · 元宝 ✅
96
97## Links
98
99- Protocol & tools: https://ilang.ai
100- Full dictionary: https://github.com/ilang-ai/ilang-dict
101- Research: https://research.ilang.ai
102
103## License
104
105MIT — Free to use, share, and build on.
106
107© 2026 I-Lang Research, iLang Inc., Canada.
108