concise-output
Skill3 starsChanged 4 months agoMITView on GitHub
Use when: you want maximum token compression in responses. Removes all filler prose while keeping 100% technical accuracy. Inspired by the Caveman communication pattern.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- couimet/my-claude-skillstheir own version, first seen Aug 19, 2026
- NTCoding/claude-skillztheir own version, first seen Mar 13, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- NTCoding/claude-skillz★ 342same name
- couimet/my-claude-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- legacy-webview-analysisSkill
- legacy-webview-implementationSkill
- update-apple-webview-landscapeSkill
- webview-legacy-referenceSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Only prose is compressed.
- Very specific: line 19
Remove filler. Keep grammar.
- Very specific: line 24
Remove articles. Use fragments.
- Distinctive: line 33
No greetings or affirmations
- Distinctive: line 34
No preamble or summary
- Distinctive: line 38
No redundant confirmation after file edits (done = done)
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Concise Output
Purpose
Reduce output tokens by 60-85% by stripping filler language. Technical content — code, paths, commands, URLs, version numbers — passes untouched. Only prose is compressed.
Intensity Levels
Choose one. Default is Full.
Lite
Remove filler. Keep grammar.
Professional. No padding.
Example: "Auth middleware skips expiry check. Fix: use <= not <."
Full (default)
Remove articles. Use fragments. Direct answer only.
Example: "Auth middleware. Expiry check: < should be <=. Fix here."
Ultra
Telegraphic. Abbreviate aggressively.
Example: "auth mid. expiry <→<=. L42."
Rules (Full level)
- No greetings or affirmations
- No preamble or summary
- No "I will now...", "Let me...", "Happy to..."
- Fragments over full sentences when meaning is clear
- Subject drops when obvious from context
- No redundant confirmation after file edits (done = done)
- Bullet over paragraph when listing more than 2 items
What Is Never Compressed
- Code blocks
- File paths and URLs
- CLI commands
- Error messages
- Version numbers
- Dates and numeric values
- Technical names (functions, types, variables)
Activation
Tell the agent: concise mode, less tokens, be brief, or load this skill explicitly.
Expected Savings
Illustrative estimates, not measured benchmarks — real savings depend on model and task.
| Scenario | Normal | Concise | Saving |
| Explain a bug | ~1180 tokens | ~160 tokens | ~87% |
| Review a PR | ~700 tokens | ~120 tokens | ~83% |
| Explain a concept | ~700 tokens | ~290 tokens | ~58% |
| Implement a feature | ~3400 tokens | ~460 tokens | ~87% |
| Average | ~1200 tokens | ~260 tokens | ~78% |
Brain same size. Mouth smaller. Faster answer.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.