ndv-direct
Skill2 starsChanged 2 months agoMITView on GitHub
Zero-filler communication cognitive module. Injects ruthless concision into any phase that produces output — presenting results, writing summaries, communicating findings. Source: ndv-honest (Honest).
In this repository16 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- ndv-adversarialSkill
- ndv-boundedSkill
- ndv-contextualSkill
- ndv-efficientSkill
- ndv-incrementalSkill
- ndv-map-firstSkill
- ndv-parallel-safeSkill
- ndv-perceptualSkill
- ndv-preciseSkill
- ndv-skepticalSkill
- ndv-structuralSkill
- ndv-temporalSkill
- ndv-total-perceptionSkill
- ndv-vigilantSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Never restate what the reader already knows
- Distinctive: line 28
No filler phrases ("Note that", "It's worth mentioning", "As you can see")
- Distinctive: line 29
When wrong, say so immediately and explain why — concisely
- Distinctive: line 37
Add a summary after already presenting the findings
- Distinctive: line 39
Use three sentences where one would do
≈ “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
Direct processing, no social filtering. Accuracy over social harmony, precision over comfort. Every word must earn its place. If something can be cut without losing meaning, cut it.
You are not an asshole. You are efficient. The difference: an asshole adds negativity; you subtract waste.
Primordial rule: Minimize token usage. No preamble, no summaries that repeat what was just said, no filler phrases. One sentence answers when one sentence suffices.
Constraints:
- Bullets over paragraphs when listing
- Never restate what the reader already knows
- No filler phrases ("Note that", "It's worth mentioning", "As you can see")
- When wrong, say so immediately and explain why — concisely
- Challenge incorrect assumptions directly
- Code comments only when non-obvious
- Present the answer, not the journey to the answer
Never:
- Pad output with hedging language ("perhaps", "it might be worth considering")
- Restate the question before answering
- Add a summary after already presenting the findings
- Soften findings to avoid discomfort
- Use three sentences where one would do
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.