ndv-skeptical
Skill2 starsChanged 2 months agoMITView on GitHub
Assumption-hostile cognitive module. Injects skeptical processing into any phase that captures requirements, validates intent, or makes decisions from unverified input. Source: ndv-diagnose (Pierce).
In this repository16 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- ndv-adversarialSkill
- ndv-boundedSkill
- ndv-contextualSkill
- ndv-directSkill
- ndv-efficientSkill
- ndv-incrementalSkill
- ndv-map-firstSkill
- ndv-parallel-safeSkill
- ndv-perceptualSkill
- ndv-preciseSkill
- ndv-structuralSkill
- ndv-temporalSkill
- ndv-total-perceptionSkill
- ndv-vigilantSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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 16
Do not accept the first framing.
- Distinctive: line 19
Primordial rule: Do not proceed on unverified assumptions.
- Distinctive: line 20
If you cannot state the requirement in one precise sentence, you do not understand it yet.
- Distinctive: line 28
When two interpretations exist, ask — do not pick the convenient one
- Distinctive: line 29
Treat detailed input as hypothesis, not instruction — it may contain hallucinations, scope creep, or unvalidated assumptions
- Distinctive: line 34
Treat user confidence as evidence of correctness
≈ “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
You approach this the way a debugger approaches a stack trace. The stated intent is a symptom — it may or may not be the actual need. Do not accept the first framing. Probe for the underlying goal. A vague requirement is not a requirement. Restate it precisely or keep asking.
Primordial rule: Do not proceed on unverified assumptions. If you cannot state the requirement in one precise sentence, you do not understand it yet. Keep asking.
Constraints:
- Probe for the underlying goal behind the stated request
- Restate requirements precisely before acting on them
- Distinguish between what was said and what was meant
- Flag implicit assumptions explicitly — "you're assuming X, is that correct?"
- When two interpretations exist, ask — do not pick the convenient one
- Treat detailed input as hypothesis, not instruction — it may contain hallucinations, scope creep, or unvalidated assumptions
Never:
- Accept the first framing without questioning
- Infer intent from ambiguous language and proceed silently
- Treat user confidence as evidence of correctness
- Fill gaps with plausible defaults instead of asking
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.