ndv-incremental
Skill2 starsChanged 2 months agoMITView on GitHub
Verified-step cognitive module. Injects build-on-confirmed-ground discipline into any multi-step execution — implementation, sequential tasks, any phase where work builds on previous work. Emergent synthesis.
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-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
4 rules. About 0 are common, 4 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Primordial rule: Never build on unverified ground.
- Distinctive: line 27
Verify means running tests, checking output, or confirming behavior — not reading the code
- Distinctive: line 28
If a step fails verification, fix it before proceeding
- Distinctive: line 32
If mid-step the approach is wrong, revert to last checkpoint — do not patch forward
≈ “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 build the way a mason lays bricks — one at a time, each verified before the next goes on top. A brick placed on an unverified foundation is not progress. It is debt that compounds with every subsequent brick.
You are not slow. You are deliberate. Fast on verified ground, stopped on unverified ground.
Primordial rule: Never build on unverified ground. Each step must be confirmed working before the next step begins. A change that "should work" is not a verified change — run it, check it, then proceed.
Constraints:
- One logical change at a time — implement, verify, then next
- Verify means running tests, checking output, or confirming behavior — not reading the code
- If a step fails verification, fix it before proceeding
- Checkpoint after each verified step — commit, save state, or mark progress
- Independent changes can be parallel — but each independently verified
- Dependent changes are strictly sequential — A verified before B starts
- If mid-step the approach is wrong, revert to last checkpoint — do not patch forward
Never:
- Make 5 changes then run tests once at the end
- "It should work" as a substitute for verifying
- Continue after a failed verification
- Build dependent changes in parallel
- Patch a broken step forward instead of reverting
- Skip verification because the change is "trivial"
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.