nve-genome-explorer
Skill2 starsChanged 4 months agoMITView on GitHub
Antigravity-native equivalent of VS Code NVE Extension — provides genome dashboard, skill audit, replay gate status, and quick actions directly in the agent context
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- Academic Paper SummarizationSkill
- Accessibility WCAG AuditSkill
- API Error TroubleshootingSkill
- CI/CD Pipeline TroubleshootingSkill
- Competitor Analysis SynthesisSkill
- Customer Onboarding AssistanceSkill
- Dependency Audit ResolutionSkill
- Docker Image OptimizationSkill
- GDPR Data MappingSkill
- genome-analyzerSkill
- incident-distillerSkill
- Kubernetes Pod DebuggingSkill
- OWASP Input ValidationSkill
- repo-auditorSkill
- research-packagerSkill
- rule-patcherSkill
- Secret Leak RemediationSkill
- skill-curatorSkill
- skill-package-builderSkill
- SOC2 Policy VerificationSkill
- tama-community-summarizerSkill
- Technology Stack EvaluationSkill
- Ticket Triage and RoutingSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 58
Read .evolution/genomes/*.json files, look at replay.status field:
- Very specific: line 102
Read .evolution/MEMORY.md — the compact knowledge base (~35 lines)
- Very specific: line 103
Run node cli/nve-audit.js — check system health
- Very specific: line 104
Check docs/backlog_tama.md — see current priorities
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
🧬 NVE Genome Explorer (Antigravity Edition)
Full equivalent of the VS Code NVE Extension, but for Google Antigravity agent. Instead of a sidebar UI with panels, the agent uses these skills and workflows at the start of each session.
When to Use
Always. This skill should be loaded at session start (via 00-session-bootstrap workflow) and used throughout the session whenever:
- You encounter an error that might have been seen before
- You complete a fix and need to record a genome
- You want to check the health of the evolution system
- You need to search for relevant skills/genomes
Panel Equivalents
The VS Code Extension has 6 panels. Here is how each is replicated in Antigravity:
Panel 1: 📊 Audit Dashboard
What it does: Shows a 5-axis audit score + SkillGraph extension score.
How to invoke:
node cli/nve-audit.jsWhat to report to user:
- Structure Score (0-100%)
- Coverage Score (0-100%)
- Quality Score (0-100%)
- Freshness Score (0-100%)
- SkillGraph Score (0-100%)
- Overall Grade (A/B/C/D/F)
Panel 2: 🧬 Genome Families
What it does: Lists all Failure Genomes grouped by family.
How to invoke:
node cli/nve-fg-summary.jsWhat to report:
- Family name, member count, avg utility
- For each genome: ID, violated invariant, replay status, utility score
Panel 3: 🔄 Replay Gate
What it does: Shows promoted/rejected/pending status for each genome.
How to check:
Read .evolution/genomes/*.json files, look at replay.status field:
- ✅
passed— genome is verified - ❌
rejected— fix didn't work on similar cases - ⏳
pending— not yet tested
Panel 4: 🧩 Skill Registry
What it does: Lists all skills with their admission status.
How to invoke:
node cli/nve-skill-search.js ""This returns all indexed skills with scores.
Panel 5: 📦 Skill Packages
What it does: Shows assembled packages ready for sharing.
How to check:
ls .evolution/skills/packages/Panel 6: ⚡ Quick Actions
These are the 9 one-click actions. In Antigravity, invoke them via CLI:
| Action | Command |
| 📝 New Incident | node cli/nve-scaffold.js incident --slug <description> |
| 🧪 Distill to Genomes | node cli/nve-distill.js |
| 🔄 Run Replay Gate | node cli/nve-replay.js |
| 🧩 Extract Skills | node cli/nve-skill-extract.js |
| 📊 Run Audit | node cli/nve-audit.js |
| 📦 Build Package | node cli/nve-skill-package.js --auto |
| 🔎 Search Skills | node cli/nve-skill-search.js "<query>" |
| 📤 Export Dashboard | node cli/nve-export-dashboard.js |
| 📋 Regenerate MEMORY | node cli/nve-memory.js |
Session Start Checklist
At the beginning of each session, the agent MUST:
- Read
.evolution/MEMORY.md— the compact knowledge base (~35 lines) - Run
node cli/nve-audit.js— check system health - Check
docs/backlog_tama.md— see current priorities - Report: "🧬 Memory loaded. Level X, Y genomes, Z skills. Audit: grade."
After Fixing a Bug
node cli/nve-scaffold.js incident --slug <description> --severity <1-10>- Fill the TODO fields in the generated JSON
node cli/nve-distill.js— extract EUs and genomesnode cli/nve-memory.js— regenerate MEMORY.md- Report: "🧬 Genome captured: FG-NNNNNN (family: X, utility: Y)"
After Completing a Feature
node cli/nve-audit.js— verify nothing degradednode cli/nve-export-dashboard.js— update dashboard data- Commit changes
Anti-Patterns
- Never skip MEMORY.md — every session must start by reading it
- Never silently fix bugs — always capture the incident first
- Never promote without replay — run Replay Gate before marking as promoted
- Never ignore utility decay — run
nve-utility.jsperiodically
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.

