Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Security
rotifer-gene
Try itThe Gene manual for Rotifer Protocol — write a Gene's express function and phenotype schema, run the four-layer security audit before publishing, and migrate a Gene's fidelity from Wrapped to Hybrid or Native. Invoke explicitly when building, auditing, or upgrading a Rotifer Gene. Do NOT use for general code review, dependency auditing, or framework migration — every procedure here operates on Rotifer Genes, their phenotype schemas, and the Rotifer CLI, and nothing else.
What it does
Three manuals, one per thing you might be doing. Read the one you need — they are long because they are references, not tutorials.
The skill document
Working on a Gene
Three manuals, one per thing you might be doing. Read the one you need — they are long because they are references, not tutorials.
| What you are doing | Read |
|---|---|
| Writing a Gene: init, express, phenotype, test, compile, publish, Arena | modules/dev.md |
| Checking one before it ships: credential and artifact scanning, four layers | modules/audit.md |
| Upgrading fidelity: Wrapped → Hybrid → Native, and proving it still works | modules/migration.md |
Which one
Match what the reader is asking for:
| They say | Go to |
|---|---|
| create, write, initialize, compile, publish, Arena, fitness | modules/dev.md |
| audit, scan, security, credential, is this safe to publish | modules/audit.md |
| upgrade, Wrapped to Native, rewrite, fidelity, refactor | modules/migration.md |
If it is ambiguous, say so and offer the choice rather than guessing — these are long documents and loading the wrong one costs the reader more than a question does.
What holds across all three
- Fidelity is declared honestly. Native means the logic is in WASM with no external calls; Hybrid means WASM plus calls to an allowlist; Wrapped means a shell around someone else's API. A Wrapped Gene labelled Native is a broken promise, not an optimization.
- F(g) is multiplicative. Any factor at zero eliminates the Gene, so a failure mode cannot be averaged away by strength elsewhere.
- Everything a reader sees is English — descriptions, schema fields, README, error messages.
- A published version is immutable. Bump, do not overwrite.
What this Skill does on your machine
Nothing on its own. It describes commands — rotifer init, test, compile,
publish, arena submit — and you run them. The ones that reach the network are
publish, arena submit --cloud and login; the rest are local. Read
modules/audit.md before your first publish: it is the difference between
finding a leaked credential on your disk and finding it in a public registry.
Related skills
Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Save, search, and manage personal notes and knowledge bases in Get笔记 on explicit request.
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Write, debug, and tune Playwright specs with locator strategy, trace diagnosis, and CI-aware timeouts.
More from xiaoba-dev
Browse all skillsRoute any Rotifer request to the right sub-capability — onboarding, scaffolding, diagnostics, search, or fidelity upgrade.
Build a Rotifer Agent from existing Genes through a 7-phase workflow of decomposition, composition, creation, and testing.
Compare two Rotifer Genes head-to-head and get a Markdown report with F(g) fitness and V(g) security grades.
Rank an Agent's Rotifer Genes against the Arena and swap in stronger ones. Invoked explicitly via /evolve — scan local capabilities, compare Genes, inspect fitness scores, and replace weak ones with user approval. Not for capabilities outside Rotifer.
Cross-vendor adversarial review. WARNING — this sends your brief, and any source files you approve, to a model hosted by a THIRD-PARTY vendor, where it stays in that vendor's session history under their retention terms. Ship a plan, proposal, or design to a model from a DIFFERENT vendor to attack it; every objection carries a verifiable anchor; the defender rules with an evidence tag on each ruling; the final round classifies into still-disputed / unresolved / verified-consensus instead of forcing agreement; a fresh-session judge is mandatory whenever the outcome looks too clean. Invoke only when the user explicitly asks for an adversarial review by a model from another vendor. One model role-playing several experts is not this skill.
Session knowledge distillation: assign what you just learned in this session into an agent's four-layer persistent knowledge base (rule / memory / skill / decision record). The core is four disciplines — search before adding, pick the right layer, guard against bloat, and run a hygiene pass before landing anything. Fits agent workflows that already have (or want to build) these four layers; this is not a general note- taking tool. Invoke explicitly at the end of a session to consolidate what was learned.