GitHub collection
kalarislabs/skill-doctor
Imported from GitHub — is this yours?
15 skills imported from this repository.
neutralize-sd11
SD-11 scanner-mediated injection — neutralize untrusted skill bytes before any model; additive-only scoring. Use when touching L2, MCP, prompts, envelopes, or scoring merge.
project-context
Skill Doctor product and architecture context. Use at the start of a session, when deciding where code lives, when the user asks how the scanner works, or before any non-trivial change.
release-publish
Pre-publish and publish path for crates.io, npm installer, GitHub Releases, SBOM. Use when cutting versions, editing release.yml, or adding publish steps. Never publish from a feature branch.
review-bots
How to work with CodeRabbit, Greptile, and Intelligence AI on Skill Doctor PRs. Use when a review bot comments or when deciding if a bot finding blocks merge.
rust-idioms
Everyday Rust engineering for Skill Doctor — errors, ownership, clippy, APIs, iterators. Use when writing or reviewing Rust that is not specifically about perf, unsafe, or YARA.
rust-invariants
Nine non-negotiable Skill Doctor product invariants. Use when changing scan defaults, scoring, features, networking, LLM/MCP paths, CLI flags, or anything that could weaken determinism or additive-only behavior.
rust-testing
How to write Skill Doctor tests — unit, integration, CLI, fixtures, determinism, additive-only. Use when adding tests, fixtures, snapshots, or changing cargo test layout.
rust-workspace
Cargo workspace layout, crate boundaries, and dependency policy for Skill Doctor. Use when creating crates, editing Cargo.toml, adding modules, moving types, or adding a dependency.
unsafe-sandbox
Rules for unsafe Rust and the L3 microVM sandbox. Use when adding unsafe blocks, FFI, sandbox features, differential replay, or canary credentials.
yara-rules
Author and compile YARA-X rules for SDTM-v1. Use when adding or changing detectors, rules/*.yar, rule IDs, or taxonomy mappings.