with one click
quaid
quaid contains 33 collected skills from quaid-app, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
Resolve knowledge gaps: fetch unresolved gaps, assess sensitivity, generate research queries, ingest findings, and close gaps with a resolution slug.
Interrupt-driven alerts: detect and surface new contradictions, stale pages, resolved gaps, and embedding drift. Priority-classified with deduplication.
Ingest meeting notes, articles, documents, and conversations into Quaid. Handles idempotent ingestion for exact-byte duplicates and vault-backed sync.
Keep the brain healthy: detect and resolve contradictions via the correction / supersede workflow, validate referential integrity, triage knowledge gaps, find orphaned pages, and compact the database.
Answer questions from the brain using FTS5 + semantic search + structured queries. Synthesize across multiple pages. Cite sources.
Agent-guided binary upgrades: version check, channel detection, download via install.sh (or manual asset fetch + SHA-256 verify), and post-upgrade validation.
Bootstrap a fresh Quaid install in one guided flow: initialize the database, attach a vault collection, install the background serve daemon, and wire MCP clients (Claude Code, Cursor). Use when onboarding a new machine or a new agent that has never run Quaid before.
{what this skill teaches agents}
{what this skill teaches agents}
Sequence stateful features from storage contract to request path to watcher/mutation closure
Guard watcher-driven archive-on-edit features from chain forks and sidecar recursion
Prove optimistic concurrency races in Rust MCP handlers with a deterministic pre-write seam
Protect namespace-local identifiers when a shared queue schema only has one key column
How to test head-only supersede retrieval without lying to yourself
How to open a narrow, honest draft PR when the branch context is wider than the landed slice
How to truth-repair an OpenSpec change when its schema target collides with the live repo
Enrich brain pages with external data from Crustdata, Exa, and Partiful. Stores raw API responses, extracts structured facts, and handles conflicts.
Review pattern for local socket auth without trusting spoofable protocol identity
How to assess and recover from a working tree parked on a stale branch before starting a new implementation batch
Defensive CI/CD patterns: semver validation, token checks, retry logic, draft detection — earned from v0.8.22
How to safely plan and execute a breaking schema migration in a Rust SQLite codebase
How to ship diagnostics without breaking a frozen MCP/JSON contract
Preserve rename-before-commit invariants by routing bulk file rewrites through the production single-file writer
Update tests when changing APIs — no exceptions
Review frozen MCP diagnostic schemas by proving the real state predicate, precedence, and negative cases instead of only checking emitted labels.
Prove hybrid-search behavior without letting vector quality hide the real seam under test.
Generate a structured "what shifted" report from the brain: changed pages, new pages, unresolved contradictions, open knowledge gaps, and upcoming timeline entries. Configurable lookback window; default is 1 day.
Keep installer, workflow, docs, and reviewer checks bound to one release asset manifest.
Keep CLI collection-aware slug routing aligned with MCP by resolving once and canonicalizing page references at the output boundary.
Validate Unix shell installers and npm postinstall flows honestly from a Windows host.
Review external coding guidance before turning it into standing repo policy.
How to coordinate with squads on different machines using git as transport
How to run Sprint 0 for a new Rust project in this squad