compound-knowledge

Cloudflare-specific rules: Pages vs Workers selection, deployment methods, Git integration requirements.

shadcn/ui component patterns: composition over custom builds, semantic theming tokens, proper form architecture, accessibility, and CLI workflow.

/debug - structured root-cause debugging with Opus delegation. 7-phase workflow: gather context, reproduce, hypothesize, instrument, diagnose, fix, verify.

Rule and template for shipping machine-readable docs alongside human docs. Any project an agent will install, build, test, deploy, or debug should have an AGENTS.md with copy-pasteable command blocks — not prose, not dashboard instructions.

/editorial-critique - deep editorial review of long-form writing. 8 parallel analysis passes: prose craft, AI-tell detection, argument architecture, conciseness, data verification, structure, impact, grammar. Judges prose against a lean, Hemingway-style house standard over ornate maximalism. Scored report with optional auto-fix.

Two foundational context files that give Claude Code a persistent identity: soul.md (AI personality and philosophy) and human-context.md (who you are, your goals, and how you work).

/deepresearch - Multi-query semantic research using the Exa MCP server. Claude generates diverse queries from your topic, fans them out via parallel Exa MCP tool calls, and synthesizes a structured research.md from full page contents. Requires the Exa MCP server registered via `claude mcp add` and an Exa API key.

/docupdate - comprehensive documentation audit and update. Checks README, TOC, onboarding flows, package lists, and module coverage against actual codebase state.

Nightly, cost-capped dreaming service that mines Claude Code session transcripts for cross-session failure patterns and optimistically auto-integrates evidence-tagged memory-store changes (write-then-review, made safe by per-op-kind postures, a 24h dwell window, per-run blast caps, batch-anomaly detection, a windowed circuit breaker, an eval gate, a daily report, and git-backed rollback). Extends self-improving's learnings store with an out-of-band analyzer -- autoheal's capture-analyze-propose pipeline, retargeted at session transcripts instead of permission events. Provides the deterministic transcript miner (discover/mine/cluster/budget plus a schema-drift canary), the map-reduce analyzer (evidence bundle -> per-change proposals -> digest, with cost caps), the optimistic integration engine (per-op-kind postures, 24h dwell window, blast caps, batch-anomaly detection, windowed self-healing circuit breaker, plus an opt-in composite eligibility gate -- default off, add/supersede only -- scoring each mined add/supersede on four transcript-verified signals through a deterministic no-LLM waterfall before admission) with the /dream, /dream-digest, /dream-review, /dream-apply commands (/dream-review vetoes/reverts post-hoc; /dream-apply is the back-compat human-gated path) plus the nightly LaunchAgent scheduler, and the memory eval harness (with/without-memory A/B plus a saturation third arm, a four-bucket outcome classifier, and an end-to-end task exercising the analyzer's own mined output -- establishing the --gate contract the optimistic engine consumes), and a read-only reconciliation report comparing Claude Code's own harness auto-memory against the learnings store (import candidates + contradictions, appended to the daily digest -- never writes to auto-memory).

Rules for browser automation tool selection: Chrome extension, Playwright, and WebMCP. Includes verification priority order and UI verification workflow.