Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere. Use when starting an audit, threat model, or architecture review on unfamiliar code, and before any vulnerability-hunting pass.
Explain and verify Klai Compose deployment boundaries (automatic core-01 config sync, validation-only gpu-01 Compose CI, and manual SOPS secret delivery). Use when changing deploy/docker-compose.yml, Caddyfile, alloy/searxng/vexa configs, Grafana provisioning, or when a deploy did not land.
Validate vexaai/ image tags in deploy compose files before committing or deploying. Use when changing deploy/docker-compose.yml image references, bumping Vexa versions, or debugging a "manifest not pullable" CI failure.
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Enforce the envfile scoping rule across Klai deploy Compose files (SPEC-SEC-ENVFILE-SCOPE-001). Use when adding a service to Compose, wiring service env vars or secrets, or diagnosing an env-scope-guard CI failure.
Build, change, or review user interfaces in klai-portal/frontend. Use for React route pages, shared UI components, design-token changes, layouts, forms, tables, navigation, accessibility, responsive behavior, and visual consistency in the Klai portal.
Complete browser automation with Playwright. Auto-detects dev servers, writes reusable test scripts, and supports screenshots, responsive checks, UX validation, login flows, link checks, and arbitrary browser automation. Use when the user wants to test a website, automate browser interactions, validate web…
Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the…
Volledig autonome pipeline voor een goedgekeurde SPEC: run → interview-standard review (auto-fix) → migraties → sync → e2e → merge. Geen menselijke stops — alleen de SPEC annotation (plan fase) vereist goedkeuring. Gebruik --review voor handmatige gates.
Runs before the agent uses a tool for Bash, Write, Edit, MultiEdit, mcp__playwright__browser_navigate and mcp__playwright__browser_tabs tool calls, executing portal-api-preflight.sh, container-hygiene-preflight.sh, worktree-no-main.sh, git-no-stash.sh, public-github-mutation-guard.py…
Use only when the user explicitly asks to run CodeIndex CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Do not use this for normal code navigation, stale-index warnings, or missing MCP tools. Examples: "Index this repo", "Reanalyze the codebase", "Generate…
Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug".
Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How does X work?", "What calls this function?", "Show me the auth flow".
Use when the user asks about CodeIndex itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What CodeIndex tools are available?", "How do I use CodeIndex?".
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?".