adk-setuplisted

Set-up, configure-overrides, init-config, refresh-metadata, verify-mcps, check-env. Stewards `$ADK_CONFIG_HOME/core.yaml` and the metadata cache. NOT a CLI-dep installer — brew, gh, jq, uv, node are the user's job (SETUP.md prints the exact commands). NOT a wiring tool — install.sh handles symlinks, MCP merges, hook wiring, AGENTS.md pointers. This skill picks up where install.sh stops: filling user data files (conversationally) and introspecting MCPs (with the agent's MCP client, which install.sh / curl cannot do). Four modes. --init: conversational scaffolding of core.yaml (workspaces, repos, data dictionary, RAG config). --enrich: queries every reachable MCP (Datadog dashboards, Statsig experiments, Mixpanel events, Snowflake schemas, Looker dashboards, Atlassian spaces, GitHub repos), summarizes findings, writes `enriched:` block + `$ADK_DATA_HOME/improve/metadata/<source>.json`. Never overwrites manually-set values. --check: superset of `scripts/adk_mcp_health.py` — also probes stdio MCPs (Atlassian via
sujeet-pro/agents-devkit · ★ 0 · Data & Documents · score 76

Install: claude install-skill sujeet-pro/agents-devkit

# adk-setup Bootstrap + maintain `$ADK_CONFIG_HOME/core.yaml`. **Global skill** — runs from anywhere; intermediate artifacts go to `$ADK_DATA_HOME/setup/<ts>/` (per `shared/paths.md`). Touches `$ADK_CONFIG_HOME/` (config) but not the cwd. `--detailed` increases MCP/config diagnostics. `--deep` selects the stronger model profile per `shared/model-depth.md`; use it when reconciling ambiguous config, migrations from older installs, or many failing connectors. ## Modes ### --init Scaffolds `$ADK_CONFIG_HOME/core.yaml` with full structure + comments. Behavior: 1. If `$ADK_CONFIG_HOME/core.yaml` exists → refuse; show user `--diff` instead. 2. Else → write fresh templates for `core.yaml`, `repos.md`, `connectors/*.md`, and `links.json5`. 4. Walk the user through filling: workspaces (cap 3 questions), one starter repo, RAG config. Then: print "edit `$ADK_CONFIG_HOME/core.yaml` (defaults / workspaces / rag) and `$ADK_CONFIG_HOME/repos.md` (per-repo entries). Add new data sources by editing `$ADK_CONFIG_HOME/connectors/<name>.md`. Re-run `/adk-setup --enrich` to populate auto-discovery." ### --enrich For each MCP (or `--source <name>` for one), call `scripts/enrich_metadata.py`: 1. Query reachable MCPs via curl / programmatic calls. 2. Write `$ADK_DATA_HOME/improve/metadata/<source>.json` (overwrites; archives previous). 3. Propose updates to `$ADK_CONFIG_HOME/connectors/<name>.md` frontmatter — only ADD; never delete manually-set values. Per-update user confirmation require