plugins/src/wiki/skills/lisa-wiki-add-ingest/SKILL.md
Scaffold a project-specific "front-door" ingest skill that does something unique (classify a source, fetch from a special system, stamp domain frontmatter) and then chains into /ingest. Use when a project needs a bespoke ingestion path that the core connectors do not cover — instead of forking the kernel. The generated skill enriches and delegates; the kernel still owns synthesis, index, log, verify, state, and PR.
npx skillsauth add codyswanngt/lisa lisa-wiki-add-ingestInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate a thin, project-local front-door ingest skill so a project can extend ingestion without
forking the kernel. The front-door does only the unique part, then hands enriched parameters to
/ingest.
wiki/sources/<sourceSystem>/
bucket and page type/frontmatter it should produce; whether it merely enriches/classifies an
input or also fetches from an external system; and its side-effect class
(read-only-ingest | repo-write | external-write)..claude/skills/lisa-wiki-local-<name>/SKILL.md and .agents/skills/lisa-wiki-local-<name>/SKILL.md.
Its body does the unique step, then delegates to the lisa-wiki-ingest skill (Claude facade
/ingest) passing the bucket/type/metadata. If it fetches, it writes only a sanitized source note
(+ run metadata) and lets the kernel do synthesis/index/log/verify/state/PR.wiki/lisa-wiki.config.json under customConnectors
({ name, skill, sourceSystem, stateFile, sideEffects }). /ingest dispatches only to
registered names — no auto-discovery.index.md, log.md, or final state — the kernel does those, in order, after it returns.external-write front-doors require config opt-in and explicit per-run intent, and their PRs
never auto-merge.lisa-wiki-ingest (what it chains into), lisa-wiki-add-role, lisa-wiki-doctor.
tools
--- name: harper-realtime description: This skill should be used when adding or troubleshooting Harper (HarperDB/Fabric) real-time behavior: MQTT topics, WebSocket resource subscriptions, resource publish/subscribe handlers, SSE-style streaming routes, and local subscriber verification. Pairs with harper-resources, harper-config-yaml, harper-schema-graphql, and harper-build-and-deploy. --- # Harper Realtime ## Overview Harper exposes live data through the same Resource model used for REST and
tools
--- name: harper-realtime description: This skill should be used when adding or troubleshooting Harper (HarperDB/Fabric) real-time behavior: MQTT topics, WebSocket resource subscriptions, resource publish/subscribe handlers, SSE-style streaming routes, and local subscriber verification. Pairs with harper-resources, harper-config-yaml, harper-schema-graphql, and harper-build-and-deploy. --- # Harper Realtime ## Overview Harper exposes live data through the same Resource model used for REST and
tools
--- name: harper-realtime description: This skill should be used when adding or troubleshooting Harper (HarperDB/Fabric) real-time behavior: MQTT topics, WebSocket resource subscriptions, resource publish/subscribe handlers, SSE-style streaming routes, and local subscriber verification. Pairs with harper-resources, harper-config-yaml, harper-schema-graphql, and harper-build-and-deploy. --- # Harper Realtime ## Overview Harper exposes live data through the same Resource model used for REST and
tools
--- name: harper-realtime description: This skill should be used when adding or troubleshooting Harper (HarperDB/Fabric) real-time behavior: MQTT topics, WebSocket resource subscriptions, resource publish/subscribe handlers, SSE-style streaming routes, and local subscriber verification. Pairs with harper-resources, harper-config-yaml, harper-schema-graphql, and harper-build-and-deploy. --- # Harper Realtime ## Overview Harper exposes live data through the same Resource model used for REST and