plugins/lisa-wiki-cursor/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.
development
Prepare a machine — a fresh laptop or a throwaway container — to run coding agents, before any repository exists. Detects which of Lisa's supported agents (Claude Code, Codex, Cursor, OpenCode, Antigravity, Copilot) are already installed, asks which credential manager the machine uses (Bitwarden, 1Password, Doppler, Vault, AWS, or none), and installs only what is missing, each by its vendor's own preferred method. Idempotent, headless by default, and emits a Dockerfile for a spin-up/spin-down environment. Run it on a new machine, in a container, or before cloning anything.
tools
Provision and verify a remote execution environment for a host project — Codex Cloud today, other remote surfaces as they are added. Generates a repository-owned setup script that installs the declared toolchain, materializes secrets through lisa-secrets-access, and runs the project's own hook. Provisions by API where one exists, by driving the vendor console where one does not, and by emitting exact config otherwise — then proves the result with the same read-back regardless of which tier did the work. Use before dispatching any work with executionEnv.
tools
Bring a developer's machine in line with the toolchain the project declares. Reports every tool in remoteEnv.tools that is missing, outdated, or unpinned for this platform, and installs the missing ones into ~/.local/bin from the same pinned, checksummed entries the remote surfaces use — but only when asked. Same manifest, same pins, same installers as lisa-setup-remote-env; what differs is consent and that the pin is a floor rather than an equality. Run it on a fresh checkout, after a manifest change, or when a tool fails at the moment of use.
tools
Route one unit of work to a remote execution surface. Reads the executionEnv parameter (local by default, codex-cloud or claude-web today), verifies the environment is provisioned and bound to this repository, submits a thin skill invocation, records the task identifier to .lisa/remote-dispatch.json, and exits without polling. Routing only — the remote runs the identical skill from the identical repository. Composable and inline: other skills invoke it via the Skill tool rather than users calling it directly.