Menu
Convert a new source into deterministic manifest, extracted text/chunks, normalized event, contextual LLM plan, and PR-ready ingestion proposal without writing canonical memory directly.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Single entry skill to set up AND operate a Markdown/Git living operational wiki (the "wiki viva kit") — configure wiki.config.yaml, scaffold or adopt the tree, ingest sources through the deterministic pipeline, run the delegated LLM deep read, keep the honesty gates green, compile the daily cockpit, and ship changes through the PR gate. Install this one skill to adopt and run the whole system; it points to the deeper per-step playbooks when you need them.
Generic router for Markdown/Git living-wiki repos that use memories/, docs/references/, wiki.config.yaml, wiki_core, PR gates, source manifests, normalized ingestion events, and operation cockpit pages.
Run the deep contextual reading (LLM pass) over the chunks selected by wiki_core, write the result to the cache, and then consolidate and INTEGRATE what was read into the target wiki pages (ingesting = integrating). The intelligence lives in the agent that runs the repo (Claude/Codex/Gemini), not in a Python LLM client.
Compile or review the living-wiki operation cockpit with current Git state, pending decisions, agent actions, source queues, stale contexts and validation links.
Audit source traceability, manifests, extracted text, chunks, indexes, LLM cache metadata, Markdown links and access-secret exclusions in a portable wiki repo.
Separate private operational memory from public derivatives, allowing useful private context in private repos while blocking secrets and unsafe publication.
| name | wiki-ingestion-agent |
| description | Convert a new source into deterministic manifest, extracted text/chunks, normalized event, contextual LLM plan, and PR-ready ingestion proposal without writing canonical memory directly. |
--emit-request, deep read by the agent, --record-result).--source <source_id> --emit-event --packet generates the normalized event
in memories/system/ingestion/events/
from the recorded deep read (quadrants filled, claims/decisions/actions
candidates, consolidated_into: [] to close) plus the gitignored integration
packet; docs/references/templates/wiki/ingestion-event.md
stays as the manual fallback.supersedes/
superseded_by/conflicts_with/conflict_resolution when claims collide);
resolve or record every conflict and ambiguity; fill the event's
consolidated_into (each target page references the source in
source_refs); every new action/claim/decision/meeting/person/project/source
page declares the hub it belongs under in moc_parent; keep its
quadrant placement relative to the page's active center (subject_ref,
subject_role, parent_projection for nested roots/templates, and
projection_overrides for exceptions) instead of flattening everything
against the wiki root; run
scripts/wiki_consolidate.py --check,
scripts/wiki_audit.py --check and
scripts/wiki_quality_report.py
--check green.consolidated_into closed.