Stats
Actions
Tags
From retriever
Handles /from-run slash commands to list processing runs, scope results to a specific run ID, or clear scoping in Retriever. Runs python tools.py and outputs tables or states directly.
How this skill is triggered — by the user, by Claude, or both
Slash command
/retriever:from-runThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> Operates under `retriever:routing`. If the user's intent actually fits a different tier — another `retriever:*` skill, a Tier 2 slash, a Tier 3 `tools.py` subcommand, or (last resort) direct DB access — stop and re-route against the ladder before continuing.
Operates under
retriever:routing. If the user's intent actually fits a different tier — anotherretriever:*skill, a Tier 2 slash, a Tier 3tools.pysubcommand, or (last resort) direct DB access — stop and re-route against the ladder before continuing.
Use this skill for /from-run, /from-run <run-id>, and /from-run clear.
For the exact read-only form /from-run:
/from-run: python3 skills/tool-template/tools.py slash . /from-runRETRIEVER_CANONICAL_TOOL_PATH pointed at ../tool-template/tools.py.For /from-run <run-id> and /from-run clear:
/from-run.npx claudepluginhub sdemyanov/retrieverHandles /scope slash commands to inspect, list, clear, save, and load active scopes in Retriever via python tools.py execution.
Browse, inspect details, compare side-by-side, and clean up past pipeline runs in working/runs/ directories via /runs commands like list, latest, {id}, clean, compare.
Generates the /process orchestrator command for a repo by writing .claude/commands/process.md that reads process-template.json and walks through configured workflow steps.