Run any Skill in Manus with one click

rumil-dispatch

Stars2

Forks1

UpdatedApril 15, 2026 at 06:00

Fire one rumil call (find_considerations, assess, scout-*, web_research, create_view) as Claude Code. This is the "rumil-mediated" lane — a normal rumil call with its usual context-building, prompts, and tools. Use when the user wants to investigate a question deeper, assess a judgement, run a specific scout, or produce a distilled view summary. The run is tagged with origin=claude-code in the trace.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

chaosGuppy

chaosGuppy/rumil

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	rumil-dispatch
description	Fire one rumil call (find_considerations, assess, scout-*, web_research, create_view) as Claude Code. This is the "rumil-mediated" lane — a normal rumil call with its usual context-building, prompts, and tools. Use when the user wants to investigate a question deeper, assess a judgement, run a specific scout, or produce a distilled view summary. The run is tagged with origin=claude-code in the trace.
allowed-tools	Bash
argument-hint	<call_type> <question_id> [--budget N] [--smoke-test]

rumil-dispatch

Fires one rumil call and streams terse progress into the conversation. This is the rumil-mediated lane: the call is a standard rumil call with its own context-building and prompts — Claude Code is just the trigger. Distinguishable from a main.py-initiated run via the origin=claude-code tag in runs.config and calls.call_params.

Defaults

Budget: --budget 3 by default. Match this to the work you're asking for — single assess/scout calls don't need more. If the user wants a full multi-call investigation, suggest they use main.py --continue instead, which the orchestrator can spread budget across.
Workspace: reads active workspace from .claude/state/rumil-session.json. Override with --workspace <name> if needed.
Visibility: the script prints the trace URL immediately. Surface it to the user in your response so they can open it in a browser alongside the CC session.

Call type picking

If the user asked for a specific type, use it. Otherwise:

"investigate X more" / "find considerations" → find-considerations
"assess X" / "judge X" / "how credible" → assess
"brainstorm subquestions" → scout-subquestions
"look for evidence on the web" → web-research
"summarize what we know" / "distill a view on X" → create-view (produces or updates a curated View summary page for a question; appropriate once a question has enough research to warrant a distilled summary)

When in doubt, ask the user before firing. Dispatching is not free.

Invocation

setopt no_glob 2>/dev/null; set -f; PYTHONPATH=.claude/lib uv run python -m rumil_skills.dispatch_call $ARGUMENTS

After it runs

The script prints:

trace URL (surface this)
→ firing <call_type> (budget N) — confirmation line
✓ done: status=... cost=$... budget=used/total — completion line
the call's result_summary if non-empty

If the call failed or the result looks off, suggest using /rumil-trace <call_id> to inspect what happened. The short call ID is in the trace URL.

More from this repository

same repository

rumil-versus-iterate

chaosGuppy/rumil

Iterate on versus's pipeline — review recent (or freshly-fired) completion / judging runs, identify concrete improvement opportunities, test them via /rumil-forks, and consolidate findings into a ranked punch list. Spawns parallel agents for trace investigation and fork experiments so wall-clock stays low. Use when the user wants to "review the recent versus runs and find improvements," "play with these traces," "see what we could do better in d&e / two_phase," or anytime after a versus generation/judging batch when it's worth turning the runs into actionable code/prompt changes. Default scope is one forethought essay × Sonnet × budget 4, but every input is overridable.

2026-05-042

rumil-system

chaosGuppy/rumil

Background knowledge for working with the rumil research workspace from Claude Code. Explains the two-lane provenance model (rumil-mediated vs cc-mediated), when to use which rumil-* skill, how workspace/session state works, and the visibility/attribution story. Auto-load this whenever the user asks about rumil, wants to inspect research, dispatch a call, discuss a question, apply moves, or review a trace.

2026-05-022

rumil-versus-complete

chaosGuppy/rumil

Run orchestrator-driven essay completions for the versus pairwise-eval pipeline. Per essay × prefix × model × workflow, fires a rumil orchestrator (TwoPhase, DraftAndEdit) and writes the resulting continuation as a `versus_texts` row tagged `kind="completion"`, `source_id="orch:<workflow>:<model>:c<hash8>"` — pickable as a contestant by `rumil-versus-judge` afterwards. Use when the user wants to A/B orchestrator-produced continuations against single-shot model continuations or against the human baseline. Both `--orch two_phase` and `--orch draft_and_edit` are usable. For single-shot completions (no orch), use `rumil-versus-generate`.

2026-05-022

rumil-versus-judge

chaosGuppy/rumil

Run pairwise judgments on versus essay-continuation pairs. Default mode is the unified blind path (single-turn LLM call, no tools, no DB) — claude-* models route direct to Anthropic, others through OpenRouter. --variant orch fires a full TwoPhaseOrchestrator run per pair. Use when the user wants to measure how rumil discriminates on pairs with known ground truth (human continuation vs. model continuations), compare blind judges against workspace-aware ones, or top up pending judgments after adding new dimensions or models.

2026-05-022

rumil-load-run

chaosGuppy/rumil

Load a rumil run into the conversation by run ID. Shows a tree of every call in the run (id, type, status, cost, event summary) grouped under the run. Use when you have a trace URL like /traces/<run_id> and want to see the whole run, not a single call. For one call's verbatim trace use rumil-trace instead. Pass --compare <other_run_id> to A/B two runs side-by-side.

2026-05-022

rumil-trace

chaosGuppy/rumil

Dump a rumil call's full execution trace — trace events plus every LLM exchange verbatim (system prompt, user message, response, tool calls). Use to inspect what happened inside a specific call, debug model confusion, or review a run for quality. Takes a short (8-char) or full call ID.

2026-05-022

name	rumil-dispatch
description	Fire one rumil call (find_considerations, assess, scout-*, web_research, create_view) as Claude Code. This is the "rumil-mediated" lane — a normal rumil call with its usual context-building, prompts, and tools. Use when the user wants to investigate a question deeper, assess a judgement, run a specific scout, or produce a distilled view summary. The run is tagged with origin=claude-code in the trace.
allowed-tools	Bash
argument-hint	<call_type> <question_id> [--budget N] [--smoke-test]

rumil-dispatch

Defaults

Budget: --budget 3 by default. Match this to the work you're asking for — single assess/scout calls don't need more. If the user wants a full multi-call investigation, suggest they use main.py --continue instead, which the orchestrator can spread budget across.
Workspace: reads active workspace from .claude/state/rumil-session.json. Override with --workspace <name> if needed.
Visibility: the script prints the trace URL immediately. Surface it to the user in your response so they can open it in a browser alongside the CC session.

Call type picking

If the user asked for a specific type, use it. Otherwise:

"investigate X more" / "find considerations" → find-considerations
"assess X" / "judge X" / "how credible" → assess
"brainstorm subquestions" → scout-subquestions
"look for evidence on the web" → web-research
"summarize what we know" / "distill a view on X" → create-view (produces or updates a curated View summary page for a question; appropriate once a question has enough research to warrant a distilled summary)

When in doubt, ask the user before firing. Dispatching is not free.

Invocation

setopt no_glob 2>/dev/null; set -f; PYTHONPATH=.claude/lib uv run python -m rumil_skills.dispatch_call $ARGUMENTS

After it runs

The script prints:

trace URL (surface this)
→ firing <call_type> (budget N) — confirmation line
✓ done: status=... cost=$... budget=used/total — completion line
the call's result_summary if non-empty

If the call failed or the result looks off, suggest using /rumil-trace <call_id> to inspect what happened. The short call ID is in the trace URL.