Run any Skill in Manus with one click

rumil-read

Stars2

Forks1

UpdatedApril 15, 2026 at 05:51

Fetch a file or URL into the conversation — the view-only lane for sources. Default mode is pure fetch-and-print with no DB and no LLM, using the same scraping/extraction pipeline that rumil-ingest would use so you can preview exactly what the ingest step would see. Flags layer more behavior — --summary for an LLM headline, --save to persist as a Source page in the workspace. Use whenever the user shares a URL, PDF, or file they want Claude to look at, especially when it's not yet clear whether the source should become a workspace artifact.

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

File ClerksOffice and Administrative Support Occupations·SOC 43-4071

SKILL.md

readonly

name	rumil-read
description	Fetch a file or URL into the conversation — the view-only lane for sources. Default mode is pure fetch-and-print with no DB and no LLM, using the same scraping/extraction pipeline that rumil-ingest would use so you can preview exactly what the ingest step would see. Flags layer more behavior — --summary for an LLM headline, --save to persist as a Source page in the workspace. Use whenever the user shares a URL, PDF, or file they want Claude to look at, especially when it's not yet clear whether the source should become a workspace artifact.
allowed-tools	Bash
argument-hint	<file_or_url> [--save] [--summary] [--full] [--workspace name]

rumil-read

Load a source — file, URL, or PDF — into the conversation. This is the view-only lane: the default mode opens no DB connection, makes no LLM call, and does not mutate the workspace. It's for "let me look at this."

Uses rumil's own scraper and file readers (rumil.scraper.scrape_url, rumil.sources.read_file_content), so what you see here is byte-identical to what rumil-ingest would feed the extraction step. Preview here, commit there.

Modes

default — fetch content, print it. No DB, no LLM.
--summary — also generate the 2-3 sentence LLM headline that a persisted Source page would get. Uses the LLM but still no DB.
--save — persist as a PageType.SOURCE page in the active workspace. Summarizes automatically (headline comes from the summary). This is the only mode that writes to the workspace. Still free of extraction calls — no considerations are produced.

--save implies a summary (create_source_page always generates one), so --summary --save is just --save.

When to use which

Intent	Command
"let me see what's in this PDF"	`rumil-read paper.pdf`
"show me this URL and preview the summary"	`rumil-read https://... --summary`
"save this to the workspace but don't run extraction yet"	`rumil-read paper.pdf --save`
"commit this and extract considerations against question X"	`rumil-ingest paper.pdf --for X`

If the user wants extraction calls fired, reach for rumil-ingest, not this. rumil-read --save is the "stash for later" path — no budget spent.

Content truncation

Default display truncates at 50,000 chars to keep the conversation surface manageable. Pass --full to dump the entire fetched content (up to INGEST_MAX_CHARS = 500,000). URLs are always fetched at the full 500k; files are read in full. When --save is used, the full content is persisted regardless of display truncation.

Workspace

All modes resolve the session workspace from .claude/state/rumil-session.json and print it in the header, overridable with --workspace name. Default and --summary modes don't touch the DB, so the workspace is label-only there (it becomes load-bearing once --save writes a Source page).

Invocation

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

After it runs

Default / --summary: source metadata (filename or URL + char count), optional summary line, then the content (truncated at 50k unless --full).
--save: the above plus ✓ saved source <short_id> and the headline. Surface the short ID in your reply — the user may want to reference it later (e.g. rumil-ingest <id> --for <q>).

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-read
description	Fetch a file or URL into the conversation — the view-only lane for sources. Default mode is pure fetch-and-print with no DB and no LLM, using the same scraping/extraction pipeline that rumil-ingest would use so you can preview exactly what the ingest step would see. Flags layer more behavior — --summary for an LLM headline, --save to persist as a Source page in the workspace. Use whenever the user shares a URL, PDF, or file they want Claude to look at, especially when it's not yet clear whether the source should become a workspace artifact.
allowed-tools	Bash
argument-hint	<file_or_url> [--save] [--summary] [--full] [--workspace name]

rumil-read

Modes

default — fetch content, print it. No DB, no LLM.
--summary — also generate the 2-3 sentence LLM headline that a persisted Source page would get. Uses the LLM but still no DB.
--save — persist as a PageType.SOURCE page in the active workspace. Summarizes automatically (headline comes from the summary). This is the only mode that writes to the workspace. Still free of extraction calls — no considerations are produced.

--save implies a summary (create_source_page always generates one), so --summary --save is just --save.

When to use which

Intent	Command
"let me see what's in this PDF"	`rumil-read paper.pdf`
"show me this URL and preview the summary"	`rumil-read https://... --summary`
"save this to the workspace but don't run extraction yet"	`rumil-read paper.pdf --save`
"commit this and extract considerations against question X"	`rumil-ingest paper.pdf --for X`

If the user wants extraction calls fired, reach for rumil-ingest, not this. rumil-read --save is the "stash for later" path — no budget spent.

Content truncation

Workspace

Invocation

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

After it runs

Default / --summary: source metadata (filename or URL + char count), optional summary line, then the content (truncated at 50k unless --full).
--save: the above plus ✓ saved source <short_id> and the headline. Surface the short ID in your reply — the user may want to reference it later (e.g. rumil-ingest <id> --for <q>).