Work the verification ladder of a research run with rs_verify — read the ladder report before claiming anything is checked, run the two file rungs (r1-record, r2-locate) that need no reader, record the r3-support verdicts and strength verdicts that only a reader can make, tell a miss from an inconclusive, and know what a clean build will still refuse. Use when a document is written and about to be called checked, when a claim's quote does not match its source, or when a gate or build answers with an integrity refusal.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Five rungs, and each one can say exactly one thing. Knowing which rung said something is the whole skill; an agent that reports "checked" without naming the rung has told the user nothing.
| rung | what it can say | who runs it |
|---|---|---|
r0-structure | the document and its ledger agree | it runs by itself — the panel shows it and a build refuses on its errors |
r1-record | the stored bytes still hash to what was ingested; the record has the fields a reference needs; every field names its origin; the title it claims is in the text that was ingested | rs_verify action=record — a FILE check, no reader |
r2-locate | every claim's quoted passage really is in its source's stored text | rs_verify action=record — a FILE check, no reader |
r3-support | a located passage supports the sentence at the strength it is written | a READER — you — and this tool only records what you decided |
r4-audit | the same passages argued the other way | a READER, after an r3-support verdict exists |
action=support and action=audit will not judge anything for you, and they are
right not to: nothing in this package reads a paper and decides what it means.
action=report first, every time. It writes nothing, and it is the only place
that lists each rung's state, what it checked, what it found, and what it could
not check — those last lines begin ? could not check. A rung that could not
run is never a pass, and the report says so in those words: a source with no
stored text has not passed r1, it is uncheckable. Believing that line and acting
on it is worth more than every other rule here, because the quiet failure this
package exists to prevent is a run that looks fully checked because everything
that could not run was silently skipped.
rs_verify slug=sleep-memory-review action=report
The ladder for sleep-memory-review as it stands (3 source(s), 8 claim(s))
r1-record [findings]
checked: 1
· origin-missing: walker2020: `year` has no recorded origin, so a reader cannot
tell whether a service supplied it or a person typed it
? could not check diaz2019: no text is stored for this source, so its title
cannot be matched against it and a quote in it cannot be located
r2-locate [findings]
quotes located: 6
· locate-miss: claim c0142's quote is NOT in the stored text of walker2020 (the
extractor reported complete coverage), so either the quote is wrong or the
source does not say it
· claim-unsourced: claim c0151 rests on no source, so no quote of it can be located
? could not check c0148/orozco2021: the locator is a `page`, which is a pointer
a reader follows rather than a string this rung can search
r3-support [needs-a-reader]
waiting on a reader: 7
r4-audit [needs-a-reader]
waiting on a reader: 0
Statuses: 6 located, 2 unverified
This report changed nothing on disk.
A rung that could not run is listed as `could not check`, never as a pass.
Two answers a search can give when it does not find a quote, and they mean opposite things:
Reporting the second as the first is slandering a source. When a finding says the
extraction reported no coverage, the repair is to improve the text: read more of
the source (pdf_read, or ocr for a scan) and ingest what it returns as text=
with the coverage it reports. Do not touch the sentence.
text-missing is the same shape of problem at the source level: a source with no
stored text is uncheckable, so neither its title nor a quote in it can be
checked at all. The fix is to read it and ingest the text — never to re-word the
claim, which would hide an unread source behind a sentence that no longer needs
one. And a claim with no source at all (claim-unsourced) fails r2 by
construction: bind it to a key and a locator.
r3-supportThe judgement is per claim and per passage: does the passage you located support
the sentence as that sentence is written? Record four things — the verdict,
the strength verdict, the reason, and the passage you judged, quoted.
supported, partially-supported, unsupported, contradicted,
misattributed.aligned, overstated, understated — a passage can support
a sentence that still claims more than the passage holds.judge names who read it (this session, or a subagent and what it was asked).
A verdict with no reason is refused, and so is one with no judge: a score with
no evidence is the one thing this ledger must not hold.rs_write, then judge it. Judging a claim you have not located is judging a
sentence against nothing.rs_verify slug=sleep-memory-review action=support
judge="session model, after reading walker2020 pp. 6-8"
verdicts=[{ "id": "c0142", "verdict": "supported", "strengthVerdict": "aligned",
"reason": "the passage reports the association in the same direction, with the
same population and no causal verb",
"passage": "slow-wave sleep duration predicted next-day recall" }]
r3-support recorded for 1 claim(s) in sleep-memory-review
- judge: session model, after reading walker2020 pp. 6-8
c0142 -> supported
A verdict is recorded, not proven: the judge, the reason and the passage are all
in the ledger so a reader can disagree with a specific one.
r4-audit takes the same shape against the claims that already have an
r3-support verdict. Asking for it first is refused — an adversarial pass over a
claim nobody has read once is not an audit.
Say this to the user in one sentence before anyone publishes. The ladder never says a source is real (r1 is provenance — whose bytes, whose record, which field from where — and it never says a DOI resolves); it never says a claim is true (r2 and r3 only ask whether the stored words are there and whether they support the sentence as written); and it never proves that an experiment was run. A run whose ladder is entirely green can still be a document about work that never happened, and no rung here would notice.
A verdict belongs to a sentence, not to an id. Change a claim's words, its
strength or its source bindings and its status, rung, judge and reason are
cleared, along with the findings a file rung left on it — a finding about a
sentence that no longer exists is not a finding. rs_write names every claim it
cleared (RE-VERIFICATION NEEDED: …). Say it out loud in the same turn, by id:
quietly editing a checked sentence back to unchecked is the one way this system
could lie to a user. Re-running the file rungs afterwards does not restore the
judgement — r3-support is a new read of the new sentence.
draft=clean is the mode whose output looks finished, so it is the one that
refuses: on structure errors, on a claim a check found unsupported,
contradicted or misattributed, and until a person has answered gate
g3-integrity — which the build opens and only a human may answer in the Research
tab. Until then draft=watermark always builds and marks the document. Do not try
to reach a clean build by deleting a bad finding, by re-labelling a verdict, or by
answering the gate yourself; the first two put a false claim in the file and the
third is the thing the gate exists to stop.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Author an editorial HTML+SVG diagram with the Diagram Design kit - choose the visual type, read its reference, start from an example, and satisfy the safety and accessibility contract that diagram_write({kind:"html"}) enforces.
日本語の概要は準備中です。原文の説明を表示しています。
Drive ffmpeg through the media_run tool as an argv array - remux instead of re-encode, map streams explicitly, trim at keyframes, scale and crop, extract audio and frames, and build GIFs, contact sheets and concatenations. Covers the flags this pack injects, reading a failure from its exit code and last log lines, and the version-dependent spellings to hedge.
日本語の概要は準備中です。原文の説明を表示しています。
Read a media file's real structure with ffprobe through media_run - the JSON invocation and how to read it, what every family of field means, how to count frames, sample without decoding everything, detect HDR and interlacing, and diagnose a missing duration, a stream with no frames or a container that lies. Covers when media_probe's own report is already enough.
日本語の概要は準備中です。原文の説明を表示しています。
Author Mermaid diagrams that parse the first time: choose the right diagram type for the question, write syntax the parser accepts, and keep the picture readable in a narrow panel. A bundled reference covers complex, large diagrams.
日本語の概要は準備中です。原文の説明を表示しています。
Write openFrameworks prototypes into the lab — real C++ (ofApp.h, ofApp.cpp, main.cpp) that builds into an app with the projectGenerator and make. Use for native/desktop sketches, performance-sensitive work, OpenGL, audio input, sensors, anything that has to be an application rather than a page.
日本語の概要は準備中です。原文の説明を表示しています。
Write p5.js prototypes into the lab — sketches that actually run in a browser, seed-reproducible, with controls generated from the sketch's own parameters. Use for generative art, flow fields, particle systems, noise, animation, anything sketched visually in the browser.
日本語の概要は準備中です。原文の説明を表示しています。