Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Paragraph Curator

skill · WILLOSCAR/research-units-pipeline-skillsLicence not declaredAudited 14 Oct 2026 · source 81994516a430

★ 514pushed 9 days ago
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 8199451
514repo stars · whole WILLOSCAR/research-units-pipeline-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 81994516a430 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Deterministically compact final H3 bodies to the active delivery profile's paragraph budget without deleting prose or changing citation-block order.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Paragraph Curator (WILLOSCAR/research-units-pipeline-skills)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/willoscar/paragraph-curator

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high1 medium1 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityWARN2
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass, no license.

Findings (2)

LOWInventory / provenanceinv.no_license
F-13 Inventory / provenanceCWE-1104Layer L0
Why
no LICENSE file and no repo licence
Fix
add a licence

Audit 0.4.1 · source sha 81994516a430 · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • PublisherWILLOSCAR GitHub userOwner of the repository this skill is read from
  • Source folderWILLOSCAR/research-units-pipeline-skills/.codex/skills/paragraph-curatorThe exact folder we audited
  • LicenceNot declaredAs the repository states it
  • Commit pinned for this verdict81994516a430A new audit runs when the source changes
  • Repository statusNot archivedLast push 9 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Deterministically compact final H3 bodies to the active delivery profile's paragraph budget without deleting prose or changing citation-block order.

---
name: paragraph-curator
description: "Deterministically compact final H3 bodies to the active delivery profile's paragraph budget without deleting prose or changing citation-block order."
---

# Paragraph Curator

## Triggers & routing

- **Trigger**: paragraph compaction, paragraph budget, compact H3, 段落压缩, 段落预算.
- **Use when**: H3 section files have passed logic polish and must converge before the final argument snapshot and merge.


Compact paragraph boundaries without performing a new semantic rewrite.

This is a deterministic convergence step. It prevents a long drafting loop from
leaving sections outside the delivery profile, while keeping the original prose
and evidence recoverable. It does not rank paragraphs, generate alternatives,
replace evidence, or decide which claims are important.

## Inputs

- `sections/S<subsection-id>.md`
- `queries.md` for `draft_profile`
- upstream logic and writer reports for operator context

Only H3 files are modified. Front matter (`S1.md`, `S2.md`), H2 lead files, and
global sections are not touched.

## Profile Contract

| Profile | Paragraphs per H3 |
|---|---:|
| `course_paper` | 5-7 |
| `survey` | 10-12 |
| `deep` | 11-13 |

The script first joins short adjacent body paragraphs while respecting the
profile floor. If a section remains over budget, it repeatedly joins the
shortest eligible adjacent pair. It never truncates a paragraph or drops a
middle block.

## Outputs

- updated H3 files under `sections/`
- `output/PARAGRAPH_CURATION_REPORT.md`
- `sections/paragraphs_curated.refined.ok` on PASS

The report records the active profile and before/after paragraph counts for
each H3. PASS requires every H3 to be within budget and the sequence of
citation blocks to be unchanged. On FAIL, the marker is removed.

## Boundaries

- If an H3 is below the floor, route to `subsection-writer` or the relevant
  evidence unit. Compaction must not invent padding.
- If prose is repetitive or logically weak, route to `writer-selfloop` or
  `section-logic-polisher`. This Skill changes paragraph boundaries, not ideas.
- Run `argument-selfloop` after this Skill so the argument ledger and section
  manifest describe the final section content.

## Run

```bash
uv run python .codex/skills/paragraph-curator/scripts/run.py \
  --workspace workspaces/<name>
```

Optional runner fields are `--unit-id`, `--inputs`, `--outputs`, and
`--checkpoint`.

Excerpt, first 2,410 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 8199451

Download folder ↗
uv run python .codex/skills/paragraph-curator/scripts/run.py \

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 81994516a430 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
CodexMentioned in its text, not testedSkills for Codex · About Codex
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 81994516a430

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/willoscar/paragraph-curator/badge.svg)](https://modelsatlas.com/skills/willoscar/paragraph-curator/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/willoscar/paragraph-curator/badge.svg)](https://modelsatlas.com/skills/willoscar/paragraph-curator/)

Questions about Paragraph Curator

What does the Paragraph Curator skill do?
Research pipelines as semantic execution units: each skill declares inputs/outputs, acceptance criteria, and guardrails. Evidence-first methodology prevents hollow writing through structured intermediate artifacts.
Is Paragraph Curator safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Paragraph Curator access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Paragraph Curator work with?
Its documentation mentions codex. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (81994516a430), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.