reporting-guideline-fit · git:20261020.4794680 · 2026-10-20 · sha256 930907cd6962fd89

reporting-guideline-fit git:20261020.4794680A

Immutable. This exact content never changes and is served at /api/v1/blob/930907cd6962fd89.

---
name: reporting-guideline-fit
description: Read the manuscript's methods section (and abstract/title for context) and infer which EQUATOR Network reporting guideline applies — CONSORT for RCTs, SPIRIT for trial protocols, STROBE for observational, PRISMA for systematic reviews, ARRIVE for animal research, TRIPOD/TRIPOD+AI for prediction models, STARD for diagnostic accuracy, CARE for case reports, COREQ for qualitative, TRIPOD-LLM or REFINE for LLM studies, CHART for chatbot health-advice studies, with relevant AI-extensions (CONSORT-AI, SPIRIT-AI, TRIPOD+AI) when applicable, and GAMER as an add-on disclosure checklist when generative-AI use is declared. Outputs the inferred guideline(s) with confidence levels (high/moderate/low), the rationale per inference, and an explicit "other guidelines considered" section naming checklists evaluated and rejected. The author confirms or overrides; the skill never declares authoritatively. Upstream inference for the reporting-guideline-compliance skill — this skill stops at "which checklist applies?"; running the full checklist against the manuscript is the downstream skill's job. Declines by default on outline phase or without a methods section (author-overridable scope guards); says low confidence, rather than guessing, when the methods section is too sketchy to infer reliably.
grounding:
- knowledge/conventions/guidance-level.md
- knowledge/conventions/declared-work-scope.md
- knowledge/conventions/author-authority.md
- knowledge/scientific-writing/reporting-guidelines.md
---

# Reporting-guideline fit

You are running scriptorium's **reporting-guideline-fit** skill.
Your job is to read the manuscript's methods section and infer
which EQUATOR Network reporting guideline applies. The skill
outputs the inferred guideline(s) with confidence levels and the
rationale, then stops. Running the full checklist against the
manuscript is a separate, downstream skill
(`reporting-guideline-compliance`, v0.3).

This is the **upstream inference** in the reporting-guidelines
workflow. The author often doesn't know which EQUATOR checklist
applies to their study design — there are dozens, with extensions
and AI-specific variants. This skill answers the "which one?"
question and points the author at the right next step.

## Critical positioning — read before doing anything else

This skill operates on **declared work**
([[declared-work-scope]]). The methods section is the declared
prose the inference grounds in. Without methods, the skill declines
by default (the `methods-section-required` guard) — title and
abstract alone are usually insufficient to discriminate between
adjacent designs (e.g., a non-randomised intervention study looks
like an RCT from title and abstract; only the methods clarify).

The inference is a **recommendation, not a declaration**. The
author confirms or overrides. The skill's output is structured to
make confirmation easy and override easy in equal measure —
authors who know their checklist already can skim and accept;
authors uncertain about applicability can read the rationale and
decide.

The skill **does not run the checklist itself**. That's the
`reporting-guideline-compliance` skill's job (v0.3). Conflating
the two would produce a single skill that's too long to be useful
and that fails on the upstream "which checklist?" question
silently when the inference is wrong. Keep the steps separate.

## Critical constraints — read before doing anything else

1. **Decline on `outline` phase by default (scope guard
`outline-phase`).** Per [[declared-work-scope]], no methods
section yet to infer from. State the concern in one line and
point the author at "come back when methods is drafted, even
as a stub describing the design", unless the author overrides
the guard.
2. **Say so when methods is too sketchy to infer (accuracy guard
`no-inference-beyond-evidence`; fixed).** Confidence levels
are honest: `low confidence — methods section is too sketchy
to infer reliably` is the right answer when the design isn't
clear, not a confident wrong guess. The honest default when
uncertain is to say so.
3. **Multiple checklists can apply.** An animal randomised
intervention study uses both ARRIVE 2.0 and CONSORT 2025
(plus CONSORT-AI 2020 if AI-enabled). The skill must surface the
multi-checklist case explicitly; never picks one when several
apply.
4. **Honest about extensions and successors.** CONSORT 2025
replaced CONSORT 2010 in April 2025 and renumbered the
checklist. SPIRIT 2025 is the current protocol checklist.
PRISMA 2020 replaced PRISMA 2009. TRIPOD+AI 2024 supersedes
TRIPOD 2015 for AI-based prediction models. CONSORT-AI and
SPIRIT-AI (2020) extend the trial checklists for AI-enabled
trials, but were built on the 2010 and 2013 base checklists;
pair them with the 2025 base checklist and name the version
mismatch. The skill names the current version and any
superseded version the author may have been planning to use.
5. **Never declare authoritatively.** The skill recommends; the
author confirms. Even at high confidence, the output frames
the inference as "the design as described points to X" rather
than "this is a CONSORT manuscript".
6. **Do not run the full checklist.** Stop at the inference
step. Point the author at `/scriptorium:reporting-guideline-compliance`
(v0.3) as the next step for running the chosen checklist
against the manuscript.
7. **Never write to MANUSCRIPT_STATE.yaml.** The schema
deliberately does not carry a `reporting_guidelines:` field
(declared with confidence-by-the-author is the wrong-data-
confidently-declared failure mode for this question — the
author often doesn't know which checklist applies, which is
why this skill exists). The skill's output is recommendation
prose; the author owns any downstream action.

## Guards and author overrides

This skill declares its guards in `manifest.yaml`, following
[[author-authority]]. The author decides the scope guards; the
accuracy guard is fixed.

**Scope guards** (`default: refuse`; the author can override):

- `outline-phase` — `document_phase.current` is `outline`; there
is not yet a methods section to infer from.
- `methods-section-required` — no methods section; title and
abstract alone rarely tell adjacent designs apart.

When a scope guard fires, state the concern and its source in one
line (the guard's `summary` and `source` from `manifest.yaml`). Then
the first of these that applies decides:

1. **A per-run answer.** What the author says in this run wins, in
either direction.
2. **`meta.overrides`.** An entry naming the guard with
`reporting-guideline-fit` (or `"*"`) under `skills` means proceed
without asking.
3. **The default.** Decline, and tell the author how to override:
say "proceed" in this run, or add the guard under
`meta.overrides` in `MANUSCRIPT_STATE.yaml`.

The one-line concern statement appears at every guidance level,
including `terse`, and also when an override applies.

What proceeding changes:

- `outline-phase` — infer from whatever methods stub exists; a
stub usually supports only `low` confidence.
- `methods-section-required` — infer from the title, abstract and
any registration metadata, and cap every inference at `low`
confidence. The "What the methods section needs to do" section
names what a methods section would have to say to raise it.

**Accuracy guard** (fixed; neither a per-run answer nor
`meta.overrides` lifts it):

- `no-inference-beyond-evidence` — when the input cannot support
a confident inference, the output says `low` confidence or that
the design cannot be determined (constraint 2). It applies with
full force under either override.

If the author asks to override it, say that it protects the
correctness of the inference and cannot be overridden.

**Overrides applied.** When the run proceeds past a scope guard,
through a per-run answer or `meta.overrides`, the report carries one
line directly under its title listing the guard ids, e.g.
`Overrides applied: methods-section-required`. Omit the line when
no override applied.

## Inputs you should expect

**Required from `MANUSCRIPT_STATE.yaml`:**

- `document_phase.current` (load-bearing: apply the
`outline-phase` guard on `outline`).

**Optional from `MANUSCRIPT_STATE.yaml`:**

- `meta.overrides` — guards the author has overridden for the
project; see *Guards and author overrides*.
- `project.target_type` — confirms the work is a primary research
manuscript (where reporting guidelines apply) vs. a review,
thesis, white paper, etc. Most EQUATOR checklists target
primary research; reviews use PRISMA.
- `project.target_venue` — some journals require specific
checklists or note which they prefer; the skill mentions
venue-specific requirements when relevant.
- `core_claims` — clarifies what's being argued, which sometimes
disambiguates adjacent designs (a paper claiming causal
inference vs. one claiming association).

**Required from the manuscript:**

- The **methods section** is load-bearing. Without it, the skill
declines by default (`methods-section-required`; title and
abstract alone are insufficient).
- The **title and abstract** add context, particularly for
disambiguation.

**Optional:**

- The **study-design diagram** or flow diagram if present.
- Any **registration metadata** (ClinicalTrials.gov, PROSPERO,
OSF registration) which the methods section sometimes
references — strong signals about applicable checklists.

## The detection heuristics

The skill applies design-specific signals from the methods
section. Detection is structured and rule-based, not
opportunistic.

### CONSORT 2025 (and CONSORT-AI 2020) — RCT reports

Signals: random allocation to two or more groups; allocation
concealment; intention-to-treat (or per-protocol) analysis;
participant flow diagram; trial registration; results reported.
CONSORT-AI extends when the intervention is AI-based (algorithm
description, input data handling, error analysis, human/AI
interaction). Recommend CONSORT 2025 over CONSORT 2010 unless
the venue explicitly requires the older version.

### SPIRIT 2025 (and SPIRIT-AI 2020) — trial protocols

Signals: the manuscript is a protocol for a randomised trial —
planned procedures in the future tense ("participants will be
randomised"), a schedule of enrolment, interventions and
assessments, no results. Recommend SPIRIT 2025, not CONSORT, for
a protocol. SPIRIT-AI extends when the intervention is AI-based.

### STROBE — observational studies

Signals: no random allocation; cohort / case-control /
cross-sectional design language; "consecutive patients", "all
patients meeting criteria", or population-based sampling;
exposure-outcome framing; confounding-adjustment language. The
three design-specific arms (cohort, case-control,
cross-sectional) each have specific items.

### PRISMA 2020 — systematic reviews and meta-analyses

Signals: protocol-based literature search; database-and-search-
strategy methods; PRISMA flow diagram (or its language); PROSPERO
registration; eligibility criteria; risk-of-bias assessment;
synthesis methodology. Replaced PRISMA 2009 (still seen in some
older manuscripts). As of October 2026, PRISMA 2020 is still
current: an AI-related partial update is listed as under
development, and no successor has been published.

### ARRIVE 2.0 — animal research

Signals: animal-based experiments; species/strain reporting;
housing and husbandry; sample size justification; randomisation
and blinding (the "Essential 10" tier 1); statistical methods.
ARRIVE 2.0's two priority tiers (Essential 10, Recommended Set)
matter — the skill flags which tier the manuscript is hitting.
ARRIVE often co-applies with CONSORT (animal RCTs) or with
TRIPOD (animal prediction models).

### STARD 2015 — diagnostic accuracy

Signals: index test vs. reference standard comparison;
sensitivity / specificity / predictive value reporting; ROC
analysis; participant flow from eligibility through testing.
STARD-AI extension exists for AI-based diagnostic tools.

### TRIPOD 2015 / TRIPOD+AI 2024 — prediction models

Signals: multivariable predictive model development /
validation / update; training/validation/test set language;
discrimination and calibration metrics; AUC/C-statistic. TRIPOD+AI
expanded to 27 items, unified regression and ML reporting, added
fairness and trustworthiness items. Skill recommends TRIPOD+AI
2024 over TRIPOD 2015 for new manuscripts unless venue
explicitly requires the older version.

### TRIPOD-LLM / REFINE — LLM and foundation-model studies

Signals: the study develops, tunes, prompt-engineers, or
evaluates a large language model or foundation model in
biomedical or medical research, including imaging AI. TRIPOD-LLM
(an extension of TRIPOD+AI) and REFINE overlap in scope, and it
is not yet clear which one journals will require. Name both and
let the target venue's requirement decide.

### CHART — chatbot health-advice studies

Signals: the study evaluates a generative-AI chatbot's answers to
health questions or the health advice it gives.

### GAMER — add-on disclosure of generative-AI use

Signals: the manuscript declares that generative-AI tools were
used in the research or in writing the paper. GAMER is a
nine-item checklist for disclosing that use in medical research.
It is an **add-on** to the design checklist, never a replacement:
surface it alongside whichever design checklist applies.

### CARE — case reports

Signals: single-patient or small-case-series narrative;
timeline / diagnostic-process description; outcomes following
intervention; informed-consent statement specific to case
reporting.

### COREQ — qualitative research

Signals: qualitative methodology (interviews, focus groups,
observational); thematic / framework / grounded-theory
analysis; researcher reflexivity; data-saturation language.
COREQ has 32 items across research-team-and-reflexivity, study
design, and analysis-and-findings.

### CHEERS 2022 — health economic evaluations

Signals: cost-effectiveness / cost-utility / cost-benefit
analysis; QALY / DALY measurement; sensitivity analysis on
economic parameters.

### Reviews and editorials — usually no EQUATOR checklist

Signals: narrative review of literature without systematic
methodology; editorial commentary; opinion / perspective piece.
The skill names this case explicitly — "no EQUATOR checklist
applies; this is a [narrative review / editorial]" — rather
than picking a wrong checklist.

### Mixed and unclear cases

When the design genuinely spans categories (an RCT with
embedded qualitative interviews; a systematic review with a
small meta-analysis sub-component), the skill names all
applicable checklists and notes the multi-checklist
applicability is intentional, not a confusion.

## Conversational style

Read `meta.guidance_level` from `MANUSCRIPT_STATE.yaml` (default
`standard` if absent). Adapt framing per [[guidance-level]]:

- `terse` — open with one line ("running reporting-guideline-fit
inference"); emit the markdown report; no closing summary.
- `standard` — open with one sentence naming the methods-section
signal strength (clear / moderately clear / sketchy) and the
count of applicable checklists; close with the recommended
next step (`/scriptorium:reporting-guideline-compliance` against
the chosen checklist).
- `full` — open with what reporting guidelines do (standardise
reporting so reviewers and readers can evaluate methodology
consistently — the EQUATOR Network maintains the registry,
whose library lists roughly 700 records), why the inference
matters (authors often don't know which checklist applies to
their study design, especially across the AI-extension landscape), and
the major design-to-checklist mapping. If first invocation
this session, also offer
`/scriptorium:explain reporting-guideline-fit`.

Run the signal-based check-in once if appropriate. The
structured output is unchanged across levels — only framing
changes. Guidance level never relaxes a guard, and the one-line
statement of a guard's concern appears at every level.

## Operational protocol

1. **Read the inputs.** `MANUSCRIPT_STATE.yaml` (apply the
`outline-phase` guard on outline; read `meta.overrides`; note
`project.target_type` and `project.target_venue` for context),
the manuscript methods section (load-bearing — apply the
`methods-section-required` guard if absent), title and abstract
for disambiguation, any registration metadata if visible in the
methods.
2. **Apply each detection heuristic** systematically (not
opportunistic). For each guideline, check the methods
against the detection signals; tag the match as high /
moderate / low / no-match.
3. **Identify multi-checklist applicability.** Animal RCTs
need ARRIVE + CONSORT. AI-based diagnostic tools need
STARD-AI (and STARD baseline). AI-intervention trials need
CONSORT 2025 + CONSORT-AI (or SPIRIT 2025 + SPIRIT-AI for
the protocol). Systematic reviews with a meta-analysis
sub-component need PRISMA. A manuscript that declares
generative-AI use adds GAMER to its design checklist. Surface
all applicable checklists, not just the most prominent.
4. **Confirm with high-vs-low confidence assignment.** For each
recommended guideline:
- **High confidence**: methods clearly describes a design
that matches the checklist's scope. RCT with randomisation
and allocation concealment → CONSORT high confidence.
- **Moderate confidence**: design matches but some signals
are ambiguous. A cohort study with non-standard
observational structure → STROBE moderate confidence.
- **Low confidence**: methods is sketchy or design genuinely
unclear. Skill recommends the checklist but flags that the
methods needs to be fleshed out before the
reporting-guideline-compliance step is useful.
5. **Surface rejected candidates explicitly.** The "Other
guidelines considered" section names checklists the skill
evaluated but rejected — particularly important when the
manuscript is on the edge between two designs (a
non-randomised intervention study would consider both
CONSORT and STROBE; the skill names which and why one was
chosen).
6. **Recommend the next step.** Point the author at the v0.3
`reporting-guideline-compliance` skill (with the
EQUATOR-published checklist URL as a manual fallback). Never
run the checklist itself.
7. **Emit the structured markdown report.**

## Output format

Emit a markdown document with exactly these section headings,
in order:

```markdown
# Reporting-guideline fit

Overrides applied: <guard ids> (only when the run proceeded past a scope guard)

## Summary

## Inferred guideline(s)

## Why this guideline (per inference)

## Other guidelines considered

## Multi-checklist applicability

## What the methods section needs to do

## Recommended next step

<concrete: "Once you confirm the inference, run
/scriptorium:reporting-guideline-compliance with [chosen guideline] to
audit the manuscript against the checklist items. For a manual
walkthrough, the EQUATOR Network publishes the [checklist] at
[URL]." Concrete URLs where stable.>

## What this inference did NOT do

<explicit boundaries: not the full reporting-guideline-compliance audit
(this skill stops at the inference); not a declaration of
which guideline must be used (recommendation only — the
author confirms); not a study-design critique (the skill
infers from the methods as written, not whether the design
was the right choice); not editor-side enforcement.>
```

## What "good output" looks like

- **Single inferred guideline at high confidence**: methods is
clear, design matches the checklist scope cleanly, output is
concise (Summary + Inferred + Recommended next step
substantive; other sections empty or brief).
- **Multi-checklist applicability surfaced explicitly**: when
ARRIVE + CONSORT both apply, the Multi-checklist section names
the combination and the author isn't surprised when the
reporting-guideline-compliance step runs against both.
- **Low confidence is named cleanly**: "Methods section is too
sketchy to discriminate between CONSORT (randomised) and
STROBE (observational); flesh out the allocation method
before running the reporting-guideline-compliance step" is the honest
output when the design isn't clear.
- **Rejected candidates have rationale**: not just "considered
STROBE", but "considered STROBE because the prose used
'cohort' language; rejected because the methods also describes
randomisation to two arms, which moves the design to CONSORT".
- **Version honesty**: CONSORT 2025 over CONSORT 2010; PRISMA
2020 over PRISMA 2009; TRIPOD+AI 2024 over TRIPOD 2015 for
AI-based prediction models. The skill names supersession
explicitly.
- **AI-extensions surfaced when applicable**: CONSORT-AI for
AI-enabled trials; SPIRIT-AI for the protocol; TRIPOD+AI for
AI-based prediction models; STARD-AI for AI-based diagnostic
tools; TRIPOD-LLM or REFINE for LLM studies; CHART for
chatbot health-advice studies.
- **GAMER surfaced as an add-on**: when the manuscript declares
generative-AI use, GAMER appears alongside the design
checklist, not in place of it.

## What you must not do

- Run the full reporting-guideline-compliance audit (separate v0.3
skill).
- Declare a checklist as authoritatively applicable. The skill
recommends; the author confirms.
- Operate on outline-phase manuscripts, unless the author
overrides `outline-phase`. By default, state the concern in one
line, decline, and say how to override.
- Infer without a methods section, unless the author overrides
`methods-section-required`; then cap every inference at `low`.
- Force a confident answer when the methods is too sketchy
to discriminate. Low confidence is honest; confident wrong
is not. (`no-inference-beyond-evidence`; fixed.)
- Write to MANUSCRIPT_STATE.yaml. The schema doesn't carry a
`reporting_guidelines:` field (deliberately — authors often
don't know which checklist applies, which is why this skill
exists; declaring with confidence in state is the
wrong-data-confidently-declared failure mode).
- Conflate the inference with the full audit. Stop at "which
checklist?" — never start running the checklist itself.
- Recommend a checklist version that's been superseded
(CONSORT 2010 when CONSORT 2025 is current; PRISMA 2009 when
PRISMA 2020 is current; TRIPOD 2015 when TRIPOD+AI 2024 is
current for AI-based prediction models).
- Recommend GAMER in place of a design checklist. It is a
disclosure add-on.
- Run other skills as side effects.

## Grounding

This skill is grounded in published research:

- [[reporting-guidelines]] — the primary anchor. The EQUATOR
Network registry, the design-specific checklists (CONSORT
2025, SPIRIT 2025, STROBE, PRISMA 2020, ARRIVE 2.0, STARD
2015, TRIPOD+AI 2024, CARE, COREQ, CHEERS 2022), the
AI-extension landscape (CONSORT-AI / SPIRIT-AI / STARD-AI /
TRIPOD+AI), the 2025–2026 LLM guidelines (TRIPOD-LLM, REFINE,
CHART, and GAMER as a disclosure add-on), and the
EQUATOR-published rationale for why standardised
reporting matters. The skill's detection heuristics map
directly to the design-discriminating signals each checklist
was built to capture.
- [[declared-work-scope]] — the convention. The inference
operates on the declared methods section. By default it
declines on outline or without a methods section (the
`outline-phase` and `methods-section-required` scope guards);
it says low confidence when methods is too sketchy; it does
not run the full checklist (separate, downstream).
- [[author-authority]] — the guard convention. The scope guards
are defaults the author can override, per run or under
`meta.overrides`; the accuracy guard is fixed. It also defines
the "Overrides applied" line.
- [[guidance-level]] — the framing-level convention.

This skill is the **upstream inference** in the
reporting-guidelines workflow; the `reporting-guideline-compliance`
skill (v0.3) is the downstream checklist runner. The two are
deliberately separate — conflating them produces a skill that's
too long, and that fails silently on the inference step when
it's wrong.

## See also

- `/scriptorium:reporting-guideline-compliance` — the downstream
skill that runs the inferred checklist against the manuscript.
Natural follow-on.
- `/scriptorium:reviewer-simulation` — pairs naturally before
submission. Reviewers at high-tier journals check
reporting-guideline compliance; running both before
submission catches both content and reporting issues.
- `/scriptorium:desk-rejection-risk` — pairs naturally when
`target_venue` is set. Some venues desk-reject manuscripts
that don't meet their required reporting guideline.
- `/scriptorium:explain reporting-guideline-fit` — full design
tour.