Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Arsoc Transparency And Reproducibility · brycewang-stanford | DecimalAI

researchby brycewang-stanford

Arsoc Transparency And Reproducibility

brycewang-stanford/arsoc-transparency-and-reproducibility

Source brycewang-stanford/awesome-journal-skills ↗License MIT

Use when documenting the coverage account of an Annual Review of Sociology (ARSoc) review and the transparency obligations of any systematic-review search or meta-analysis the review itself contains. Builds the search/selection record and the reproducibility plan; it does not gather the literature (arsoc-literature-synthesis) or appraise individual studies' designs (arsoc-comprehensiveness-and-balance).

SkillScore95Maintained

Automatic

Research pack

Last verified 8/15/2026

What it changes

Passed 21 of 22 test cases with the skill, and 16 of 22 without it.

Without skill73%

With skill95%

Checks it passed that the model alone missed

Identifies editorial strategy and scope planning as the next workflow step.
Recommends transitioning to editorial strategy and volume timeline planning.
Directs submission workflow progression toward editorial strategy and submission.

and 5 more in the full report

5 fixed16 passed either way1 still failing0 broke

Pass-rate lift: +23 pp
Tokens: +11%
Agent turns: 0%
Response time: -35%

Model gemini-3.6-flashMeasured 8/15/2026v121 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-arsoc-transparency-and-reproducibility/SKILL.md https://app.decimal.ai/s/brycewang-stanford-arsoc-transparency-and-reproducibility/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-arsoc-transparency-and-reproducibility, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/brycewang-stanford-arsoc-transparency-and-reproducibility/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-arsoc-transparency-and-reproducibility

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-arsoc-transparency-and-reproducibility/SKILL.md https://app.decimal.ai/s/brycewang-stanford-arsoc-transparency-and-reproducibility/SKILL.md

Raw file: /s/brycewang-stanford-arsoc-transparency-and-reproducibility/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-arsoc-transparency-and-reproducibility.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

After completing the literature coverage account and transparency checklist for an Annual Review submission, what is the specified immediate next workflow step?

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies the next step as transitioning to editorial strategy and volume timeline planning.	Missed	Passed

case-20 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md73 linessingle file

Transparency & Reproducibility for a Review (arsoc-transparency-and-reproducibility)

When to trigger

The synthesis is settled and you must show how the literature was searched and selected
The review reports a quantitative synthesis (meta-analysis, meta-regression, citation analysis) of its own
A Committee member or referee is likely to ask "how did you decide what to include?"
You want the coverage account to pre-empt the predictable "you omit literature X" pushback

What "transparency" means in a review with no primary data

An ARSoc review reports no new data of its own, so the usual replication-package machinery (raw data, estimation code, a reproducibility README of your analysis) does not apply to the review's claims about the world. Transparency instead bites on two things you do produce:

The coverage account — a documented, near-PRISMA-style record of how the literature was searched, screened, and selected. This is what makes "comprehensive" a verifiable claim rather than a boast.
Any analysis the review itself runs — if the review contributes a meta-analysis, a citation/bibliometric analysis, or a re-coded dataset of studies, that artefact must be reproducible and depositable like any quantitative work.

Distinguish the two clearly: you are not defending an identification strategy of your own (there is none); you are documenting how you found and weighed others' work, and reproducing any synthesis you actually computed.

The coverage account (near-PRISMA, adapted for sociology)

Carry forward the saturation log from arsoc-literature-synthesis into a brief, sharable record:

Element	What to document
Databases & dates	Sociological Abstracts, Web of Science, Scopus, JSTOR, Google Scholar — with search dates
Search terms & traditions	keyword strings and the theoretical-tradition names swept
Inclusion / exclusion	what counted (years, methods/modes, languages, publication types) and what was excluded and why
Mode coverage	how qualitative, computational, demographic, and theoretical work were captured (not just quant)
Saturation	where forward/backward snowballing stopped yielding new must-cites
Counts	rough numbers screened vs. discussed, so "comprehensive" is auditable

Sociology reviews are rarely strict PRISMA systematic reviews, but a near-PRISMA narrative of the search makes the coverage defensible and is increasingly expected. Confirm whether the topic warrants a formal PRISMA flow on the author pages (检索于 2026-06；以官网为准).

When the review runs its own analysis

If the review contributes a meta-analysis or bibliometric study:

Deposit data + code in a public repository (OSF, Dataverse, Zenodo) so the synthesis is reproducible; cite the DOI.
State the protocol: inclusion criteria, effect-size extraction, coding rules, weighting, heterogeneity and publication-bias diagnostics.
Pool only commensurable studies — never reduce qualitative or theoretical work to a spurious effect size (see arsoc-tables-figures).

Track record

Benchmark

21 / 22

test cases passed, vs 16 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

brycewang-stanford / awesome-journal-skills

Annual-Review-of-Sociology-Skills/skills/arsoc-transparency-and-reproducibility/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

brycewang-stanford/arpsych-transparency-and-reproducibilityUse when documenting the literature search and making any embedded meta-analysis reproducible for an Annual Review of Psychology (ARPsych) review. Covers search transparency, meta-analytic rigor, and open materials; it does not run the narrative search (arpsych-literature-synthesis) or design exhibits (arpsych-tables-figures).Close match+18 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.