Ready to supercharge your AI agents?

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

Proofread Lecture Files · brycewang-stanford | DecimalAI

documentationby brycewang-stanford

Proofread Lecture Files

brycewang-stanford/proofread

Source brycewang-stanford/Auto-Empirical-Research-Skills ↗License NOASSERTION

Run the proofreading protocol on academic writing — papers or manuscripts. Checks grammar, typos, layout issues, consistency, and academic writing quality. Produces a report without editing files. Make sure to use this skill whenever the user wants surface-level writing errors found — not substantive academic critique. Triggers include: "proofread", "check for typos", "grammar check", "look for errors in my draft", "proofread all", "polish this", "check my writing", "are there any mistakes", "pr

SkillScore75Maintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Writing & Editing pack

Last verified 8/8/2026

What it changes

Passed 14 of 18 test cases with the skill, and 9 of 18 without it.

Without skill50%

With skill75%

Checks it passed that the model alone missed

The response identifies search-and-replace artifacts.
The response identifies `Slides/` as a target directory.
The response identifies `Quarto/` as a target directory.

and 6 more in the full report

8 fixed10 passed either way4 still failing2 broke

Pass-rate lift: +25 pp
Tokens: -41%
Agent turns: 0%
Response time: -71%

Model gemini-3.6-flashMeasured 8/8/2026v618 of 24 cases passed with skill · 18 comparable

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-proofread/SKILL.md https://app.decimal.ai/s/brycewang-stanford-proofread/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-proofread, 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-proofread/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-proofread

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

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

Raw file: /s/brycewang-stanford-proofread/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-proofread.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

I am running the proofreading protocol on `Slides/chapter2_calculus.tex`. What is the exact path where the output report must be stored?

What was checked, without and with the skill
Checked	Without skill	With skill
The response specifies `quality_reports/chapter2_calculus_report.md` as the target file path.	Missed	Passed

case-05 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md35 linessingle file

Proofread Lecture Files

Run the mandatory proofreading protocol on lecture files. This produces a report of all issues found WITHOUT editing any source files.

Steps

Identify files to review:
- If $ARGUMENTS is a specific filename: review that file only
- If $ARGUMENTS is "all": review all lecture files in Slides/ and Quarto/
For each file, launch the proofreader agent that checks for:

GRAMMAR: Subject-verb agreement, articles (a/an/the), prepositions, tense consistency TYPOS: Misspellings, search-and-replace artifacts, duplicated words OVERFLOW: Overfull hbox (LaTeX), content exceeding slide boundaries (Quarto) CONSISTENCY: Citation format, notation, terminology ACADEMIC QUALITY: Informal language, missing words, awkward constructions
Produce a detailed report for each file listing every finding with:
- Location (line number or slide title)
- Current text (what's wrong)
- Proposed fix (what it should be)
- Category and severity
Save each report to quality_reports/:
- For .tex files: quality_reports/FILENAME_report.md
- For .qmd files: quality_reports/FILENAME_qmd_report.md
IMPORTANT: Do NOT edit any source files. Only produce the report. Fixes are applied separately after user review.
Present summary to the user:
- Total issues found per file
- Breakdown by category
- Most critical issues highlighted

Track record

Benchmark

14 / 18

test cases passed, vs 9 / 18 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 — 8/2/2026

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 / Auto-Empirical-Research-Skills

skills/15-Felpix-Studios-social-science-research/skills/proofread/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v6

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

Ready to supercharge your AI agents?

See it in action

What's inside

Proofread Lecture Files

Steps

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills