Ready to supercharge your AI agents?

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

Get Started Free →

Generate Abstract · brycewang-stanford | DecimalAI

documentationby brycewang-stanford

Generate Abstract

brycewang-stanford/abstract

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

Reads the manuscript and notebooks to generate a structured abstract.

SkillScore59Maintained

Automatic

Writing & Editing pack

Last verified 8/9/2026

What it changes

Passed 8 of 14 test cases with the skill, and 7 of 14 without it.

Without skill50%

With skill59%

Checks it passed that the model alone missed

Specifies 1 to 2 sentences for the Motivation section.
Specifies 2 to 3 sentences for the Key results section.
Mentions extracting main coefficient estimates and significance levels.

and 1 more in the full report

4 fixed9 passed either way7 still failing2 broke

Pass-rate lift: +9 pp
Tokens: -41%
Agent turns: 0%
Response time: -68%

Model gemini-3.6-flashMeasured 8/9/2026v113 of 22 cases passed with skill · 14 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-abstract/SKILL.md https://app.decimal.ai/s/brycewang-stanford-abstract/SKILL.md

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

decimalai skills add brycewang-stanford-abstract

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

Which part of index.qmd supplies the content for the final "Contribution" sentence of the abstract?

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies the Conclusion section as the source for the paper's contribution.	Missed	Passed

case-12 · gemini-3.6-flash · 8/9/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md43 linessingle file

Generate Abstract

Read the manuscript and generate a structured abstract.

Arguments

$ARGUMENTS — optional target word count (default: 150 words)

Steps

Parse the target word count from arguments (default 150 if not specified).
Read index.qmd in full:
- Identify the research question from the Introduction
- Identify the data and methods from the Data/Methods sections
- Identify key results from the Results section
- Identify the contribution from the Conclusion
Read the registered notebooks to extract key quantitative findings:
- Main coefficient estimates and significance levels
- Sample size
- Key figures or descriptive statistics
Draft a structured abstract with these components:
- Motivation (1–2 sentences): What problem or question does this paper address? Why does it matter?
- Data and methods (1–2 sentences): What data, sample, and empirical approach are used?
- Key results (2–3 sentences): What are the main findings? Include specific numbers where possible.
- Contribution (1 sentence): What is the paper's contribution to the literature or policy?
Verify the word count is within ±10% of the target. Adjust if needed.
Present the draft to the user for review.
On approval, update the abstract: field in the YAML front matter of index.qmd:
```
abstract: |
  <drafted abstract text>
```

Error handling

Track record

Benchmark

8 / 14

test cases passed, vs 7 / 14 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/29-quarcs-lab-project20XXy/dot-claude/skills/abstract/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1

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

Generate Abstract

Arguments

Steps

Error handling

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills