Ready to supercharge your AI agents?

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

Computer Science — 10 Skills · brycewang-stanford | DecimalAI

researchby brycewang-stanford

Computer Science — 10 Skills

brycewang-stanford/cs-skills

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

10 computer science skills. Trigger: algorithms, systems research, software engineering, security papers. Design: theory, complexity analysis, code-centric research, and security methods.

NewMaintained

Automatic

Research pack

Last verified 8/30/2026

What it changes

6 of 23 test cases passed with the skill.

Pass-rate lift: —
Tokens: -29%
Agent turns: 0%
Response time: -20%

Model gemini-3.6-flashMeasured 8/30/2026v16 of 23 cases passed with skill · 7 comparable

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

Lift withheld: 7 comparable cases; this report requires 8.

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

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

decimalai skills add brycewang-stanford-cs-skills

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

We are compiling a taxonomy of machine learning attacks strictly from ACM CCS, NDSS, IEEE S&P, and USENIX Security. Which guide specifically curates AI security papers from these top four security conferences?

What was checked, without and with the skill
Checked	Without skill	With skill
Recommends selecting ai-security-papers-guide/SKILL.md.	Missed	Passed
Identifies top-4 security conferences as the core filtering criteria.	Passed	Passed

case-13 · gemini-3.6-flash · 8/30/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md16 linessingle file

Computer Science — 10 Skills

Select the skill matching the user's need, then read its SKILL.md.

Skill	Description
ai-security-papers-guide	AI security papers from top-4 security conferences
algorithms-complexity-guide	Analyze algorithm complexity and computational efficiency for research
code-llm-papers-guide	Survey and paper collection on LLMs for code generation
dblp-api	Search computer science publications, authors, and venues via DBLP
distributed-systems-guide	Distributed systems design patterns and analysis for CS research
formal-verification-guide	Formal methods, theorem proving, and model checking for CS research
gaussian-splatting-papers-guide	Curated papers and resources for 3D Gaussian Splatting
llm-aiops-guide	Papers on LLMs for IT operations and AIOps research
software-engineering-research	Guide to software engineering research topics and methodologies
software-heritage-api	Archive and retrieve source code history via Software Heritage API

Track record

Benchmark

6 / 23

test cases passed with the skill

Adoption

Users: 1
Times used: 30

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/9/2026

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/43-wentorai-research-plugins/skills/domains/cs/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/9/2026Version 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

Computer Science — 10 Skills

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills