Ready to supercharge your AI agents?

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

Get Started Free →

Source Coding · vibeeval | DecimalAI

scienceby vibeeval

Source Coding

vibeeval/source-coding

Source vibeeval/vibecosystem ↗License MIT

Problem-solving strategies for source coding in information theory

SkillScore100Maintained

Automatic

Research pack

Last verified 8/4/2026

What it changes

Passed 20 of 20 test cases with the skill, and 17 of 20 without it.

Without skill86%

With skill100%

Checks it passed that the model alone missed

Specify scripts/z3_solve.py
Specify scripts/sympy_compute.py
Specify the target name shannon_bound

3 fixed19 passed either way0 still failing0 broke

Pass-rate lift: +14 pp
Tokens: +36%
Agent turns: 0%
Response time: -25%

Model gemini-3.6-flashMeasured 8/4/2026v122 of 22 cases passed with skill · 20 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/vibeeval-source-coding/SKILL.md https://app.decimal.ai/s/vibeeval-source-coding/SKILL.md

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

decimalai skills add vibeeval-source-coding

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

curl -fsSL --create-dirs -o .claude/skills/vibeeval-source-coding/SKILL.md https://app.decimal.ai/s/vibeeval-source-coding/SKILL.md

Raw file: /s/vibeeval-source-coding/SKILL.md ↗ · machine-readable summary at /s/vibeeval-source-coding.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

You are calculating symbolic expressions for expected code length simplification in Python. Which script file in the scripts directory handles symbolic simplification harness tasks?

What was checked, without and with the skill
Checked	Without skill	With skill
Specify scripts/sympy_compute.py	Missed	Passed

case-08 · gemini-3.6-flash · 8/4/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md65 linessingle file

Source Coding

When to Use

Use this skill when working on source-coding problems in information theory.

Decision Tree

Source Coding Theorem
- Minimum average code length >= H(X)
- Achievable with optimal codes
- z3_solve.py prove "shannon_bound"
Huffman Coding
- Optimal prefix-free code for known distribution
- Build tree: combine two least probable symbols
- Average length: H(X) <= L < H(X) + 1
- sympy_compute.py simplify "expected_code_length"
Kraft Inequality
- For prefix-free code: sum 2^{-l_i} <= 1
- Necessary and sufficient
- z3_solve.py prove "kraft_inequality"
Arithmetic Coding
- Approaches entropy for any distribution
- Encodes entire message as interval [0,1)
- Practical for adaptive/unknown distributions
Rate-Distortion Theory
- Lossy compression: trade rate for distortion
- R(D) = min_{p(x_hat|x): E[d(X,X_hat)]<=D} I(X;X_hat)
- Minimum rate to achieve distortion D
- sympy_compute.py minimize "I(X;X_hat)" --constraint "E[d] <= D"

Tool Commands

Scipy_Huffman

Track record

Benchmark

20 / 20

test cases passed, vs 17 / 20 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 — 8/1/2026

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

vibeeval / vibecosystem

skills/math/information-theory/source-coding/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version 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

Source Coding

When to Use

Decision Tree

Tool Commands

Scipy_Huffman

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills