Ready to supercharge your AI agents?

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

Audit · ccch1mneyyy | DecimalAI

code reviewby ccch1mneyyy

Audit

ccch1mneyyy/audit

Source ccch1mneyyy/dsh-tui ↗License MIT

Use when asked to audit a codebase, or when the /audit command runs — find security, correctness, and quality issues across a project and report them organized by severity.

NewMaintained

Automatic

Security & AppSec pack

Last verified 9/9/2026

What it changes

Passed 3 of 12 test cases with the skill, and 7 of 12 without it.

Without skill61%

With skill26%

Checks it passed that the model alone missed

Ranks confirmed findings by severity level.
Explains code simplification in terms of preserved behavior.

2 fixed4 passed either way7 still failing10 broke

Pass-rate lift: -35 pp
Tokens: +66%
Agent turns: 0%
Response time: +43%

Model gemini-3.6-flashMeasured 9/9/2026v26 of 23 cases passed with skill · 12 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/ccch1mneyyy-audit/SKILL.md https://app.decimal.ai/s/ccch1mneyyy-audit/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ccch1mneyyy-audit, 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/ccch1mneyyy-audit/ and pins it in .decimal/skills.lock

decimalai skills add ccch1mneyyy-audit

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

curl -fsSL --create-dirs -o .claude/skills/ccch1mneyyy-audit/SKILL.md https://app.decimal.ai/s/ccch1mneyyy-audit/SKILL.md

Raw file: /s/ccch1mneyyy-audit/SKILL.md ↗ · machine-readable summary at /s/ccch1mneyyy-audit.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

Please perform a thorough security audit on our terminal application's session state and file access modules. Do not modify any files yet; we just want a findings-only report. We need a breakdown of verified defects ranked by severity level, including exact code locations, trigger conditions, impact analysis, and recommended fixes, along with a brief summary of which subsystems were inspected.

What was checked, without and with the skill
Checked	Without skill	With skill
Leaves source files unmodified when requested.	Passed	Passed
Ranks confirmed findings by severity level.	Missed	Passed
Lists inspected subsystems and material gaps.	Passed	Passed

case-01 · gemini-3.6-flash · 9/9/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md8 linessingle file

Establish the audit scope, then trace the relevant runtime paths. For a findings-only request, leave code unchanged; carry out fixes when the user has requested them.

Identify entry points, state owners, external inputs, and teardown paths within the requested scope.
Follow inputs through validation and consumers. In this TUI, inspect applicable session projections, plugin capabilities, file access, terminal escape handling, and long-session resource bounds. Prioritize paths whose failure can lose state, cross a trust boundary, or leave the terminal unusable. Check dependencies and lockfiles for known vulnerabilities against advisory data.
Confirm suspected defects against callers, existing guards, and focused regressions. Check exports, registries, and supported compatibility paths before declaring code dead. Explain a simplification in terms of current requirements and the behavior it preserves.
Report confirmed findings by severity with location, trigger, impact, and a concrete remedy. Keep unverified leads separate. For a cross-layer failure, a short input → boundary → effect trace may be enough to explain it.
State the areas examined, checks actually run, and material gaps. No findings means none found in that scope, not proof that the whole project is safe. An audit can finish without findings or a forced list of healthy areas.

Track record

Benchmark

3 / 12

test cases passed, vs 7 / 12 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 v5 — 9/9/2026

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

ccch1mneyyy / dsh-tui

skills/audit/SKILL.md

View on GitHub ↗

License MITImported 9/9/2026Version v2

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