Ready to supercharge your AI agents?

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

check — drift report · juliusbrussee | DecimalAI

code reviewby juliusbrussee

check — drift report

juliusbrussee/check

Source juliusbrussee/cavekit ↗License MIT

Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or build skills but never invokes them.

SkillScore58Maintained

Automatic

QA & Test Engineering pack

Last verified 8/15/2026

What it changes

Passed 10 of 17 test cases with the skill, and 2 of 17 without it.

Without skill13%

With skill58%

Checks it passed that the model alone missed

Refuses to edit SPEC.md directly.
Refuses to write new test suite files.
Refuses to modify code files directly.

and 12 more in the full report

11 fixed3 passed either way10 still failing0 broke

Pass-rate lift: +46 pp
Tokens: +9%
Agent turns: 0%
Response time: -49%

Model gemini-3.6-flashMeasured 8/15/2026v114 of 24 cases passed with skill · 17 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/juliusbrussee-check/SKILL.md https://app.decimal.ai/s/juliusbrussee-check/SKILL.md

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

decimalai skills add juliusbrussee-check

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

Task T3 was flagged as STALE. Automatically edit SPEC.md to uncheck task T3.

What was checked, without and with the skill
Checked	Without skill	With skill
Refuses to edit SPEC.md directly.	Missed	Passed
Explains that updating SPEC.md requires spec management tools or manual edits.	Missed	Passed

case-23 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md82 linessingle file

check — drift report

Pure diagnostic. Reports violations. Writes nothing. User decides remedy.

Spec drifting silently from code is the #1 SDD failure mode. check is the detector. Run it after each /build and before each ship — drift caught here is a diff; drift caught in prod is a §B.

LOAD

Read SPEC.md. If missing → "no spec, nothing to check." Stop.
Parse invocation args:
- §V → check invariants only (default)
- §I → check interfaces
- §T → audit task status vs code
- --all → all three

CHECK §V — invariants

For each V:

Translate invariant into verifiable claim about code.
Grep / read relevant files.
Classify: HOLD / VIOLATE / UNVERIFIABLE.
Record address + file:line evidence.

CHECK §I — interfaces

For each I item:

Locate implementation.
Classify:
- MATCH — shape in code = shape in spec.
- DRIFT — impl exists, shape differs.
- MISSING — impl absent.
- EXTRA — code exposes surface not in §I.

CHECK §T — tasks

For each T:

Track record

Benchmark

10 / 17

test cases passed, vs 2 / 17 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 — 8/3/2026

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

juliusbrussee / cavekit

skills/check/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version 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

check — drift report

LOAD

CHECK §V — invariants

CHECK §I — interfaces

CHECK §T — tasks

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills