Ready to supercharge your AI agents?

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

SIG audit loop · fallow-rs | DecimalAI

codingby fallow-rs

SIG audit loop

fallow-rs/sig-audit-loop

Source fallow-rs/fallow ↗License MIT

Iteratively improve Fallow maintainability using measured SIG audit deltas, retaining only changes that improve the targeted property without regressions.

SkillScore78Maintained

Automatic

Coding pack

Last verified 9/28/2026

What it changes

Passed 16 of 20 test cases with the skill, and 13 of 20 without it.

Without skill65%

With skill78%

Checks it passed that the model alone missed

Names `sig-audit` as the command to run.
Requires running `review` prior to submitting final changes.
Reverts the change because the target property score did not improve.

3 fixed15 passed either way5 still failing0 broke

Pass-rate lift: +13 pp
Tokens: -45%
Agent turns: 0%
Response time: -49%

Model gemini-3.6-flashMeasured 9/28/2026v218 of 23 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/fallow-rs-sig-audit-loop/SKILL.md https://app.decimal.ai/s/fallow-rs-sig-audit-loop/SKILL.md

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

decimalai skills add fallow-rs-sig-audit-loop

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

curl -fsSL --create-dirs -o .claude/skills/fallow-rs-sig-audit-loop/SKILL.md https://app.decimal.ai/s/fallow-rs-sig-audit-loop/SKILL.md

Raw file: /s/fallow-rs-sig-audit-loop/SKILL.md ↗ · machine-readable summary at /s/fallow-rs-sig-audit-loop.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

What command or tool must be run at the start of a signature metric optimization loop to identify which property is weak in our codebase?

What was checked, without and with the skill
Checked	Without skill	With skill
Names `sig-audit` as the command to run.	Missed	Passed

case-21 · gemini-3.6-flash · 9/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md13 linessingle file

SIG audit loop

Run sig-audit and select one weak property.
Identify a bounded structural change with a measurable expected effect.
Measure before, implement, and measure after with identical settings.
Keep the change only when the target improves and verification remains green.
Repeat until the target is met or further changes have no credible benefit.
Run review before proposing the final result.

Never combine unrelated cleanup into one measurement iteration.

Track record

Benchmark

16 / 20

test cases passed, vs 13 / 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 v5 — 8/31/2026

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

fallow-rs / fallow

.agents/skills/sig-audit-loop/SKILL.md

View on GitHub ↗

License MITImported 8/31/2026Version v2

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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

SIG audit loop

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills