Ready to supercharge your AI agents?

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

Coverage loop · fallow-rs | DecimalAI

testingby fallow-rs

Coverage loop

fallow-rs/coverage-loop

Source fallow-rs/fallow ↗License MIT

Iteratively improve Fallow Rust test coverage with cargo-llvm-cov, prioritizing meaningful untested behavior and preserving runtime correctness.

SkillScore73Maintained

Automatic

QA & Test Engineering pack

Last verified 9/28/2026

What it changes

Passed 15 of 20 test cases with the skill, and 10 of 20 without it.

Without skill50%

With skill73%

Checks it passed that the model alone missed

The response states to run review as the final step.
The response specifies running review as the final step.
The response states to keep tests that lock a real invariant.

and 4 more in the full report

6 fixed10 passed either way5 still failing1 broke

Pass-rate lift: +23 pp
Tokens: -49%
Agent turns: 0%
Response time: -47%

Model gemini-3.6-flashMeasured 9/28/2026v216 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/fallow-rs-coverage-loop/SKILL.md https://app.decimal.ai/s/fallow-rs-coverage-loop/SKILL.md

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

decimalai skills add fallow-rs-coverage-loop

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

I just completed adding behavior tests for `crypto/signatures.rs`, re-ran the targeted tests, and verified that coverage increased with zero redundant tests. What is the final step I must run before submitting this work?

What was checked, without and with the skill
Checked	Without skill	With skill
The response states to run review as the final step.	Missed	Passed

case-07 · 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.md14 linessingle file

Coverage loop

Capture a coverage baseline with the repository-supported command.
Select uncovered behavior by risk, not by easiest lines.
Add behavior-focused tests that survive refactors.
Re-run targeted tests and the same coverage command.
Keep only tests that improve meaningful coverage or lock a real invariant.
Repeat until the selected risk area is covered or remaining gaps require a separate design change.
Run review.

Do not add assertions that merely execute code without checking behavior.

Track record

Benchmark

15 / 20

test cases passed, vs 10 / 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/coverage-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

Coverage loop

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills