Ready to supercharge your AI agents?

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

Get Started Free →

Performance loop · fallow-rs | DecimalAI

codingby fallow-rs

Performance loop

fallow-rs/perf-loop

Source fallow-rs/fallow ↗License MIT

Iteratively optimize Fallow performance with stable benchmarks, before-and-after evidence, and correctness gates.

SkillScore88Maintained

Automatic

Coding pack

Last verified 9/28/2026

What it changes

Passed 21 of 24 test cases with the skill, and 17 of 24 without it.

Without skill71%

With skill88%

Checks it passed that the model alone missed

Specifies executing `review` as the final step.
Specifies running `review` at the end of the cycle.
Requires that performance improvements be reproducible to be kept.

and 1 more in the full report

4 fixed17 passed either way3 still failing0 broke

Pass-rate lift: +17 pp
Tokens: -54%
Agent turns: 0%
Response time: -53%

Model gemini-3.6-flashMeasured 9/28/2026v2 · latest is v421 of 24 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.6-flash on 10/4/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.

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-perf-loop/SKILL.md https://app.decimal.ai/s/fallow-rs-perf-loop/SKILL.md

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

decimalai skills add fallow-rs-perf-loop

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

We finished implementing an optimization in `hyper-router`, verified the benchmark baseline vs new run, and confirmed all tests pass. What is the mandatory final step before finalizing the optimization work?

What was checked, without and with the skill
Checked	Without skill	With skill
Specifies executing `review` as the final step.	Missed	Passed

case-16 · 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.md18 linessingle file

Performance loop

Choose a stable benchmark and preserve its identity and workload. Before you freeze it, prove that it can see the problem: a known slowdown must move the result.
Record a statistically useful baseline. Set a target and a minimum number of rounds. Do not stop before that minimum unless you reach the target.
Profile the hot path before editing.
Implement one bounded optimization.
Re-run the same benchmark and correctness checks.
Keep the change only when the improvement is reproducible and no contract regresses.
Use a new benchmark identifier for a materially different workload.
Run review.

Do not report performance gains from debug builds or incomparable fixtures.

Track record

Benchmark

21 / 24

test cases passed, vs 17 / 24 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 — 9/30/2026

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/perf-loop/SKILL.md

View on GitHub ↗

License MITImported 9/30/2026Version v4

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

Performance loop

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills