CtrlK
BlogDocsLog inGet started
Tessl Logo

lading-optimize-hunt

Coordinates optimization attempts. Captures baselines, implements changes, invokes review, and records outcomes.

60

1.37x
Quality

43%

Does it follow best practices?

Impact

88%

1.37x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/lading-optimize-hunt/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

64%

-24%

Record Optimization Outcome

Recording verdicts verbatim

Criteria
Without context
With context

Verbatim YAML content

40%

100%

Correct YAML file path

100%

0%

db.yaml entry added

100%

0%

id field matches

100%

80%

target field matches

100%

80%

technique field matches

100%

80%

status field correct

100%

80%

verdict field correct

100%

80%

file field correct

100%

80%

Template format followed

100%

80%

100%

55%

Automate the Performance Optimization Hunt

Scripting the hunt workflow

Criteria
Without context
With context

Preflight invoked first

100%

100%

Baseline files cleared

0%

100%

criterion directory removed

0%

100%

cargo criterion micro-benchmark

0%

100%

hyperfine warmup and runs

50%

100%

hyperfine JSON export

40%

100%

Memory stats captured

0%

100%

Baseline before implementation

100%

100%

ci/validate called

100%

100%

Review invocation order

30%

100%

BENCH strips path and extension

0%

100%

100%

40%

Optimize the Syslog Payload Generator

Single focused change with review handoff

Criteria
Without context
With context

Single optimization applied

100%

100%

Buffer declared outside loop

0%

100%

Buffer cleared per iteration

0%

100%

format!() removed from loop

100%

100%

ci/validate documented

0%

100%

No post-change benchmarks

100%

100%

Review owns verdict

0%

100%

Minimal scope

100%

100%

Technique named

100%

100%

Repository
DataDog/lading
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.