perf-loop

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

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/perf-loop/SKILL.md

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, well-sequenced optimization loop with explicit correctness and reproducibility gates. Its only gap is actionability: the steps name what to do but don't provide the executable commands or tooling to do it.

Suggestions

Add concrete commands or one-line examples for the key steps (e.g., the benchmark invocation, the profiling tool to use, and what `review` runs).

Briefly specify how to judge 'statistically useful baseline' (e.g., number of runs or variance threshold) so the gate is reproducible.

Clarify what 'materially different workload' means for switching benchmark identifiers, or link to where workload definitions live.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: a numbered loop plus one guarding rule, no padding or explanation of concepts Claude already knows; every line earns its place.	3 / 3
Actionability	Steps are concrete imperatives but lack executable commands/scripts (no actual benchmark command, profiling tool, or how to invoke `review`), so guidance is specific yet not copy-paste ready.	2 / 3
Workflow Clarity	A clear numbered sequence with an explicit validation checkpoint (step 5 re-run + correctness checks) and a keep-only-when-reproducible gate (step 6); the final 'Do not report...' rule acts as a guardrail, matching the feedback-loop anchor.	3 / 3
Progressive Disclosure	A simple under-50-line single-purpose skill with well-organized sections and no external references needed, so per the simple-skills note it qualifies for a 3 on organization alone.	3 / 3
	Total	11 / 12 Passed

Description

50%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description states concrete capabilities and a clear domain but omits an explicit 'when to use' trigger clause, capping its completeness. Trigger terms are reasonable but not rich with the natural variations a user would say.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases (e.g., 'Use when the user asks to speed up or optimize Fallow, reduce latency, or wants benchmarked performance gains').

Broaden trigger terms with natural user phrasings like 'slow', 'speed up', 'latency', 'throughput', and 'benchmark Fallow'.

Name more specific concrete actions (e.g., 'profile the hot path, run before/after benchmarks, gate changes on correctness checks') to lift specificity.

Dimension	Reasoning	Score
Specificity	It names the domain (Fallow performance) and several concrete actions ('optimize', 'stable benchmarks', 'before-and-after evidence', 'correctness gates'), but the actions are generic verbs rather than a comprehensive list of specific capabilities.	2 / 3
Completeness	It clearly answers 'what' (iteratively optimize performance with benchmarks and correctness gates) but there is no 'Use when...' clause or equivalent explicit trigger guidance for when Claude should invoke it, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	'performance', 'benchmarks', 'optimize' are relevant natural terms, but it lacks common variations a user would actually say (e.g., 'speed up', 'slow', 'latency', 'benchmark Fallow') and leans on the project name 'Fallow' as the main trigger.	2 / 3
Distinctiveness Conflict Risk	Tied to the specific Fallow project niche, which is somewhat distinctive, but generic performance/benchmark language could still overlap with a general benchmarking or profiling skill.	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: fallow-rs/fallow
Path: .agents/skills/perf-loop/SKILL.md
Commit: 55944e8

Reviewed: about 18 hours ago

Table of Contents

Discovery Implementation Validation

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.