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%Weight 40%Scale 1-3

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

The body is an exemplar of lean, well-sequenced instruction design: a tight numbered loop with explicit validation gates, a keep/reject feedback decision, and a no-debug-build guardrail. Its only gap is actionability, since most steps describe what to do rather than naming concrete tools or commands.

Dimension	Reasoning	Score
Conciseness	The body is a lean numbered loop plus one guardrail sentence ("Do not report performance gains from debug builds or incomparable fixtures."); it assumes Claude's competence and explains no background concepts, so every token earns its place.	3 / 3
Actionability	Steps give specific bounded direction ("Implement one bounded optimization", "Record a statistically useful baseline") and one concrete command ("Run `review`"), but most steps are instructions rather than executable commands or tools, so guidance is actionable but not copy-paste ready.	2 / 3
Workflow Clarity	A clear numbered sequence includes explicit validation checkpoints and a feedback loop: step 5 re-runs benchmark and correctness checks, step 6 gates the change on reproducibility and no-contract-regression, and step 7 mandates a fresh benchmark for a different workload.	3 / 3
Progressive Disclosure	This is a simple single-purpose skill well under 50 lines with no need for external references, and its content is cleanly organized into one loop plus a guardrail, so it qualifies for a top score without bundle files.	3 / 3
	Total	11 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 is concise and names a clear Fallow-specific performance niche with concrete artifacts (benchmarks, evidence, gates), but it lacks an explicit 'Use when...' trigger clause, which caps both completeness and distinctiveness at the mid level. It is solid but not exemplary.

Suggestions

Add an explicit trigger clause, e.g. 'Use when optimizing Fallow performance, running benchmarks, or profiling hot paths.'

Replace the single generic verb 'optimize' with several concrete actions (e.g. 'profile hot paths, run stable benchmarks, gate changes on correctness') to lift specificity.

Include natural user phrasings like 'speed up Fallow' or 'make Fallow faster' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("Fallow performance") and several concrete components ("stable benchmarks, before-and-after evidence, and correctness gates"), but the only action verb is the generic "optimize", so it does not enumerate multiple specific concrete actions as comprehensively as a level-3 anchor.	2 / 3
Completeness	It clearly states what the skill does (iteratively optimize Fallow performance with benchmarks, evidence, and gates), but the "when to use it" guidance is only implied with no "Use when..." clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant natural terms like "optimize Fallow performance" and "benchmarks" are present, but it omits common variations a user might actually say (e.g. "speed up", "make it faster", "profile") and has no explicit trigger clause.	2 / 3
Distinctiveness Conflict Risk	The Fallow-specific performance niche is reasonably distinct, but without explicit trigger phrasing it could still overlap with general profiling or benchmarking skills, keeping it below a level-3 clear-niche rating.	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: 8 days 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.