perf-loop

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

Quality

76%

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 ./.claude/skills/perf-loop/SKILL.md

Quality

Content

86%Weight 40%Scale 1-5

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 performance loop with explicit correctness and reproducibility gates, respecting token budget and Claude's competence. The only meaningful gap is that profiling/correctness tooling is left unspecified and the failure-recovery loop is implicit.

Dimension	Reasoning	Score
Conciseness	An extremely lean 8-step list with a one-line closing guard and no explanation of concepts Claude already knows; every token earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor.	5 / 5
Actionability	Concrete, specific procedural guidance with clear criteria ('preserve its identity and workload', 'bounded optimization', 'reproducible', 'no contract regresses', run `review`), but no specific profiling tools or commands are named beyond `review`, leaving a minor gap versus fully executable 5.	4 / 5
Workflow Clarity	A clearly sequenced 8-step process with explicit validation checkpoints (step 5 re-run benchmark + correctness checks; step 6 keep only if reproducible and no contract regresses), but the error-recovery feedback loop on validation failure is implicit rather than an explicit 'fix and retry'.	4 / 5
Progressive Disclosure	A well-organized single-purpose skill under 50 lines with one clear heading and a structured list, needing no external references; per the simple-skill exception this scores 5.	5 / 5
	Total	18 / 20 Passed

Description

66%Weight 40%Scale 1-5

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 several concrete actions with a clearly scoped domain, but it omits any explicit 'when to use' trigger guidance, which caps completeness at 3 and slightly weakens distinctiveness. Adding a 'Use when...' clause would lift the two weaker dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to speed up Fallow, reduce latency, or improve benchmark results.'

Add natural synonyms users might say ('slow', 'latency', 'speed up', 'throughput') to broaden trigger coverage toward 5.

Optionally name the benchmark/correctness artifacts (e.g. a specific benchmark suite) to sharpen specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists several concrete methodological actions — 'stable benchmarks', 'before-and-after evidence', 'correctness gates' — alongside the core 'optimize Fallow performance', matching the 'lists several specific actions; minor gaps' anchor.	4 / 5
Completeness	The 'what' is clear (iteratively optimize Fallow performance with named methods) but there is no 'Use when...' or equivalent explicit trigger guidance, so per the rubric cap completeness stays at 3.	3 / 5
Trigger Term Quality	Contains natural phrases a user would say ('optimize ... performance', 'benchmarks', 'before-and-after evidence') with good coverage, but lacks synonyms or explicit trigger variations, so it falls just below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The Fallow-specific scope and concrete methodology give it a distinct niche with minimal conflict risk, though the absence of explicit trigger guidance leaves minor overlap risk with general performance skills.	4 / 5
	Total	15 / 20 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: .claude/skills/perf-loop/SKILL.md
Commit: 7e1e075

Reviewed: 3 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.