axiom-optimize-build

Use when the user mentions slow builds, build performance, or build time optimization.

Quality

61%

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 ./axiom-codex/skills/axiom-optimize-build/SKILL.md

Quality

Content

62%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 skill is highly actionable, with concrete grep/xcodebuild commands and explicit good/bad fixes, but it is a monolithic document with duplicated scan instructions and no validation/feedback loop for the destructive remediation steps it implies. Tightening the repetition and adding a measure-before/after verification step would raise both conciseness and workflow clarity.

Suggestions

Merge the duplicated 'What You Check' and 'Scan Process' sections so each grep/Glob pattern appears once, cutting repetition and tokens.

Add an explicit validation feedback loop: measure build time before changes, apply a fix, rebuild, and re-measure to confirm the win before moving on.

Move the full build-settings catalog and Build Timeline walkthrough into reference files (e.g. SETTINGS.md, TIMELINE.md) and link them from the body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and mostly tells Claude what to check rather than explaining concepts, but sections repeat the same grep patterns and Glob steps in both 'What You Check' and 'Scan Process', and impact labels are restated, so it could be tightened, matching the 'mostly efficient but some unnecessary explanation or could be tightened' anchor.	3 / 5
Actionability	It provides concrete, executable grep and xcodebuild commands with exact setting names and expected values, plus a copy-paste-ready good/bad build-phase fix, covering the common cases fully executable as written.	5 / 5
Workflow Clarity	The Scan Process is a numbered five-step sequence, but it is read-only scanning with no validation checkpoints, and the remediation side (applying build-setting or script changes) is a batch/destructive operation with no verify-before/after or rollback step, so per the destructive-operation cap it cannot exceed 3.	3 / 5
Progressive Disclosure	No bundle files exist and the body is a single monolithic document; the content is organized into sections but material that could be split (full setting catalogs, timeline walkthrough, output format) is inlined with no one-level-deep references, matching 'some structure but could be better organized; content that should be separate is inline'.	3 / 5
	Total	14 / 20 Passed

Description

61%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 cleanly pairs a clear trigger ('Use when the user mentions slow builds...') with a clear domain, giving strong what/when completeness and low conflict risk. Its main weakness is specificity, since it states the goal rather than the concrete actions the skill performs.

Suggestions

Name concrete actions the skill performs, e.g. 'Scans Xcode build settings, build phase scripts, and Swift compiler flags to find quick wins that reduce build time'.

Add natural synonyms and specifics users actually say, such as 'Xcode build time', 'incremental builds', or 'clean build is slow'.

Optionally reference the target scope (Xcode/Swift) in the description so it is unmistakably distinct from generic build-tooling skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('build performance'/'build time optimization') but states only the general action of optimizing builds, listing no concrete actions like which settings to check or fixes to apply, fitting the anchor that names the domain with minimal/generic actions rather than the 4-anchor's 'several specific actions'.	3 / 5
Completeness	It has a clear 'Use when...' clause giving the trigger conditions and a clear 'what' (optimizing build time), satisfying both what and when, though the 'what' is generic ('build time optimization') and could be more explicit about what the skill actually does.	4 / 5
Trigger Term Quality	It captures 'slow builds', 'build performance', and 'build time optimization', which are relevant phrases a user might say, but it lacks common synonyms and file/scheme references (e.g. Xcode, Swift, incremental builds, clean build times), matching the anchor with some relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	'Build performance'/'build time optimization' is a fairly distinct niche unlikely to collide with unrelated skills, with only minor overlap risk against general performance or tooling skills, matching the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	14 / 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: CharlesWiltgen/Axiom
Path: axiom-codex/skills/axiom-optimize-build/SKILL.md
Commit: 69ffef6

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.