axiom-fix-build

Use when the user mentions Xcode build failures, build errors, or environment issues.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./axiom-codex/skills/axiom-fix-build/SKILL.md

Quality

Content

77%

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

The body is highly actionable with a clear, well-validated workflow, but it is monolithic and somewhat redundant, repeating the structured-error-capture recipe and keeping inline content that could be offloaded to reference files.

Suggestions

Move the CI/CD simulator-runtime download block and the error-pattern table into a reference file (e.g. references/ci-cd.md) and link to it, reducing inline length.

State the structured-error-capture recipe once in 'Running Builds' and reference it by section from section 2, the CI/CD block, and the Audit Guidelines instead of restating it.

Tighten the restated environment-check rationale to remove duplicated guidance between 'Mandatory First Steps' and 'Interpreting Results'.

Dimension	Reasoning	Score
Conciseness	Most content is genuinely additive (specific xcodebuild flags, xcresulttool recipes, MCP-server subtleties), but the structured-error-capture guidance is restated across 'Running Builds', section 2, the CI/CD section, and the Audit Guidelines, and the CI/CD runtime-download block could be trimmed.	2 / 3
Actionability	Commands are concrete and largely copy-paste ready (killall -9 xcodebuild, rm -rf DerivedData, xcodebuild -resolvePackageDependencies, simctl erase), with placeholders like <ACTUAL_SCHEME_NAME> explicitly justified by instructing xcodebuild -list lookup.	3 / 3
Workflow Clarity	Clear sequencing via mandatory first steps, a symptom-to-section decision tree, and rebuild/retest verification checkpoints with feedback loops (read errors, fix, rebuild, re-read), plus a 'When to Stop and Report' escalation path.	3 / 3
Progressive Disclosure	There are no bundle files and all content is inline in a ~455-line SKILL.md; well-organized into sections, but content that could be split out (CI/CD runtime download, error pattern table) is inline with no one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

72%

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 has clear, natural trigger terms and a distinct niche, but it omits the skill's concrete actions and its 'what', making the completeness and specificity weaker.

Suggestions

Add the concrete actions the skill performs, e.g. 'Diagnose and fix Xcode build failures by checking the environment, killing zombie processes, clearing Derived Data, and re-running builds'.

Combine what and when into one sentence so both are explicit, e.g. 'Diagnose and fix Xcode build failures via environment-first cleanup. Use when the user mentions build failures, build errors, or environment issues.'

Dimension	Reasoning	Score
Specificity	The description names the Xcode build domain and trigger categories ('Xcode build failures, build errors, or environment issues') but lists no concrete actions the skill performs, so it falls short of the 'multiple specific concrete actions' anchor.	2 / 3
Completeness	It provides an explicit 'Use when...' trigger but never states what the skill does (diagnose/fix), leaving the 'what' missing rather than fully answered.	2 / 3
Trigger Term Quality	'Xcode build failures, build errors, or environment issues' are natural phrases a user would actually say, giving good coverage of likely trigger terms.	3 / 3
Distinctiveness Conflict Risk	The Xcode-build niche with explicit triggers is clearly distinct from other skills and unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 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: CharlesWiltgen/Axiom
Path: axiom-codex/skills/axiom-fix-build/SKILL.md
Commit: ea3be7c

Reviewed: 1 day 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.