axiom-fix-build

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

Quality

62%

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-fix-build/SKILL.md

Quality

Content

77%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 highly actionable with executable commands, explicit validation, and clear feedback loops for destructive operations. Its weaknesses are conciseness (restated workflows and a verbose CI/CD section) and progressive disclosure (a large monolithic file with no reference splits).

Suggestions

Move the CI/CD simulator-runtime download command catalog and the Error Pattern Recognition table into separate reference files linked from the body to improve progressive disclosure and trim the main file.

Collapse the Audit Guidelines section or fold it into the Decision Tree, since both restate the workflow steps already covered in 'Fix Workflows'.

Tighten the CI/CD runtime-download block to the one or two commands actually used in diagnosis, keeping variants in a reference.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the ~460 lines contain notable redundancy — the Audit Guidelines and Decision Tree restate the workflows, and the CI/CD simulator-runtime download section lists many command variants. It is not a 4 because several sections could be materially tightened without losing clarity.	3 / 5
Actionability	The guide is packed with concrete, executable bash commands (ps, du, xcrun simctl, xcodebuild with resultBundlePath, xcresulttool) covering the common cases. Placeholders like <ACTUAL_SCHEME_NAME> are explicitly justified with a recipe (xcodebuild -list), so they are not penalized.	5 / 5
Workflow Clarity	Sequencing is explicit (mandatory checks → identify → fix → verify → report) with validation checkpoints and a fix→rebuild→re-read feedback loop; destructive ops are followed by verification. It is not a 4 because checklists (Audit Guidelines, mandatory checks) and error-recovery loops are all present.	5 / 5
Progressive Disclosure	Section headers and internal cross-references (§1–§6) give good structure, but the skill is a monolithic ~460-line file with no bundle files, and chunks like the CI/CD runtime-download commands and the error-pattern table could live in separate references. It is not a 4 because content that should be split out is fully inline and no external references exist despite the size.	3 / 5
	Total	16 / 20 Passed

Description

47%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 a clear trigger clause but omits the 'what' — it never states what the skill does (e.g., diagnoses and fixes Xcode build failures). Trigger terms are natural and the niche is fairly distinct, but the missing action/capability statement limits completeness and specificity.

Suggestions

Lead with the 'what' before the 'when', e.g., 'Diagnoses and fixes Xcode build failures using environment-first diagnostics. Use when the user mentions Xcode build failures, build errors, or environment issues.'

Add concrete capability verbs (cleans Derived Data, kills zombie xcodebuild processes, resolves SPM cache issues) so the description answers 'what does this do'.

Replace the generic 'environment issues' with Xcode-specific synonyms like 'compile errors' or 'linking errors' to sharpen distinctiveness and trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Xcode build failures, build errors, or environment issues") but lists no concrete actions, mirroring the anchor 'Names the domain but actions are minimal or generic'. It is below a 3 because it offers zero actions, only a trigger phrase.	2 / 5
Completeness	A clear 'when' is present ("Use when the user mentions...") but no 'what' describes what the skill does, matching the anchor 'only when is present without what'. It is not a 3 because that anchor requires a clear 'what', which is absent here.	2 / 5
Trigger Term Quality	Phrases like "Xcode build failures", "build errors", and "environment issues" are natural terms users would say, giving good keyword coverage. It is not a 5 because synonyms like 'compile errors', 'won't build', or 'linking errors' are missing.	4 / 5
Distinctiveness Conflict Risk	The Xcode build-failure niche is mostly distinct with clear triggers, but the generic tail "environment issues" creates minor overlap risk with related dev-environment skills. It is not a 5 because of that residual overlap risk.	4 / 5
	Total	12 / 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-fix-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.