axiom-build

Use when ANY iOS build fails, test crashes, Xcode misbehaves, or environment issue occurs before debugging code. Covers build failures, compilation errors, dependency conflicts, simulator problems, environment-first diagnostics.

Quality

77%

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 ./.claude-plugin/plugins/axiom/skills/axiom-build/SKILL.md

Quality

Content

67%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 well-organized, highly actionable router with clear triggers, a decision tree, and useful anti-rationalization/conflict-resolution guardrails. Its main weakness is redundancy — the routing table is repeated three times, most heavily in a long Example Invocations section — and its references are external cross-suite files rather than bundled materials.

Suggestions

Remove or drastically condense the Example Invocations section: its ~50 user prompts duplicate the Routing Logic and Decision Tree triggers, which already make the routing unambiguous.

Consolidate the Routing Logic and Decision Tree into a single quick-reference table to avoid restating the same 16 routes twice.

Clarify cross-suite references (e.g., "See axiom-shipping (skills/testflight-triage.md)") with consistent, resolvable paths so the invoke targets are unambiguous.

Dimension	Reasoning	Score
Conciseness	Individual routing entries are tight and avoid explaining concepts Claude already knows, but the same 16 routes are restated three times (Routing Logic, Decision Tree, and a ~115-line Example Invocations block), which is significant redundancy that could be trimmed.	3 / 5
Actionability	Each route gives a concrete, executable next step — `skills/xcode-debugging.md`, `Launch build-fixer agent`, `/axiom:console` — with minor gaps where entries point vaguely to "See axiom-shipping (skills/...)" cross-suite references.	4 / 5
Workflow Clarity	A numbered 16-step Decision Tree gives a clear routing sequence, and Anti-Rationalization plus When-NOT-to-Use tables act as conflict-resolution guardrails; this is a lookup router rather than a multi-step process with feedback loops, so it stops short of the explicit validate/retry pattern.	4 / 5
Progressive Disclosure	Well-structured as an overview router with one-level-deep, clearly signaled references ("Invoke: skills/X.md"), but no bundle files exist in references/scripts/assets and several targets are external cross-suite pointers that cannot be verified from this skill's bundle.	4 / 5
	Total	15 / 20 Passed

Description

87%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 strong: it explicitly states both what the skill covers and when to use it, with natural trigger phrasing and a clearly distinct iOS build/environment niche. Minor specificity gaps (problem categories vs. actions, a few omitted sub-topics) keep it just short of perfect.

Dimension	Reasoning	Score
Specificity	Lists several concrete issue categories — "build failures, compilation errors, dependency conflicts, simulator problems, environment-first diagnostics" — giving specific coverage rather than vague language, though these are problem types rather than named actions and a few body-covered cases (signing, TestFlight) are omitted.	4 / 5
Completeness	Explicitly answers both what ("Covers build failures, compilation errors, dependency conflicts, simulator problems, environment-first diagnostics") and when ("Use when ANY iOS build fails, test crashes, Xcode misbehaves, or environment issue occurs before debugging code") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say — "build fails", "test crashes", "Xcode misbehaves", "environment issue" — with good coverage, though a few common synonyms/extensions are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — iOS/Xcode build and environment-first diagnostics before debugging code — with distinct triggers and minimal overlap risk against code-logic skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: CharlesWiltgen/Axiom
Path: .claude-plugin/plugins/axiom/skills/axiom-build/SKILL.md
Commit: 4ae86a3

Reviewed: 5 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.