axiom-performance

Use when app feels slow, memory grows, battery drains, or diagnosing ANY performance issue. Covers memory leaks, profiling, Instruments workflows, retain cycles, performance optimization.

Quality

85%

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

Quality

Content

70%

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

A well-structured routing skill with excellent progressive disclosure and a clear decision tree, but it loses conciseness to a redundant Anti-Rationalization table and overlapping Example Invocations, and offers no inline executable code by design.

Suggestions

Trim or remove the 21-row Anti-Rationalization table; the Decision Tree already routes these cases, and restating self-defeating thoughts is largely inferable padding.

Cut the Example Invocations section (60+ lines) since it duplicates Decision Tree routing; keep at most 3-4 representative examples if any.

For the highest-leverage workflows (e.g. memory-auditor, /axiom:profile), include one inline command or invocation so the skill is actionable without always deferring to a referenced file.

Dimension	Reasoning	Score
Conciseness	The body is a large routing index that largely earns its tokens, but the 21-row Anti-Rationalization table restates common-sense objections at length, and routing entries plus a 60+ line Example Invocations section substantially duplicate the Decision Tree, adding padding Claude could infer.	2 / 3
Actionability	It points to specific files, agents, and slash commands, but as a router it offers no executable code/commands inline; guidance is 'See skills/X.md' / 'Launch agent' rather than copy-paste-ready instructions, fitting the 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	The Decision Tree provides a clearly sequenced, branching diagnostic flow (memory first then profiling; busy vs blocked hang triage) with explicit routing on conditions, giving a strong feedback-style routing workflow appropriate to a router skill.	3 / 3
Progressive Disclosure	The SKILL.md is an overview that one-level-deep references out to specialized skills (memory-debugging.md, performance-profiling.md, energy.md, etc.) and auditor agents, with clearly signaled navigation and no nested reference chains.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description with explicit triggers and concrete capability list; it cleanly answers both what and when and is highly distinct.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete capabilities (memory leaks, profiling, Instruments workflows, retain cycles, performance optimization) rather than vague actions, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It explicitly answers both 'what' (memory leaks, profiling, Instruments workflows, retain cycles, performance optimization) and 'when' via the 'Use when app feels slow, memory grows, battery drains, or diagnosing ANY performance issue' clause.	3 / 3
Trigger Term Quality	It surfaces natural user-facing phrases ('app feels slow', 'memory grows', 'battery drains') plus technical terms users would say, giving good coverage of how a user would describe these problems.	3 / 3
Distinctiveness Conflict Risk	It carves a clear iOS/macOS performance niche (Instruments, retain cycles, ARC) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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-performance/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.