Name: arn-spark-spike
Rating: 71.2 (1 reviews)
Author: AppsVortex

arn-spark-spike

This skill should be used when the user says "spike", "arn spike", "validate risks", "technical validation", "proof of concept", "validate architecture", "risk spike", "test this risk", "will this work", "technical spike", "validate the stack", or wants to validate critical technical risks from the architecture vision by creating minimal proof-of-concept code and testing whether the chosen technologies work as expected.

Quality

87%

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

Quality

Content

85%Weight 40%Scale 1-3

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-structured, actionable multi-step workflow with strong sequencing, validation checkpoints, and appropriate use of a single offloaded reference template. The main weakness is repetition of the CLAUDE.md configuration-lookup boilerplate, which inflates token usage without adding clarity.

Suggestions

Extract the repeated 'read CLAUDE.md / check for a ## Arness section / extract configured directory' lookup into a single referenced helper or a once-stated convention referenced by each step, instead of restating it in Prerequisites, Step 3, and Step 4.

Condense the verbatim dialogue templates (e.g., the risk-list and results-summary blocks) to structural skeletons, trusting Claude to phrase the surrounding prose.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and does not explain concepts Claude already knows, but the 'read CLAUDE.md and check for a ## Arness section' lookup is repeated verbatim across Prerequisites, Step 3, and Step 4, and the templated dialogue could be tightened.	2 / 3
Actionability	Highly actionable for an orchestration skill: concrete agent name ('arn-spark-spike-runner' via Task tool, foreground), specific paths (spike workspace, ${CLAUDE_PLUGIN_ROOT}/.../spike-report-template.md), explicit AskUserQuestion usage with multiSelect, and copy-paste-ready dialogue templates.	3 / 3
Workflow Clarity	Six clearly sequenced steps with explicit validation checkpoints ('Wait for user approval', 'Wait for the agent to complete fully') and feedback loops for failures (accept/alternative/update-vision), plus a dedicated sequential-execution warning and an Error Handling section.	3 / 3
Progressive Disclosure	Well-organized into overview, numbered workflow steps, agent invocation guide, and error handling; the heavy report template is offloaded to a real one-level-deep reference (references/spike-report-template.md) that is clearly signaled via an explicit Read command.	3 / 3
	Total	11 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 gives explicit trigger phrases, states both what the skill does and when to use it, and occupies a distinctive niche. Its only weakness is that the action list is somewhat high-level rather than a comprehensive enumeration of concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain (technical risk validation) and concrete actions ('creating minimal proof-of-concept code and testing whether the chosen technologies work as expected'), but stops at two relatively high-level actions rather than enumerating multiple specific operations.	2 / 3
Completeness	Explicitly answers both what ('validate critical technical risks ... by creating minimal proof-of-concept code and testing whether the chosen technologies work') and when ('should be used when the user says ... or wants to validate ...'), with explicit triggers.	3 / 3
Trigger Term Quality	Strong coverage of natural trigger phrases a user would actually say — 'spike', 'arn spike', 'validate risks', 'technical validation', 'proof of concept', 'will this work', 'validate the stack' — matching the top anchor for natural-term coverage.	3 / 3
Distinctiveness Conflict Risk	Clear niche (technical-risk POC validation) with distinctive, namespaced triggers ('arn spike', 'risk spike', 'validate the stack') unlikely to collide with other skills.	3 / 3
	Total	11 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: AppsVortex/arness
Path: plugins/arn-spark/skills/arn-spark-spike/SKILL.md
Commit: 7f87870

Reviewed: 14 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.