openspec-new-change

Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.

Quality

87%

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

100%

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

A tight, actionable, well-sequenced workflow with concrete CLI commands and explicit checkpoints, appropriately self-contained for a single-purpose skill.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven, assumes Claude's competence, and avoids explaining concepts Claude already knows; every section (Input, Steps, Output, Guardrails) earns its place.	3 / 3
Actionability	Provides concrete, executable commands (openspec new change, openspec status --change, openspec instructions) with placeholders only where the value is inherently conditional on prior output.	3 / 3
Workflow Clarity	A clearly numbered six-step sequence with explicit checkpoints (status output, a STOP-and-wait step) and guardrails that handle error cases (invalid name, existing change, schema selection).	3 / 3
Progressive Disclosure	No external references are needed for this self-contained single-purpose workflow, and the content is well-organized into clearly labeled sections, satisfying the simple-skill allowance.	3 / 3
	Total	12 / 12 Passed

Description

75%

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 clear, third-person description with an explicit trigger clause and a distinct niche, though its action list and natural-term coverage are somewhat narrow.

Suggestions

Broaden trigger terms to include common user variations like 'start a change', 'propose a feature', or 'scaffold a spec' alongside 'create a new feature, fix, or modification'.

List one or two more concrete actions (e.g., 'scaffold the change directory and surface the first artifact template') to lift specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	Names the domain and a single concrete action ('Start a new OpenSpec change using the experimental artifact workflow') but does not enumerate multiple specific actions, so it stops short of the comprehensive anchor.	2 / 3
Completeness	Explicitly states what it does and provides a 'Use when the user wants to create...' trigger clause, satisfying both the what and the when.	3 / 3
Trigger Term Quality	Includes natural phrasings ('create a new feature, fix, or modification') but covers limited variations and leans on the technical 'OpenSpec change' term rather than a broad set of user utterances.	2 / 3
Distinctiveness Conflict Risk	The OpenSpec/artifact-workflow niche is specific and tied to a distinct CLI, making it unlikely to trigger for unrelated skills.	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: Draculabo/AntigravityManager
Path: .agent/skills/openspec-new-change/SKILL.md
Commit: de8d68d

Reviewed: about 12 hours 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.