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

80%

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 ./eval/local/skills/benchmarks/dependency/openspec/openspec-new-change/SKILL.md

Quality

Content

85%

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

A tightly organized, actionable workflow skill with a clear sequence and explicit checkpoints. Its only real weakness is minor repetition of the --schema guidance.

Suggestions

Consolidate the --schema decision into one place (step 2) and reference it rather than restating it in step 3 and guardrails.

Shorten the quoted AskUserQuestion prompt to a brief instruction since Claude can phrase the question itself.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with concrete commands, but the --schema guidance is restated across step 2, step 3, and guardrails, and the quoted AskUserQuestion prompt adds mild redundancy that could be tightened.	2 / 3
Actionability	Provides fully executable commands (openspec new/status/instructions) with exact flags and specifies the AskUserQuestion tool usage, giving copy-paste-ready guidance.	3 / 3
Workflow Clarity	A clear 6-step sequence with an explicit STOP, a status-check checkpoint before fetching instructions, and guardrails covering invalid names and pre-existing changes for error recovery.	3 / 3
Progressive Disclosure	A self-contained, well-organized skill (Input/Steps/Output/Guardrails) with no bundle files and no need for external references, satisfying the simple-skill allowance.	3 / 3
	Total	11 / 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, well-triggered description that answers both what and when for an OpenSpec-specific task. It is slightly weak on action specificity and trigger-term breadth.

Suggestions

List 2-3 concrete actions the skill performs (e.g., scaffold a change, inspect artifact status, fetch artifact instructions) to raise specificity.

Broaden trigger terms with common phrasings like "new change", "start a change", or "OpenSpec proposal" for fuller coverage.

Dimension	Reasoning	Score
Specificity	Names the core action ("Start a new OpenSpec change") and change types (feature/fix/modification), but does not list multiple distinct concrete actions like the score-3 anchor requires.	2 / 3
Completeness	Explicitly states what ("Start a new OpenSpec change using the experimental artifact workflow") and when ("Use when the user wants to create a new feature, fix, or modification").	3 / 3
Trigger Term Quality	"new feature, fix, or modification" are reasonably natural user terms, but coverage is narrow and tied to OpenSpec jargon ("artifact workflow") without common variations.	2 / 3
Distinctiveness Conflict Risk	Scoped to OpenSpec change creation with a distinct trigger set, making it unlikely to fire 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: rpamis/comet
Path: eval/local/skills/benchmarks/dependency/openspec/openspec-new-change/SKILL.md
Commit: 2945693

Reviewed: about 9 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.