openspec-continue-change

Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.

Quality

95%

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

100%

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 concise, actionable workflow with concrete CLI commands, explicit JSON field handling, a clear sequenced branching flow, and a verification checkpoint. It respects Claude's competence and is well-organized with no redundant external references.

Dimension	Reasoning	Score
Conciseness	The body is lean and instructional, assuming Claude's competence without explaining what OpenSpec or artifacts are; the only repetition is a deliberate guardrail reiteration about context/rules being constraints, which earns its place rather than padding. There is no unnecessary concept explanation or filler that could be trimmed without loss.	3 / 3
Actionability	It provides fully executable commands (openspec list/status/instructions with --json) and enumerates the exact JSON fields to parse and act on, giving copy-paste-ready guidance; above level 2 which expects pseudocode or missing details.	3 / 3
Workflow Clarity	Steps 1-4 are clearly sequenced with status-based branching and an explicit verification checkpoint ('Verify the artifact file exists after writing before marking progress'); the one-artifact-per-invocation guardrail limits batch/destructive risk, satisfying the feedback-loop expectation. Validation is explicit and the sequence has checkpoints rather than gaps.	3 / 3
Progressive Disclosure	Content is organized into clear, navigable sections (Input, Steps, Output, Artifact Creation Guidelines, Guardrails) with no nested references; no bundle files exist, and for this self-contained CLI-orchestration skill inline organization is appropriate. There is no monolithic wall of text or content that should be split out into separate files.	3 / 3
	Total	12 / 12 Passed

Description

90%

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 clear, uses third person, and supplies an explicit trigger clause answering both what and when. Its main weakness is specificity: it names a single core action rather than enumerating the concrete operations the skill performs.

Suggestions

Enumerate the concrete actions the skill performs (e.g., listing changes, checking status, fetching artifact instructions, and writing the next artifact file) to raise specificity from a single named action to a list.

Add a couple more natural trigger variations users might say (e.g., 'pick up where I left off', 'show my open changes') to broaden trigger-term coverage.

Optionally note the required 'openspec CLI' dependency in the description so the trigger context signals the tooling constraint up front.

Dimension	Reasoning	Score
Specificity	Names the domain ('OpenSpec change') and one core action ('creating the next artifact') but does not list multiple distinct concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.	2 / 3
Completeness	It states what the skill does ('Continue working on a change by creating the next artifact') and an explicit 'Use when...' clause answering when to invoke it, satisfying both halves; not level 2 because the trigger is explicit rather than implied.	3 / 3
Trigger Term Quality	Phrases like 'progress their change', 'create the next artifact', and 'continue their workflow' are natural terms a user would say, giving good coverage; it is above level 2 which expects only some relevant keywords with missing variations.	3 / 3
Distinctiveness Conflict Risk	The 'OpenSpec change' / 'next artifact' niche is specific with distinct triggers and is unlikely to fire for unrelated skills; above level 2 because it is not merely a generic document/file scope.	3 / 3
	Total	11 / 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-continue-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.