CtrlK
BlogDocsLog inGet started
Tessl Logo

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. Also use when the user says "openspec new change" or "opsx new".

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

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 highly actionable, well-sequenced workflow with genuine validation checkpoints and error-recovery branches, all backed by copy-paste-ready commands. Its main weakness is the dense, clause-heavy prose in the store-selection and project-check sections and redundant --schema guidance, which cost token efficiency without adding clarity.

Suggestions

Rewrite the store-selection paragraph as a short bullet list (discover ids, which commands take --store, stickiness rule) — the current nested-clause prose is the single densest block in the file.

State the --schema rule once (in step 2 or step 3) and drop its repetition in the other step and in Guardrails.

Consider splitting the project-check error-triage cases (root null vs. "Declared in" store-resolution errors) into a compact two-row decision list so the branch conditions are scannable at a glance.

DimensionReasoningScore

Conciseness

Mostly efficient — the content is non-obvious CLI semantics Claude cannot infer — but the store-selection paragraph is a dense block of nested clauses that could be tightened into bullets, and the --schema guidance is repeated three times (step 2, step 3, and Guardrails). Fits anchor 3 (could be tightened) rather than 2, since there is no padding about concepts Claude already knows.

3 / 5

Actionability

Every step ships a copy-paste-ready command (openspec list --json, openspec new change "<name>", openspec status --change "<name>" --json, openspec instructions <first-artifact-id> --change "<name>") with the exact JSON fields to read (root, planningHome, changeRoot, artifactPaths, nextSteps) and an exact ask-the-user prompt. Fully executable with placeholders covering the common cases.

5 / 5

Workflow Clarity

Clear numbered sequence with an explicit pre-write validation checkpoint (run openspec list --json and read root before any write), detailed error-recovery branches (root null vs. the "Declared in"/"Invalid store declaration" case, auto-selected vs. explicit-request handling), and a hard STOP step with guardrails. Matches the anchor-5 pattern of explicit validation with feedback loops.

5 / 5

Progressive Disclosure

No bundle files exist and the ~75-line body is organized into clearly labeled sections (Store selection, Project check, Input, Steps, Output, Guardrails) with no nested references. Falls short of 5 only because the two long prose sections (store selection and project check) are dense reference-style material that could be restructured into bullets or split into separate sections.

4 / 5

Total

17

/

20

Passed

Description

82%Weight 40%Scale 1-5

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 description that clearly states both what the skill does and when to use it, with explicit third-person trigger phrases including the exact CLI invocations. Its only weakness is thin action coverage — it names the single top-level action rather than enumerating what the workflow actually does.

Suggestions

Enumerate 2-3 more concrete actions in the description (e.g., scaffolds the change directory, shows artifact status, fetches instructions for the first artifact) to lift specificity beyond a single action.

Add one or two natural trigger variants such as "start a change" or "create a change" so users who paraphrase rather than quoting the CLI command still match.

DimensionReasoningScore

Specificity

Names the domain and one concrete action ("Start a new OpenSpec change using the experimental artifact workflow") but does not list several specific actions like scaffolding the change, showing artifact status, or fetching artifact instructions. Fits anchor 3 (domain plus 1-2 concrete actions), not anchor 4 which requires several listed actions.

3 / 5

Completeness

Explicitly answers both 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..." plus concrete trigger phrases "openspec new change" / "opsx new"), matching the anchor-5 pattern.

5 / 5

Trigger Term Quality

Includes exact command phrases users would say ("openspec new change", "opsx new") plus natural terms ("new feature, fix, or modification"), giving good keyword coverage. Falls short of anchor 5 because common variants like "start a change", "create a change", or "openspec change" are missing.

4 / 5

Distinctiveness Conflict Risk

"OpenSpec" plus the specific CLI command triggers carve a clear niche with minimal conflict risk; other skills would not naturally trigger on these phrases. Only negligible overlap with hypothetical sibling openspec workflow skills.

5 / 5

Total

17

/

20

Passed

Validation

100%

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
Fission-AI/OpenSpec
Reviewed

Table of Contents

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.