CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

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

86%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 tight, highly actionable workflow with concrete CLI commands, explicit guardrails, and a clear stopping point. Its only weaknesses are a thrice-repeated schema instruction and the absence of validation steps for command outcomes, which keep conciseness and workflow clarity just below top marks.

DimensionReasoningScore

Conciseness

The body is lean and free of concept explanations, but the schema rule is stated three times (step 2, step 3's "Add --schema <name> only if...", and the guardrail "Pass --schema if using a non-default workflow"). These repeated minor instances could be trimmed, matching the efficient-with-minor-overlap anchor of 4 rather than the every-token-earns-its-place 5.

4 / 5

Actionability

The skill gives copy-paste-ready commands (`openspec new change "<name>"`, `openspec status --change "<name>"`, `openspec instructions <first-artifact-id> --change "<name>"`, `openspec schemas --json`) plus exact AskUserQuestion wording, and explains how to derive the one placeholder from status output. This is fully executable instruction-only guidance covering the common cases, matching the 5 anchor rather than the minor-gaps 4.

5 / 5

Workflow Clarity

Steps 1-6 are clearly sequenced with a STOP checkpoint and guardrails for error conditions (invalid name, existing change), but there are no checks on command outcomes (e.g., what to do if `openspec new change` fails or status output is unexpected). This fits the clear-sequence-with-minor-validation-gaps anchor of 4; the 5 would require explicit validate-and-retry loops.

4 / 5

Progressive Disclosure

The skill is a short, single-purpose workflow with no bundle files and no need for external references, yet is organized into clear Input, Steps, Output, and Guardrails sections. Under the simple-skill guideline this well-organized structure earns the top score.

5 / 5

Total

18

/

20

Passed

Description

67%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.

The description cleanly answers both 'what' and 'when' with an explicit trigger clause, but it names only one concrete action and its trigger phrasing is broad enough to risk overlap with generic feature/fix skills. Adding more action verbs and OpenSpec-specific trigger terms would sharpen it.

Suggestions

List 2-3 concrete actions the skill performs (e.g., scaffolds the change directory, checks artifact status, fetches the first artifact template) to raise specificity.

Add natural trigger synonyms such as 'add', 'implement', 'OpenSpec change', or 'spec change' so users phrasing the request differently still hit the skill.

Scope the 'when' clause to OpenSpec contexts (e.g., 'Use when starting a new OpenSpec change...') to reduce overlap with general feature/fix workflows.

DimensionReasoningScore

Specificity

"Start a new OpenSpec change using the experimental artifact workflow" names the domain and one concrete action (starting a change), but lists no further actions (e.g., scaffolding, showing artifact status, fetching instructions). This matches the anchor for naming a domain with 1-2 concrete actions without comprehensive coverage; a 4 would require several specific actions listed.

3 / 5

Completeness

The description 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 with a structured step-by-step approach") with concrete trigger phrases. This clearly matches the top anchor rather than the 4, whose 'when' would be less explicit.

5 / 5

Trigger Term Quality

Trigger phrases like "create a new feature, fix, or modification" are natural, but common variations and synonyms are missing (e.g., "add", "implement", "openspec change", "spec", "proposal"). Coverage is partial rather than the 'good keyword coverage with a few missing' of a 4.

3 / 5

Distinctiveness Conflict Risk

The 'what' carves out a clear OpenSpec niche, but the 'when' clause ("wants to create a new feature, fix, or modification") is broad enough to overlap with general feature-development or fix workflows outside OpenSpec. It is somewhat specific yet could still collide with similar skills, fitting the 3 anchor better than the minor-overlap 4.

3 / 5

Total

14

/

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

TencentBlueKing/bk-bcs

Path

bcs-runtime/bcs-k8s/bcs-component/bcs-drplan-controller/.claude/skills/openspec-new-change/SKILL.md

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.