CtrlK
BlogDocsLog inGet started
Tessl Logo

056-design-avoid-breaking-changes

Use when you need to review a plan, OpenSpec change, specification, or implementation proposal for breaking-change risk across commands, skills, generated outputs, XML sources, README/docs, tests, CI, APIs, schemas, configuration, data, migration, and release guidance. This should trigger for requests such as Review breaking changes in this spec; Check compatibility risks; Avoid breaking changes in this OpenSpec change; Review migration impact before release; Assess command and skill compatibility. Part of Plinth Toolkit

68

Quality

82%

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

78%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.

A well-structured, lean instruction-only skill with a clear sequenced workflow, concrete classification taxonomy, and exemplary progressive disclosure through a single one-level-deep reference. Adding a worked example finding and an explicit verification checkpoint would lift the borderline-4 dimensions.

Suggestions

Add a short worked example of a classified finding (e.g., a renamed command mapped to BREAKING with affected users, artifact, and recommended deprecation window) to lift actionability from 4 to 5.

Insert an explicit verification checkpoint between classification and reporting, such as 'Before reporting, confirm each finding has affected users, artifacts, contracts, and validation evidence', to make workflow_clarity validation explicit.

Trim the 'What is covered in this Skill?' bullet list where it duplicates surfaces already enumerated in the frontmatter description, to tighten conciseness toward 5.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence without over-explaining concepts; the 'What is covered' bullet list partially overlaps the frontmatter description and could be trimmed slightly, keeping it just below 5.

4 / 5

Actionability

Concrete, actionable methodology with an explicit classification taxonomy (BREAKING, POTENTIALLY BREAKING, NON-BREAKING, UNKNOWN) and required report fields (affected users, artifacts, contracts, validation evidence); the absence of a worked example of an actual finding is the minor gap versus 5.

4 / 5

Workflow Clarity

Five clearly numbered, well-sequenced steps (read reference, inventory surfaces, classify, recommend migration/validation, report); the workflow is read-only so the destructive/batch validation cap does not apply, but validation checkpoints between classification and reporting are implicit rather than explicit.

4 / 5

Progressive Disclosure

Clear overview in SKILL.md with a single well-signaled one-level-deep reference (references/056-design-avoid-breaking-changes.md, verified to exist at 225 lines) mentioned both in the Constraints and a dedicated Reference section; content is appropriately split.

5 / 5

Total

17

/

20

Passed

Description

86%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, comprehensive description with explicit 'what' and 'when' guidance and natural trigger phrases. The only notable issue is second-person voice ('you need to review'), which triggers a one-point specificity penalty under the rubric.

DimensionReasoningScore

Specificity

Enumerates a comprehensive set of compatibility surfaces (commands, skills, generated outputs, XML sources, README/docs, tests, CI, APIs, schemas, configuration, data, migration, release guidance) and concrete trigger actions (Review, Check, Avoid, Assess), which would warrant a 4, but reduced by 1 per the second-person voice penalty since the description opens 'Use when you need to review...'.

3 / 5

Completeness

Clearly answers both 'what' (review plans, OpenSpec changes, specs, or implementation proposals for breaking-change risk across enumerated surfaces) and 'when' ('Use when you need to review...', 'This should trigger for requests such as...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Explicit natural trigger phrases a user would say ('Review breaking changes in this spec', 'Check compatibility risks', 'Avoid breaking changes in this OpenSpec change', 'Review migration impact before release', 'Assess command and skill compatibility') with synonym coverage across review/check/assess/avoid.

5 / 5

Distinctiveness Conflict Risk

Clear niche scoped to breaking-change/compatibility review of Plinth Toolkit and OpenSpec artifacts with distinct triggers; minor overlap risk with general code-review skills keeps it just below 5.

4 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jabrena/plinth
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.