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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

57%

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

A well-organized review-process skill with excellent progressive disclosure and a clear taxonomy, held back by redundant surface listings and example/format detail that lives only in the reference file.

Suggestions

Merge the 'What is covered in this Skill?' list with workflow step 2 to remove the duplicated surface inventory and tighten conciseness.

Add a brief inline example of a severity-ranked finding or the report structure so the body is actionable without requiring the reference.

Insert an explicit validation/checkpoint note in the workflow (e.g., confirm artifact authority and read-only scope before classifying) to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but the 'What is covered in this Skill?' bullet list substantially overlaps the surfaces re-listed in workflow step 2 ('Inventory compatibility surfaces'), so it could be tightened by consolidating the two.	2 / 3
Actionability	For an instruction-only skill it gives concrete guidance (a BREAKING/POTENTIALLY BREAKING/NON-BREAKING/UNKNOWN taxonomy and MUST/MUST NOT constraints), but the worked examples and report format are deferred to the reference rather than shown inline, leaving key details unstated in the body.	2 / 3
Workflow Clarity	The five steps are clearly sequenced with a conditional branch (step 4 only for risks), but there are no explicit validation checkpoints or feedback loops within the workflow itself; validation appears only as an output mention in step 5.	2 / 3
Progressive Disclosure	The body is a clear overview with well-signaled one-level-deep navigation: the reference is named in the Constraints ('MUST read references/056-design-avoid-breaking-changes.md') and again in a dedicated Reference section with a markdown link, and the referenced file exists.	3 / 3
	Total	9 / 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.

A strong, specific description with explicit trigger guidance and a clear niche; its only demerit is the second-person 'you need' phrasing, which the rubric penalizes on specificity.

Suggestions

Rephrase the opening in third person (e.g., 'Use when reviewing a plan, OpenSpec change...') to avoid the second-person specificity penalty.

Consider trimming the long surface enumeration slightly to sharpen the core action without losing the trigger coverage.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete compatibility surfaces ('commands, skills, generated outputs, XML sources, README/docs, tests, CI, APIs, schemas, configuration, data, migration, and release guidance') which would anchor at 3, but the judging guidelines mandate a one-point penalty for second-person voice, and the opening 'Use when you need to review' uses 'you', reducing it to 2.	2 / 3
Completeness	It clearly answers both 'what' (review plans/specs/proposals for breaking-change risk across named surfaces) and 'when' via the explicit 'Use when...' clause and concrete trigger examples, matching the score-3 anchor.	3 / 3
Trigger Term Quality	It lists natural phrases a user would actually 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'), giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (breaking-change/compatibility review for OpenSpec changes within the Plinth Toolkit) with distinct triggers, making it unlikely to fire for the wrong skill.	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: jabrena/plinth
Commit: aaee915

Reviewed: 1 day 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.