multi-version-compliance

Apply or review multi-version support compliance for first-party Nx plugins. Primary entry point: a Linear task ID (NXC-XXXX) from the "Multi-version supported across plugins" milestone — the task carries the resolved support window, findings, and "Needs human decision" items. Falls back to self-discovery when no task exists. Use when asked to "fix multi-version compliance for @nx/X", "do NXC-XXXX", "review this compliance PR", or when working on a branch / PR titled "multi-version support compliance for @nx/X". Covers the canonical shape (assertSupportedPackageVersion, all-generators-enforce-floor.spec.ts, peer dep alignment, requires-gate auditing, user-pin preservation, executor / inferred-plugin feature gating).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

The body is highly actionable with a clearly sequenced, validation-gated multi-phase workflow and a well-structured reference architecture with verified bundle files. Its only weakness is conciseness: a few large inline blocks could be moved to references to shorten the SKILL.md surface.

Suggestions

Move the full findings-doc template (lines 326-398) into a reference file (e.g. references/findings-doc-template.md) and keep only a short pointer plus the key shape in SKILL.md, since it is already flagged as the Phase 2 output artifact.

The inline A–F checklist (lines 354-393) overlaps canonical-shape.md; reference it there and retain only the mode-specific load guidance to reduce duplication.

Tighten the large 'Mode workflows' entry-point and reference-PR tables where rows restate behavior already covered in the Linear-fetching protocol and critical rules.

Dimension	Reasoning	Score
Conciseness	The body is information-dense with no concept-explanation fluff (it never explains what Nx, semver, or peer deps are), but at ~385 lines it carries large inline blocks — the full findings-doc template (lines 326-398) and the A–F checklist that overlaps canonical-shape.md — that could be tightened by referencing instead. This matches 'mostly efficient but could be tightened' rather than the lean score-3 anchor.	2 / 3
Actionability	Fully executable guidance throughout: exact commands ('gh pr view <N> --repo nrwl/nx --json state', 'npx nx test <plugin> --testPathPattern=...', 'npx nx format'), exact MCP calls ('mcp__linear-server__get_issue id="NXC-XXXX"'), real file/symbol paths, and a copy-paste findings-doc template — copy-paste ready.	3 / 3
Workflow Clarity	Fix mode is sequenced as Phases 1–6 with an explicit 'User OK gate' at the end of Phase 2, verification steps (Phase 4 tests, Phase 5 verify locally), error-recovery footguns, and the Linear-fetching protocol with halt conditions — clear sequence with validation checkpoints and feedback loops for the destructive/batch edits involved.	3 / 3
Progressive Disclosure	A dedicated 'Which references to load (context hygiene)' table maps each mode to required/optional references, the referenced files (canonical-shape.md, anti-patterns.md, gotchas.md, examples.md) all exist in ./references/, are one level deep, clearly signaled, and the body instructs 'Don't pull all of them' — matching the well-signaled one-level-deep anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 specific, third-person, and answers both what and when with explicit, natural trigger phrasings tied to a distinct niche. It hits the top anchor on every dimension with no fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities and entry points — 'Apply or review multi-version support compliance', 'peer dep alignment, requires-gate auditing, user-pin preservation, executor / inferred-plugin feature gating' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (apply/review compliance, canonical shape coverage) and when (a 'Use when asked to...' clause with multiple concrete triggers), so it hits the 'clearly answers both' anchor.	3 / 3
Trigger Term Quality	Surfaces natural phrasings a user would say — 'fix multi-version compliance for @nx/X', 'do NXC-XXXX', 'review this compliance PR', 'multi-version support compliance for @nx/X' — giving good coverage of real trigger terms.	3 / 3
Distinctiveness Conflict Risk	A tightly scoped niche — first-party Nx plugins, NXC-XXXX task IDs, a named milestone — with distinct triggers unlikely to collide with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: nrwl/nx
Path: .claude/skills/multi-version-compliance/SKILL.md
Commit: 0abf7a4

Reviewed: 4 days 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.