custom-dependency-pr-solver

Batch-process Dependabot PRs end-to-end: checkout, rebase, review, changeset, validate, and auto-merge high-confidence PRs. USE FOR: process all Dependabot PRs, clear dependency backlog, batch-merge safe Dependabot updates, batch-process dependency PRs. DO NOT USE FOR: single-PR deep review (use fusion-dependency-review), feature PRs, non-Dependabot dependency PRs, or PRs requiring manual code changes.

1.34x

Quality

—

Does it follow best practices?

Impact

98%

1.34x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

92%

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

A well-structured, token-efficient batch workflow with concrete commands, clear sequencing, and validation feedback loops. The only weakness is progressive disclosure: the authoritative changeset/confidence/rebase rules are externalized to a non-bundle repo instruction file that is neither bundled nor clearly navigable.

Suggestions

Either vendor '.github/instructions/dependabot-pr.instructions.md' into the skill's references/ bundle (with a clearly signaled one-level-deep link) or inline the key changeset/confidence/rebase decision rules so the skill is self-contained.

Add explicit navigation cues (e.g., 'See [references/dependabot-pr-instructions.md]') wherever the body currently defers to the repo instructions file, so the reference depth is clearly signaled rather than implied.

Consider moving the research and verdict comment templates out of inline prose references into a short 'References' section that enumerates all bundle files in one place for easier discovery.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence — no concept explanations, just commands and rules — with every section earning its tokens; it does not pad with context Claude already knows.	3 / 3
Actionability	Provides fully executable commands ('gh pr list ...', 'gh pr merge <number> --squash --admin', 'pnpm test && pnpm build && pnpm -w check') with copy-paste-ready specifics, and the delegation to fusion-dependency-review is explicit rather than vague.	3 / 3
Workflow Clarity	A clear 8-step sequence with explicit validation (Step 6) and feedback loops (conflict abort/skip, validation failure → needs-manual-intervention → final report), appropriate for a batch mutation workflow.	3 / 3
Progressive Disclosure	SKILL.md is an overview and its asset references (research/verdict templates) are real one-level-deep bundle files, but the core decision rules repeatedly live in '.github/instructions/dependabot-pr.instructions.md', an external repo path outside the bundle that is referenced but not clearly signaled as a separate navigable resource.	2 / 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.

A strong, third-person description that states concrete capabilities and provides explicit positive and negative trigger guidance with clear separation from the related fusion-dependency-review skill. Every dimension lands at the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'checkout, rebase, review, changeset, validate, and auto-merge high-confidence PRs' — rather than abstract language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both 'what' (batch-process Dependabot PRs end-to-end) and 'when' via explicit USE FOR / DO NOT USE FOR trigger clauses, so it is not capped at 2.	3 / 3
Trigger Term Quality	The USE FOR list ('process all Dependabot PRs, clear dependency backlog, batch-merge safe Dependabot updates, batch-process dependency PRs') gives good coverage of natural phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Clear Dependabot-batch niche with explicit DO NOT USE routing single-PR review to 'fusion-dependency-review' and excluding feature/non-Dependabot PRs, making wrong-skill conflicts unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: equinor/fusion-framework
Commit: 54fb2a7

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.