finish-pr

Use when a non-trivial code change is substantially complete and needs a final diff audit, documentation check, verification record, or pull request description.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%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 tight, well-structured instruction-only skill with concrete file and operation references, explicit verification checkpoints, and a sensible publish guardrail. The only minor gap is that build/test commands are referenced indirectly rather than named.

Suggestions

Name a representative example build/test command shape (e.g. 'npm test', 'pytest', or 'cargo test') alongside the 'from CLAUDE.md' reference so the verification step is copy-pasteable even before CLAUDE.md is read.

Add a short validation feedback loop line (e.g. 'if a check fails, fix and re-run before proceeding') to make the recovery path explicit in step 4.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding or explanation of concepts Claude already knows; every line earns its place and competence is assumed.	5 / 5
Actionability	Names specific files, git operations (merge-base diff, submodule pointer changes), and comment categories to audit, but 'run the relevant build... from CLAUDE.md' is slightly abstract rather than naming concrete commands.	4 / 5
Workflow Clarity	A clear 5-step sequence with explicit verification checkpoints ('Record exact commands and outcomes', 'Verify every claim against the final diff') and a publish guardrail, satisfying the validation requirement for an outward-facing skill.	5 / 5
Progressive Disclosure	Under 50 lines with no need for external references, organized into clear Workflow and Quality gate sections; per the simple-skill rule this is appropriately structured.	5 / 5
	Total	19 / 20 Passed

Description

92%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 precise, third-person description with an explicit 'Use when...' trigger and a concrete enumeration of capabilities, hitting both what and when cleanly. Slight room only for additional trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain (PR finalization) and multiple concrete actions — 'final diff audit, documentation check, verification record, or pull request description' — providing comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (the four listed tasks) and 'when' via a concrete 'Use when a non-trivial code change is substantially complete' trigger clause.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('final diff audit', 'documentation check', 'verification record', 'pull request description'), though a few common synonyms or variations are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (reviewer-facing PR finalization) with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	19 / 20 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: eloqdata/eloqkv
Path: .agents/skills/finish-pr/SKILL.md
Commit: 1aaf236

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.