Name: attach-review-to-pr
Rating: 53.6 (1 reviews)
Author: NeoLabHQ

Blog Docs Log in Get started

attach-review-to-pr

Add line-specific review comments to pull requests using GitHub CLI API

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./antigravity/skills/attach-review-to-pr/SKILL.md

The canonical home for this skill is attach-review-to-pr in NeoLabHQ/context-engineering-kit

Quality

Content

60%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.

The content is highly actionable with executable commands and strong error guidance, but it is padded by repeated parameter/API-reference sections and fails to split bulk material into the (missing) reference files it implies.

Suggestions

Remove the duplicate parameter tables: keep one 'Parameters Explained' table and delete the redundant 'Parameter Flags' and closing 'API Reference' sections, or move the full API Reference into a separate references/ file.

Extract the helper scripts (pr-files.sh, check-reviews.sh) into a scripts/ bundle directory and reference them by path instead of inlining.

Add an explicit validate->fix->retry checkpoint in the multi-comment review workflow (e.g. verify each line exists in the diff before posting, then on 422 check for pending reviews and retry) to earn workflow_clarity 5.

Create the referenced ./create-pr.md and ./commit.md files (or remove the broken links) so cross-references resolve.

Dimension	Reasoning	Score
Conciseness	Parameter lists are repeated in three places (table, 'Parameters Explained'/'Parameter Flags', and the closing 'API Reference'), and the single-comment and multi-comment examples are restated multiple times, making it noticeably verbose rather than merely 'some unnecessary explanation' (3).	2 / 5
Actionability	Provides fully copy-paste-ready `gh api` commands with correct -f/-F/--input flags, complete JSON payloads, and concrete paths/line numbers covering single, multi-line, and multi-comment cases plus helper scripts.	5 / 5
Workflow Clarity	Includes SHA-first gathering, pending-review checks, and a dedicated error-recovery section, but the main multi-comment (batch) workflow lacks an embedded validate->fix->retry checkpoint, so per the batch-operation feedback-loop cap it stays at 4 rather than 5.	4 / 5
Progressive Disclosure	No references/, scripts/, or assets/ bundle directories exist, the inlined ~510-line monolith contains an API Reference and helper scripts that belong in separate files, and the two referenced files (./create-pr.md, ./commit.md) do not exist, matching score 2 (content that belongs in separate files is inlined).	2 / 5
	Total	13 / 20 Passed

Description

61%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.

The description clearly states the skill's purpose and domain with mostly natural trigger terms, but it omits any explicit 'Use when...' guidance, capping completeness, and lacks synonym coverage that would push it to the top tier.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when posting inline/line-specific code review comments on a pull request via gh or the GitHub MCP tool.'

Broaden trigger coverage with synonyms users actually say: 'inline comments', 'code review', 'PR feedback', 'line comments'.

Optionally surface the two paths (single comment vs. multi-comment review) in the description to lift specificity toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain (PR review comments) and one concrete action ('Add line-specific review comments'), matching score 3 rather than 4 which requires several distinct listed actions.	3 / 5
Completeness	Has a clear 'what' but no 'Use when...' or equivalent trigger clause; per guidelines a missing 'when' clause caps completeness at 3 rather than 4.	3 / 5
Trigger Term Quality	Includes natural developer terms ('review comments', 'pull requests', 'GitHub CLI', 'API') but omits common synonyms like 'inline comments', 'code review', or 'PR feedback', so it sits at 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	'line-specific review comments to pull requests' is a specific niche with only minor overlap risk against a generic code-review skill, matching 4 rather than 5 which requires minimal conflict risk with explicit distinct triggers.	4 / 5
	Total	14 / 20 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
skill_md_line_count	SKILL.md is long (510 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: NeoLabHQ/context-engineering-kit
Path: antigravity/skills/attach-review-to-pr/SKILL.md
Commit: 23e2428

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.