Tessl • The package manager for agent skills

check-pr

Check a GitHub, GitLab, or Perforce PR/MR/CL for review comments, failing checks, and PR-body gaps. Use when asked to inspect, fix, or prepare a change for submission.

Quality

84%

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

81%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 highly actionable, well-sequenced multi-platform workflow with strong validation checkpoints and valid one-level references. Its main weakness is length and redundancy across the three platforms, which depresses conciseness.

Suggestions

Move the inlined GraphQL thread-resolution query and the elaborate GitLab Greptile-note jq filter into the existing reference files, keeping only a concise invocation in SKILL.md to improve both conciseness and progressive disclosure.

Consolidate the repeated per-platform command patterns (detect/identify/fetch/wait) into a shared structure with platform-specific overrides, reducing the ~360-line body and cross-platform redundancy.

Trim the explanatory commentary inside the Greptile gate code blocks to essential comments, since the commands are self-explanatory to Claude.

Dimension	Reasoning	Score
Conciseness	The body runs ~360 lines with elaborate, partly redundant platform-specific blocks (notably the Greptile freshness gate's multi-line jq pipelines and verbose commentary); while mostly concrete rather than conceptual fluff, it could be tightened, fitting anchor 3 better than 4.	3 / 5
Actionability	Provides fully executable, copy-paste-ready bash for GitHub, GitLab, and Perforce across every step with concrete gh/glab/p4 commands and jq filters covering the common cases, matching anchor 5.	5 / 5
Workflow Clarity	Steps 0–10 are clearly sequenced with explicit validation checkpoints (§3 check polling, §4 Greptile freshness gate) and a feedback loop ('Address the findings, push, and re-run Greptile until it concludes success'), satisfying the anchor 5 criteria including for batch/destructive operations.	5 / 5
Progressive Disclosure	Two real one-level-deep references are clearly signaled in the body ('see [the GraphQL reference](references/graphql-queries.md)' and 'see [the GitLab API reference](references/gitlab-api.md)'), but substantial API detail (e.g. the inlined GraphQL query in §9) lives in SKILL.md rather than the reference files, leaving minor organization gaps at anchor 4.	4 / 5
	Total	17 / 20 Passed

Description

87%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 well-crafted description that explicitly covers both what the skill does and when to use it, with concrete platform-specific triggers and low conflict risk. Minor specificity and synonym coverage gaps keep two dimensions at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain (PR/MR/CL review across GitHub, GitLab, Perforce) and three concrete actions — 'review comments, failing checks, and PR-body gaps' — but does not enumerate the full capability set (resolving threads, pushing fixes), so it falls at anchor 4 rather than 5.	4 / 5
Completeness	Explicitly states what it does ('Check a ... PR/MR/CL for review comments, failing checks, and PR-body gaps') and when to use it ('Use when asked to inspect, fix, or prepare a change for submission') with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	Strong natural keywords including 'PR/MR/CL', 'review comments', 'failing checks', and 'inspect, fix, or prepare a change for submission'; a few common variants (spelled-out 'pull request'/'merge request') are absent, placing it just below the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (cross-platform PR/MR/CL review and submission preparation) with distinct triggers and minimal overlap with other skills, matching the anchor 5 'clear niche' criterion.	5 / 5
	Total	18 / 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: paperclipai/paperclip
Path: .agents/skills/check-pr/SKILL.md
Commit: bd1fdc2

Reviewed: 5 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.