CtrlK
BlogDocsLog inGet started
Tessl Logo

gh-review-requests

Fetch unread GitHub notifications for open PRs where review is requested from a specified team or opened by a team member. Use when asked to "find PRs I need to review", "show my review requests", "what needs my review", "fetch GitHub review requests", or "check team review queue".

73

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is gh-review-requests in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

88%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, actionable skill body with an explicit workflow, output contract, and fallback. Its main weakness is progressive disclosure: the body references a script under scripts/ that is not present in the bundle, leaving a dangling reference.

Suggestions

Ship the referenced scripts/fetch_review_requests.py in a scripts/ bundle directory so the primary command resolves, or inline the equivalent gh api logic if no bundle is intended.

Trim the example JSON output and presentation table to the minimal fields needed to convey the contract.

Make the fallback section explicitly conditional on the script being unavailable, so the two paths are clearly alternatives rather than parallel guidance.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence — the JSON output contract, reasons legend, presentation table, and fallback all earn their place. The example output block and table could be trimmed slightly, placing it just below the maximally lean 5 anchor.

4 / 5

Actionability

Provides a concrete copy-paste command with arguments, a multi-team variant, a documented output JSON schema, and a fully concrete gh api fallback path, covering the common cases.

5 / 5

Workflow Clarity

A clear three-step sequence (identify team, run script, present results) with explicit edge-case handling for zero results and script failure. It is a read-only query skill, so the destructive/batch validation cap does not apply and the simple-skill exception justifies a 5.

5 / 5

Progressive Disclosure

Well-organized sections with a clearly signaled, one-level-deep script reference, but the referenced scripts/fetch_review_requests.py has no corresponding scripts/ bundle directory, so the navigation reference is partially broken — a minor organization gap below the top anchor.

4 / 5

Total

18

/

20

Passed

Description

95%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 strong, third-person description that cleanly answers both what the skill does and when to trigger it, with a rich set of natural trigger phrases. The only minor gap is that it describes one composite fetch-and-filter action rather than a list of several distinct actions.

DimensionReasoningScore

Specificity

Names the domain and concrete filtering criteria ('unread GitHub notifications for open PRs where review is requested from a specified team or opened by a team member'), but it is one core fetch-and-filter action rather than multiple distinct actions, so it sits just below the comprehensive 5 anchor.

4 / 5

Completeness

Explicitly states what it does (fetch unread review_requested notifications for open PRs filtered by team) and when to use it with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Five natural user phrases ('find PRs I need to review', 'show my review requests', 'what needs my review', 'fetch GitHub review requests', 'check team review queue') give comprehensive coverage of how a user would phrase the need.

5 / 5

Distinctiveness Conflict Risk

A clearly defined niche (team-scoped GitHub review-request queue) with distinct triggers and minimal overlap with other skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.