CtrlK
BlogDocsLog inGet started
Tessl Logo

review-pr

Monitor and respond to automated PR reviews (Codex bot). Use when pushing a PR, checking review status, or responding to bot feedback. Handles the full cycle of push -> wait for review -> evaluate comments -> fix -> re-push.

73

Quality

90%

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

SKILL.md
Quality
Evals
Security

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 well-structured, highly actionable workflow with executable commands, explicit feedback loops, and clear sequencing. Minor conciseness tightening is the only improvement area.

DimensionReasoningScore

Conciseness

Largely efficient — concrete gh/jq commands and tight prose — with minor over-explanation (e.g., the labels section rationale and 'How to evaluate Codex comments' preamble) that could be trimmed. Not a 5 because a few passages restate context Claude already knows.

4 / 5

Actionability

Provides copy-paste-ready gh api + jq commands for every operation (status check, fetching comments, replying via in_reply_to) plus concrete dismissal-reply examples; covers the common cases fully.

5 / 5

Workflow Clarity

Clear multi-step sequence with explicit feedback loops: push -> check review count -> evaluate comments -> fix/dismiss -> reply -> re-push -> repeat until thumbs-up. Validation checkpoints (count==0 wait, stale-comment verification, 'when a PR is ready' criteria) are explicit.

5 / 5

Progressive Disclosure

No bundle files exist, so this is a self-contained skill under ~80 lines with well-organized section headers (Checking status, Evaluating comments, Responding, Fix-push-review cycle, Stale comments, Labels, When ready); per the simple-skill guidance, this scores 5 with good organization and no nested references.

5 / 5

Total

19

/

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 strong, well-targeted description that clearly conveys both capability and trigger conditions for a specific Codex-bot PR review workflow. Minor room to mention replying to dismissal comments, but no real weaknesses.

DimensionReasoningScore

Specificity

Names concrete actions ('Monitor and respond to automated PR reviews', 'pushing a PR, checking review status, responding to bot feedback') and a multi-stage cycle, with minor coverage gaps (no mention of replying to comments).

4 / 5

Completeness

Explicitly states what it does ('Monitor and respond to automated PR reviews', 'Handles the full cycle of push -> wait for review -> evaluate comments -> fix -> re-push') and when to use it ('Use when pushing a PR, checking review status, or responding to bot feedback').

5 / 5

Trigger Term Quality

Natural phrases like 'pushing a PR', 'checking review status', 'responding to bot feedback' map well to what a user would say; a few synonyms (e.g., 'pull request' spelled out) are missing.

4 / 5

Distinctiveness Conflict Risk

The narrow niche of 'automated PR reviews (Codex bot)' with Codex-specific triggers is highly distinct and unlikely to fire for unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
PrefectHQ/fastmcp
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.