CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-comments

Fetch PR comments, research each one against the codebase, assess validity, and present an action plan. Use when: (1) user says "pr-comments", "review pr comments", "check pr feedback", (2) user pastes a GitHub PR URL and wants to understand/triage the comments, (3) user wants to plan responses to code review feedback. CRITICAL: present the plan for approval before making any code changes.

72

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 skill body with concrete commands and templates and an explicit approval checkpoint. It could be tightened by deduplicating the codebase-research and bot-warning instructions and by adding error-recovery guidance for failed API calls.

Suggestions

Merge step 3a ('Read the code under review') and 3f ('Read surrounding code') into a single instruction to remove redundancy, and drop the repeated bot-warning from the Rules section since it already appears in 3e.

Add a brief error-recovery checkpoint after the Fetch step (e.g., 'If a gh api call fails, check auth/rate-limit and retry before proceeding') to raise workflow clarity.

Trim emphasis scaffolding (NON-NEGOTIABLE / You MUST / NOT sufficient) to one firm directive — the same constraint is stated multiple times.

DimensionReasoningScore

Conciseness

Mostly efficient and free of concept-explaining padding, but repeats the thoroughness directive (3a vs 3f 'read surrounding code') and restates the bot-warning in both step 3e and the Rules section; emphasis words (NON-NEGOTIABLE, MUST, NOT) could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready gh api commands, exact jq fields, a comment-display format, a concrete classification schema (Fix / Fix (modified) / Skip / Discuss), and a full plan output template covering the common cases.

5 / 5

Workflow Clarity

Six clearly sequenced steps with an explicit approval gate (step 6 'stop and wait'), but lacks error-recovery feedback loops (e.g., what to do when a gh api call fails) so it stops short of the validate-fix-retry ideal.

4 / 5

Progressive Disclosure

A single self-contained file organized into clear numbered workflow steps and a Rules section with no nested references; at ~130 lines it exceeds the under-50-line simple-skill exception but remains well-structured.

4 / 5

Total

17

/

20

Passed

Description

96%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 clearly states capabilities and triggers with concrete phrasing and an explicit approval guardrail. Minor overlap risk with broader code-review skills keeps distinctiveness just below maximum.

DimensionReasoningScore

Specificity

Lists multiple concrete actions on a named domain — 'Fetch PR comments, research each one against the codebase, assess validity, and present an action plan' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (fetch, research, assess, present plan) and 'when' via a numbered 'Use when:' clause with concrete trigger phrases, plus a CRITICAL approval guardrail.

5 / 5

Trigger Term Quality

Includes natural phrases a user would say and their synonyms — "pr-comments", "review pr comments", "check pr feedback", "code review feedback", and "GitHub PR URL" — with broad coverage of likely triggers.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (PR comment triage) with distinct triggers, but 'review pr comments' / 'check pr feedback' carry some overlap risk with general code-review skills.

4 / 5

Total

19

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mayank-arora/agent-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.