CtrlK
BlogDocsLog inGet started
Tessl Logo

address-pr-review

Critically triage pull request review comments against PR requirements and codebase reality, implement only valid fixes, and reply only when declining a suggestion. Use when the user asks to address PR comments, review feedback, CodeRabbit/Bugbot threads, or `/address-pr-review`.

69

Quality

83%

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

75%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 body is highly actionable — real gh/GraphQL/REST commands, a verdict decision table, and a checklist-driven workflow with explicit validation before acting. Its main weakness is redundancy: the critical-evaluation guidance is restated across sections 1 and 3 rather than stated once, inflating token cost without adding information.

Suggestions

Merge the 'Critical evaluation (read first)' section and the 'Validate before acting' bullets in step 3 into a single triage checklist — the stale-comment and scope checks currently appear in both.

Collapse the 'Decline (with reply)' list and the five 'Is there a real problem?' verdict bullets into one decision list (or extend the verdict table) so decline criteria are stated once.

Add a short error-recovery step after 'Run targeted build/tests' in step 4 (what to do when validation fails) to close the workflow feedback loop.

DimensionReasoningScore

Conciseness

All guidance is skill-specific (no concept padding), but triage criteria are covered three times — the 'Critical evaluation' questions, the 'Decline (with reply)' list, and the 'Validate before acting' bullets repeat the same stale-comment and scope checks (e.g. 'Read current code at the cited path — comments may be stale' appears verbatim in both sections 1 and 3).

3 / 5

Actionability

Fully executable throughout: copy-paste-ready `gh pr view`, GraphQL query with jq filtering, REST reply command, a verdict→action table, and concrete example decline replies covering the common cases.

5 / 5

Workflow Clarity

Clear 7-step sequence with a progress checklist and explicit checkpoints (validate-before-acting bullets, 'run targeted build/tests' before push), but no error-recovery loop if tests fail, which keeps it below the top anchor.

4 / 5

Progressive Disclosure

Well-organized with clear section headers, a verdict table, and no buried or nested references; the body is self-contained with no bundle files to disclose. The duplicated triage lists could be consolidated into one section to tighten the structure.

4 / 5

Total

16

/

20

Passed

Description

92%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 description: it states what the skill does in third person with three concrete, differentiated actions, and gives an explicit 'Use when' clause with natural trigger terms including tool names and the slash command. Only minor synonym coverage keeps trigger quality from full marks.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Critically triage pull request review comments against PR requirements and codebase reality, implement only valid fixes, and reply only when declining a suggestion" — covering triage, selective implementation, and reply policy comprehensively with no vague filler.

5 / 5

Completeness

Explicitly answers both what ("triage... implement only valid fixes... reply only when declining") and when ("Use when the user asks to address PR comments, review feedback, CodeRabbit/Bugbot threads, or `/address-pr-review`") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural trigger phrases — "address PR comments", "review feedback", "CodeRabbit/Bugbot threads" — but misses common variations like "code review comments", "reviewer suggestions", or "respond to feedback".

4 / 5

Distinctiveness Conflict Risk

Clear niche — critical triage of PR review comments with a reply-only-on-decline policy — with distinct triggers (CodeRabbit/Bugbot, PR comments) that would not fire for general coding or PR-creation skills.

5 / 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
novuhq/novu
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.