triage-reviews

Triage PR review comments by classifying feedback, accepting actionable suggestions, rejecting non-applicable ones with explanations, and creating tracked follow-up tasks. Use when processing code review feedback on pull requests.

Quality

86%

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.

The body is highly actionable with executable gh commands, clear sequencing, and strong validation/idempotency checkpoints for a destructive batch operation. Its main weakness is redundancy across the overview, task-execution, and communication sections that inflates token usage without adding guidance.

Suggestions

Collapse the 'Workflow Overview' diagram/list and the 'Default flow' under 'Task Execution' into the single Step 1-5 sequence to remove restated content.

Move the full example summary table and the full .claude/pr-review-triage.local.md YAML block into a short reference file, keeping only a compact schema sketch inline.

Merge 'Communication Style' into the relevant action sections (Step 5 replies, beads issue descriptions) so it is not a standalone filler section.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tables and terse step blocks, but several sections are redundant — the 'Workflow Overview' restates the step list, 'Task Execution' repeats flag behavior already covered in Usage and inline, and 'Communication Style' is partially filler — fitting anchor 3's 'mostly efficient but could be tightened'.	3 / 5
Actionability	Provides copy-paste-ready gh api/gh pr commands with exact endpoints, a concrete example summary table, and example reply tone, fully matching anchor 5's 'fully executable; copy-paste ready code or commands'.	5 / 5
Workflow Clarity	A clear 5-step sequence with explicit validation checkpoints ('Wait for user confirmation', dry-run gating), an Idempotency section that pre-checks each action before performing it, and an Error Handling section for this batch/destructive operation — matching anchor 5's explicit validation steps and feedback loops.	5 / 5
Progressive Disclosure	Well-sectioned single-file skill with one clearly signaled external reference (.claude/pr-review-triage.local.md) and no nested references, fitting anchor 4's 'good structure; most content appropriately placed; minor organization gaps' — a few large blocks (full example summary table, full config YAML) could live in separate files.	4 / 5
	Total	17 / 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.

The description is strong: it states concrete capabilities and provides an explicit 'Use when' trigger, fully answering what and when with domain-specific language. The only minor gap is keyword synonym coverage.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'classifying feedback, accepting actionable suggestions, rejecting non-applicable ones with explanations, and creating tracked follow-up tasks' — giving comprehensive coverage of the domain, matching the anchor 5 example.	5 / 5
Completeness	Explicitly answers both what ('Triage... by classifying... accepting... rejecting... creating tracked follow-up tasks') and when ('Use when processing code review feedback on pull requests') with a concrete trigger clause, matching anchor 5.	5 / 5
Trigger Term Quality	Includes natural phrases ('PR review comments', 'code review feedback', 'pull requests') but misses common synonyms like 'reviewer comments' or 'review suggestions', fitting anchor 4's 'good keyword coverage; a few natural terms missing' rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (PR review comment triage with accept/reject/task-creation actions) and uses domain-specific triggers, giving minimal overlap risk with other skills, matching anchor 5.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: rikdc/ai-skills
Path: plugins/pr-review-triage/skills/triage-reviews/SKILL.md
Commit: cd15778

Reviewed: 2 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.