multi-reviewer-patterns
Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.
73
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/agent-teams/skills/multi-reviewer-patterns/SKILL.mdQuality
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured description that clearly communicates both what the skill does and when to use it. The specificity of capabilities like 'finding deduplication' and 'severity calibration' makes it distinctive. The main weakness is that trigger terms could be broader to capture more natural user phrasings like 'PR review' or 'review summary'.
Suggestions
Add more natural trigger term variations such as 'PR review', 'pull request review', 'review summary', 'merge review feedback', or 'deduplicate review findings' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'coordinate parallel code reviews', 'finding deduplication', 'severity calibration', and 'consolidated reporting'. These are distinct, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting') and when ('when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'code reviews', 'severity', 'consolidated reporting', and 'multi-reviewer', but misses common natural variations users might say such as 'PR review', 'pull request', 'review feedback', 'merge duplicates', or 'review summary'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on multi-reviewer coordination, deduplication, severity calibration, and consolidated reporting creates a clear niche that is distinct from a general code review skill or a single-reviewer linting skill. Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a solid conceptual framework for multi-reviewer code reviews with useful tables for dimension selection, severity calibration, and a report template. However, it lacks executable implementations, an explicit end-to-end workflow with validation checkpoints, and could benefit from tighter prose and better progressive disclosure by splitting reference material into separate files.
Suggestions
Add an explicit end-to-end workflow section with numbered steps tying together dimension selection, review execution, deduplication, calibration, and report generation—including validation checkpoints between stages.
Replace the pseudocode deduplication process with a concrete, executable implementation (e.g., a Python function or structured algorithm with real example input/output).
Include a worked example showing a complete mini-review: 2-3 sample findings from different reviewers, the deduplication/merge result, and the final consolidated report output.
Move the detailed report template and severity calibration tables to separate reference files (e.g., REPORT_TEMPLATE.md, SEVERITY_GUIDE.md) and link to them from the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably well-structured but includes some unnecessary framing (e.g., 'When to Use This Skill' section restates what the tables already make clear). The tables are efficient, but the overall document could be tightened—the deduplication process pseudocode and some table entries are somewhat verbose for what Claude could infer. | 2 / 3 |
Actionability | The skill provides structured guidance through tables, merge rules, and a report template, which are useful. However, it lacks executable code or concrete tool-based commands—the deduplication process is pseudocode, and the report template uses placeholders rather than a worked example with real data. It describes processes rather than providing copy-paste-ready implementations. | 2 / 3 |
Workflow Clarity | The deduplication process has a clear sequence, and the dimension allocation tables guide decision-making. However, there's no overarching end-to-end workflow tying the pieces together (e.g., 'Step 1: Select dimensions → Step 2: Run reviews → Step 3: Deduplicate → Step 4: Calibrate → Step 5: Generate report'), and there are no validation checkpoints or feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | The content is organized into logical sections with clear headers, which aids navigation. However, the report template and severity tables are quite lengthy inline content that could be split into separate reference files. There are no references to external files for deeper detail, and the document is somewhat monolithic for its length. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
27a7ed9
- 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.