CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/agent-teams/skills/multi-reviewer-patterns/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 delivers concrete, well-tabled guidance for dimension allocation, deduplication, severity calibration, and reporting, but suffers from internal redundancy, an implicit rather than explicit orchestration workflow lacking validation checkpoints, and an orphaned reference file that is never surfaced to the reader.

Suggestions

Link references/review-dimensions.md from the 'Available Dimensions' or 'When to Use This Skill' section (e.g., 'Full per-dimension checklists: see [review-dimensions.md](references/review-dimensions.md)') so the existing bundle file is discoverable.

Merge the 'Merge Rules' and 'Deduplication Process' sections into one canonical rule list to remove the duplicated guidance, and drop the intro paragraph or 'When to Use' section that restates the frontmatter description.

Add an explicit end-to-end orchestration sequence with checkpoints — e.g., '1. Select dimensions → 2. Dispatch parallel reviewers → 3. Confirm all reviewer reports received → 4. Deduplicate → 5. Calibrate severity → 6. Verify report totals before publishing' — to give the multi-step process validation steps.

DimensionReasoningScore

Conciseness

Mostly efficient with tables and no re-explanation of known concepts, but the 'Merge Rules' list and the 'Deduplication Process' pseudocode restate the same five rules, and the intro paragraph plus 'When to Use This Skill' section duplicate the frontmatter description. Tightening these would remove noticeable redundancy.

3 / 5

Actionability

Merge rules, the severity criteria table, calibration rules, and the copy-paste-ready consolidated report template are concrete and executable guidance. The minor gap is that how parallel reviewers are actually dispatched and how their reports are collected is left unspecified.

4 / 5

Workflow Clarity

The implied sequence (allocate dimensions, run reviews, dedupe, calibrate, report) is present via section ordering and the numbered dedup process, but there is no explicit end-to-end workflow and no validation checkpoints such as confirming all reviewer reports are in before merging or verifying the final report totals.

3 / 5

Progressive Disclosure

The body has clear section structure, but the provided bundle file references/review-dimensions.md — detailed per-dimension checklists that are exactly the material a reference should hold — is never mentioned or linked anywhere in the body, making it undiscoverable despite existing on disk.

3 / 5

Total

13

/

20

Passed

Description

88%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: concrete capability list plus an explicit trigger clause in third person. The only weaknesses are a few missing natural synonyms in the trigger terms and slight overlap risk with generic code-review skills.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions — 'Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting' — comprehensively covering the skill's scope with no generic filler.

5 / 5

Completeness

It explicitly answers both 'what' (deduplication, severity calibration, consolidated reporting) and 'when' via the concrete 'Use this skill when...' clause, matching the top anchor.

5 / 5

Trigger Term Quality

Trigger phrases like 'organizing multi-reviewer code reviews', 'calibrating finding severity', and 'consolidating review results' are natural, but common variations such as 'duplicate findings', 'triage', or 'PR/pull request review' are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

'Multi-reviewer', 'parallel', and 'severity calibration' carve a mostly distinct niche, but the broad phrase 'code reviews' creates minor overlap risk with general code-review skills.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

wshobson/agents

Path

plugins/agent-teams/skills/multi-reviewer-patterns/SKILL.md

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.