CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

next-bundle-optimizer

Audit and reduce Next.js browser initial-load work. Use for slow route startup, oversized client bundles, duplicate browser dependencies, or features that can wait for interaction.

Quality

87%

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

The canonical home for this skill is next-bundle-optimizer in vercel/next.js

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 tightly written, well-sequenced workflow with explicit done-criteria, validation gates, error-recovery loops, and clean one-level reference splitting. The main gaps are the absence of any executable example for the JSONL interpretation step and minor token overhead from repeated external-skill install instructions.

Suggestions

Include a minimal example of the line-oriented analysis script (e.g., a jq or awk one-liner over the decompressed JSONL records) so the core interpretation step in section 3 is as executable as the capture step.

Condense the three inline external-skill install instructions in sections 1 and 5 into a single shared pattern (one sentence plus short skill names) to recover tokens.

Trim the snapshot-naming paragraph in section 2 to the essential rules: use distinct before/after names, and reuse of an explicit name replaces the prior capture.

DimensionReasoningScore

Conciseness

The body is dense operational guidance with no explanations of concepts Claude already knows, but the three inline external-skill install commands ("npx skills add https://github.com/vercel/next.js/tree/canary/skills/...") and the elaborate snapshot-naming paragraph ("Capture generates a unique timestamp name when omitted, and replaces an existing capture when an explicit name is reused") could be trimmed.

4 / 5

Actionability

Capture, export and schema-resolution commands are copy-paste executable ("pnpm exec next analyze --output --snapshot 'audit-before-unique-1'", "pnpm exec node -p \"require.resolve('next/analyze/graph-v1.schema.json')\""), but the core interpretation step ("Stream decompression ... into a line-oriented analysis script") and the min-cut solver invocations have no in-body example.

4 / 5

Workflow Clarity

Six numbered steps each end with an explicit "**Done:**" checkpoint, and validation is thorough: exit-status checking under pipefail ("pipefail prevents gzip from hiding a failed export"), "Discard output when export or gzip fails", "Revert a change that fails either condition", plus a graph-evidence checklist for the complex pass.

5 / 5

Progressive Disclosure

The body stays an overview and splits detailed methods into two well-signaled, one-level-deep references ("Read [Graph methods](references/graph-methods.md) before constructing the graph or running solvers") that exist as real leaf files in the bundle with no nested references.

5 / 5

Total

18

/

20

Passed

Description

82%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 compact, third-person description that clearly answers both what and when using concrete, natural trigger phrases and a well-defined Next.js niche. Its only weakness is that it names just two capability verbs, leaving the skill's specific actions implicit.

Suggestions

Name one or two more concrete capabilities in the what-clause (e.g., "capture analyzer snapshots, diff before/after bundle composition, dedupe browser dependencies") to raise capability specificity.

Add common user phrasings such as "bundle size", "slow page load" or "code splitting" as trigger synonyms alongside the existing terms.

DimensionReasoningScore

Specificity

Only two concrete actions are stated ("Audit and reduce Next.js browser initial-load work") — the same domain-plus-two-verbs structure as the anchor-3 example — and the remaining phrases describe use cases rather than capabilities, so it does not reach the "several specific actions" of anchor 4.

3 / 5

Completeness

It explicitly answers both what ("Audit and reduce Next.js browser initial-load work") and when ("Use for slow route startup, oversized client bundles, duplicate browser dependencies, or features that can wait for interaction") with four concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases a user would say are present ("slow route startup", "oversized client bundles", "duplicate browser dependencies"), but common variations such as "bundle size", "page load" or "code splitting" are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

"Next.js browser initial-load work" carves out a clear niche with distinct triggers (bundle bloat, initial-load deferral), creating minimal conflict risk with other skills.

5 / 5

Total

17

/

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

boranfurkan/planb-hackathon

Path

skills/.agents/skills/next-bundle-optimizer/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.