CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

next-partial-prefetching-optimizer

Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant, wants reusable content to wait for navigation, or needs to choose between default, viewport, and intent prefetching. Requires Next.js 16.3+.

Quality

83%

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%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, highly actionable workflow skill with an exemplary RED-to-GREEN loop, explicit validation checkpoints, differential verification, and a completion checklist. Its two weaknesses are the missing bundle files that the workflow depends on mid-stream (rig-template.md and reference/red-test-robustness.md are referenced as required reading but absent from the bundle), and some repetition of the unattended/handoff guidance across sections.

Suggestions

Include the referenced bundle files in the skill package: both `rig-template.md` and `reference/red-test-robustness.md` are cited as required reading at critical workflow moments (rig discovery, false-RED recovery) but are not present in the bundle, breaking the one-level-deep reference structure.

Consolidate the unattended-operation guidance, which appears in three places (intro paragraph, 'Reporting to the user', 'Handoff'), and the adoption-skill redirect, stated nearly verbatim in both the intro and Handoff — state each once in the most load-bearing location.

Add a minimal `instant()` test skeleton (one source link, one prefetched assertion, one deferred assertion) so the RED/GREEN loop is executable without first locating the linked guide's testing pattern.

DimensionReasoningScore

Conciseness

The body is dense, task-specific, and free of explanations of concepts Claude already knows — no primer on what prefetching or Next.js is; nearly every sentence pushes the workflow forward. Minor trimming is possible: the unattended/no-stopping instruction appears three times ("Run the workflow unattended...", "This loop runs unattended, so do not stop...", "Do not leave a build or test for the user to monitor"), and the adoption-skill redirect is stated nearly verbatim in both the intro ("This is not an adoption skill...") and the Handoff section. Not a 3 because these repetitions are confined and the rest earns its tokens; not a 5 because the redundancy is more than zero.

4 / 5

Actionability

Concrete and executable throughout for an instruction-only skill: exact paths ("node_modules/next/dist/docs/01-app/02-guides/optimizing-prefetching.md"), exact config ("experimental.exposeTestingApiInProductionBuild"), named APIs (instant(), navigation(), prefetch(), prefetch={true/false}), and a precise differential procedure (remove only the optimization, rerun, require RED, reapply, require GREEN). Not a 5 because no test or assertion skeleton is shown inline — the actual test shape is delegated to the linked guide's testing pattern and to bundle files — leaving minor gaps to close before writing code.

4 / 5

Workflow Clarity

The multi-step process is clearly sequenced with explicit validation checkpoints and feedback loops: define the contract → reuse/discover the rig → prove current behavior (unlocked scaffold, then locked RED with explicit false-RED recovery via red-test-robustness.md) → smallest optimization worked to GREEN one at a time → verify via remove/reapply differential → checklist and handoff. Error-recovery guidance is explicit ("A timeout before the URL changes... indicates a rig or route problem"), and the completion checklist reifies every checkpoint.

5 / 5

Progressive Disclosure

On paper the structure is good: a scoped overview, detail pushed to two one-level-deep bundle files declared in a Files section ("rig-template.md: production build, test context...", "reference/red-test-robustness.md: trustworthy RED and differential checks"), and a Further reading section for external docs. However, neither referenced bundle file exists in the provided bundle (no rig-template.md, no reference/ directory, no references/scripts/assets), so the references dangle and the split cannot be verified — scoring against the actual bundle structure per the judging guidelines caps this below the 4 the signaling alone would earn.

3 / 5

Total

16

/

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 strong description that explicitly answers both what the skill does and when to use it, with concrete Next.js-specific trigger phrases and clear preconditions that distinguish it from sibling adoption/optimizer skills. The main weakness is that the headline capability ('Optimize what ... navigations include before the click') is phrased somewhat abstractly rather than as a list of concrete actions.

DimensionReasoningScore

Specificity

The description names the domain ("Optimize what selected Next.js client navigations include before the click under Partial Prefetching") and one to two concrete actions — choosing "between default, viewport, and intent prefetching" — but the primary verb 'Optimize what ... navigations include' is abstract and the coverage of capabilities is not comprehensive. It is not a 4 because it does not list several distinct specific actions the way the anchor-4 example does; it is above a 2 because the actions named are concrete and domain-tied, not generic.

3 / 5

Completeness

Both 'what' ("Optimize what selected Next.js client navigations include before the click under Partial Prefetching") and 'when' ("Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant...") are explicitly stated with concrete trigger phrases, plus an explicit precondition ("Requires Next.js 16.3+"). This matches the anchor-5 example structure of clear what + explicit when with triggers.

5 / 5

Trigger Term Quality

Natural trigger phrases are present: "wants selected URL-specific UI to be instant", "wants reusable content to wait for navigation", "prefetching", "Next.js", "viewport, and intent prefetching". A user asking to make specific links instant or to tune prefetching would plausibly say these terms. Not a 5 because common variations like 'fast navigation', 'link hover', or 'load faster' phrasings are absent.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche — post-adoption Partial Prefetching tuning for Next.js — with distinct triggers (instant URL-specific UI, deferred reusable content, default/viewport/intent policy choice) and explicit scoping ("Use after Cache Components and Partial Prefetching are adopted", "Requires Next.js 16.3+") that separates it from sibling adoption and cache-components skills. Conflict risk is minimal.

5 / 5

Total

17

/

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

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

boranfurkan/reproducer-hackathon

Path

skills/.agents/skills/next-partial-prefetching-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.