CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the `partialPrefetching` flag, opt routes in with `export const prefetch = 'partial'`, audit `Link prefetch={true}` behavior, preserve existing prefetched UI with `instant()` tests, or resolve the instant-link-prefetch-partial and instant-shell-url-data insights.

Quality

91%

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-adoption 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.

The body is a strong, deeply actionable runbook with an unusually rigorous validation gate and feedback loops, held back by a broken progressive-disclosure dependency: the repeatedly referenced `rig-template.md` is absent from the bundle, undermining the primary test-backed preservation path. Secondary costs are mild repetition of a few operational caveats. Fixing the missing reference file would materially raise both actionability and progressive disclosure.

Suggestions

Ship the referenced `rig-template.md` in the bundle (e.g., under references/) or inline its rig-setup and liveness-check content — the skill's primary path depends on it four times and it currently does not exist.

Deduplicate repeated caveats: state 'automatic prefetching runs only in production' once in the requires section and reference it from step 6, and consolidate the three occurrences of 'record the blocker and deferred test coverage' into the preservation gate.

Consider moving the step 5 URL-data insight taxonomy and the step 6 verification checklist into a one-level-deep reference file to slim the main SKILL.md, keeping the seven-step sequence as the overview.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational knowledge (preservation gate, shadow-root overlay access, codemod dirty-tree handling) and largely assumes Claude's competence, but includes repeated statements: "automatic prefetching runs only in production" appears in requires, the step 6 checklist, and the step 6 check-in; "record the blocker and deferred test coverage" appears three times; user-language guidance appears twice. These are minor, trimmable instances rather than pervasive padding, so this sits above the mostly-efficient-but-notable-excess anchor (3) and matches efficient-with-minor-trims (4); it falls short of lean-every-token-earns-its-place (5).

4 / 5

Actionability

Concrete, executable guidance dominates: `rg -n '\bprefetch\b|router\.prefetch' -g '*.tsx' -g '*.jsx' .`, `npx @next/codemod@canary remove-partial-prefetch ./app` with dirty-tree/`--force` and manual fallback handling, `npx skills add …`, and `find node_modules/next/dist/docs -name '<slug>.md'`. However, the primary test-backed path instructs "create it from **`rig-template.md`**" and "work through **`rig-template.md`** setup and liveness checks", yet no such file exists in the bundle (no references/, scripts/, or assets/ directories are present), leaving a real gap in copy-paste readiness for the main workflow. This is mostly-executable with a minor-to-material gap — above score 3, below the fully copy-paste-ready score 5.

4 / 5

Workflow Clarity

Seven explicitly sequenced steps with an up-front preservation gate ("Do not continue to step 3 until the suite has actually passed"), feedback loops (rerun unchanged tests after each destination and "treat failures as the work queue"), a pre-check-in verification checklist, and error-recovery guidance ("Before blaming a broken route on the flag, reproduce it with `partialPrefetching` off"; codemod fallback if unavailable). This matches the anchor with explicit validation steps, error-recovery loops, and checklists; score 4 would require missing checkpoints, and none are.

5 / 5

Progressive Disclosure

Scored against the actual bundle structure, which contains no files at all: the body's only bundle-file reference, **`rig-template.md`** (cited four times as the source for rig setup and liveness checks), does not exist, so a reader following the primary path hits a dead end. Internal section structure is good and external doc links are clearly signaled and one level deep, but ~185 lines of dense procedural detail are inlined and the one intended reference file is missing — matching 'some structure, references present but problematic' (3) rather than good structure with minor gaps (4), and well above minimal-structure (2) since headers and step ordering make the document navigable.

3 / 5

Total

16

/

20

Passed

Description

100%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 exemplary: third-person voice, concrete actions named with exact config keys and code, an explicit 'Use when' clause with six trigger conditions, and a distinct niche that is unlikely to fire for the wrong skill. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with exact API surface: "flip the `partialPrefetching` flag", "opt routes in with `export const prefetch = 'partial'`", "audit `Link prefetch={true}` behavior", "preserve existing prefetched UI with `instant()` tests", and "resolve the instant-link-prefetch-partial and instant-shell-url-data insights". This matches the comprehensive-coverage anchor; score 4 would require minor coverage gaps, and none are present.

5 / 5

Completeness

Both what and when are explicit: "Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces" (what) and "Use when the user wants to…" followed by six concrete trigger conditions (when). This mirrors the anchor example that clearly answers both with concrete trigger phrases; score 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

"Use when the user wants to enable or adopt Partial Prefetching" plus the flag name and route export captures the natural phrases a user would say for this niche feature — the feature name itself is the trigger term, alongside actionable variants ("flip the flag", "audit", "preserve", "resolve … insights"). No common natural phrasing is missing, so this exceeds the good-but-incomplete coverage of score 4.

5 / 5

Distinctiveness Conflict Risk

The description targets a single named Next.js feature with its own flag (`partialPrefetching`), route export, and insight slugs, giving it a clear niche with distinct triggers and minimal conflict risk against adjacent skills (e.g., general Cache Components or PDF/document skills). It is not merely 'somewhat specific' (score 3) nor does it carry minor overlap risk (score 4).

5 / 5

Total

20

/

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-partial-prefetching-adoption/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.