CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

runtime-cache

Vercel Runtime Cache API guidance — ephemeral per-region key-value cache with tag-based invalidation. Shared across Functions, Routing Middleware, and Builds. Use when implementing caching strategies beyond framework-level caching.

57

Quality

72%

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/vercel/skills/runtime-cache/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

An excellent, dense API reference with fully executable examples, accurate cross-system distinctions, and concrete limits — its main weaknesses are the lack of pre-purge validation for destructive operations, marketing/date padding in the Observability section, and a monolithic single-file structure instead of split reference files.

Suggestions

Move the CLI Cache Commands, Next.js Integration, and CDN Cache Tags sections into separate reference files (e.g. cli.md, nextjs.md), keeping SKILL.md as a lean overview with clearly signaled one-level-deep links.

Add a validation step before destructive or batch purge operations — e.g. verify the affected tags against the limits table (16 tags per bulk REST call, 64 per item) and confirm the target scope before running `vercel cache purge` or `dangerouslyDeleteByTag`.

Trim the Observability section's dashboard release details and remove or relocate the "(March 5, 2026)" dated release information to a changelog reference, keeping only what is needed to monitor hit rates and storage.

DimensionReasoningScore

Conciseness

The body is mostly a tight, non-obvious API reference with no explanation of concepts Claude already knows, but the Observability section pads with dashboard release marketing ("redesigned purging interface", "available on all plans and take effect instantly") and includes the time-sensitive date "(March 5, 2026)" outside any deprecated/old-patterns section, fitting anchor 3 rather than 4.

3 / 5

Actionability

Fully executable, copy-paste-ready guidance throughout: complete getCache/set/get/delete/expireTag snippets, a full fetch-handler caching example, a server action, concrete CLI commands with flags (e.g. "vercel cache dangerously-delete --tag blog-posts --revalidation-deadline-seconds 3600"), and a limits table — matching anchor 5.

5 / 5

Workflow Clarity

"When to Use" / "When NOT to Use" provide clear decision guidance and distinctions (e.g. "cache.expireTag() — operates on Runtime Cache only"), but destructive and batch operations ("vercel cache purge", "dangerouslyDeleteByTag") have no validation or verification steps before execution, so workflow clarity is capped at 3 per the rubric guideline.

3 / 5

Progressive Disclosure

Section headers are clear, but this is a ~230-line monolith with no bundle files at all: CLI command reference, Next.js integration, and CDN cache tag sections are inlined content that belongs in separate reference files, matching anchor 3 ("content that should be separate is inline") rather than 4.

3 / 5

Total

14

/

20

Passed

Description

70%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 well-formed description that clearly states what the skill covers and when to use it, with third-person voice and no fluff. Its main gaps are the thin set of concrete capability verbs and the absence of richer natural trigger terms (revalidate, purge, CDN).

DimensionReasoningScore

Specificity

"Vercel Runtime Cache API guidance — ephemeral per-region key-value cache with tag-based invalidation" names the domain and one concrete capability (tag-based invalidation), matching anchor 3 rather than 4 because no other concrete actions (store, retrieve, purge, CLI) are explicitly stated.

3 / 5

Completeness

It explicitly answers both: what ("ephemeral per-region key-value cache with tag-based invalidation") and when ("Use when implementing caching strategies beyond framework-level caching"). The 'when' clause is abstract rather than concrete user trigger phrases, so it does not reach anchor 5.

4 / 5

Trigger Term Quality

Natural terms users would say are present ("caching", "cache", "invalidation", "Vercel", "Functions"), but a few common variations such as "revalidate", "purge", or "CDN" are missing, which matches the anchor-4 example's coverage level.

4 / 5

Distinctiveness Conflict Risk

The Vercel Runtime Cache is a clear niche, and "beyond framework-level caching" distinguishes it from framework-level cache skills; however the broad phrase "caching strategies" leaves minor overlap risk with sibling Vercel cache skills (CDN cache, Data cache), fitting anchor 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

openai/plugins

Path

plugins/vercel/skills/runtime-cache/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.