omni-cache

Manage the LLM response cache. View cache statistics, clear entries, configure TTL policies, and control semantic-similarity caching thresholds.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/omni-cache/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, well-organized API skill with copy-paste curl examples and appropriate deferral to the OpenAPI spec, but it is incomplete for the claimed TTL/threshold configuration capabilities and lacks validation guidance around destructive cache-clearing operations.

Suggestions

Add executable curl examples for the TTL-policy and semantic-similarity-threshold configuration endpoints that the description promises, rather than deferring all payload detail to the OpenAPI spec.

Add a validation/verification checkpoint for the destructive DELETE endpoints (e.g. inspect GET /api/cache/stats before and after, or require explicit confirmation) so the workflow includes a feedback loop.

Drop the redundant Overview section that restates the frontmatter description verbatim, or replace it with unique framing.

Dimension	Reasoning	Score
Conciseness	The body is lean — mostly copy-paste curl commands with no concept explanation Claude already knows; not level 2 because there is no padded or unnecessary explanation, though the Overview restates the frontmatter description verbatim.	3 / 3
Actionability	Provides concrete, executable curl examples for four endpoints, but is incomplete: the description promises configuring TTL policies and semantic-similarity thresholds yet no corresponding endpoint/example is shown, and request/response detail is deferred entirely to the OpenAPI spec; not level 3 because key actions lack copy-paste guidance, not level 1 because the shown commands are fully executable.	2 / 3
Workflow Clarity	Endpoints are listed clearly, but the destructive operations (DELETE /api/cache clears all caches, DELETE /api/cache/stats) have no validation or verification steps, which per the rubric guideline caps workflow clarity at 2; not level 1 because the structure is unambiguous, not level 3 because no confirm/verify checkpoints exist for destructive calls.	2 / 3
Progressive Disclosure	Short, well-sectioned body (Overview, Authentication, Endpoints, Payloads) that defers detailed schemas one level deep to the OpenAPI spec with clear signaling; no bundle files are present, and the simple, well-organized structure meets the 3 anchor for simple skills.	3 / 3
	Total	10 / 12 Passed

Description

82%

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 specific, third-person description with concrete actions and a clear niche, but it omits any explicit 'Use when...' trigger guidance, which caps completeness at 2.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when managing the LLM response cache, clearing cached responses, or adjusting TTL/semantic-similarity caching settings.'

Include common user phrasings (e.g. 'clear the cache', 'cache stats', 'cache hit rate') to broaden natural trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "View cache statistics, clear entries, configure TTL policies, and control semantic-similarity caching thresholds" — matching the multiple-specific-actions anchor; not level 2 because the action set is comprehensive rather than partial.	3 / 3
Completeness	Clearly answers "what" but has no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2; not level 3 because the "when" trigger is entirely absent rather than explicit.	2 / 3
Trigger Term Quality	Uses natural domain terms a cache-managing user would actually say ("cache statistics", "clear entries", "TTL policies"); not level 2 because coverage spans several distinct natural keywords rather than a single generic phrase.	3 / 3
Distinctiveness Conflict Risk	Targets a narrow, specific niche ("LLM response cache" with semantic-similarity caching) unlikely to overlap with other skills; not level 2 because the domain is distinctly scoped rather than generically phrased.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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: diegosouzapw/OmniRoute
Path: skills/omni-cache/SKILL.md
Commit: 3070925

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.