omni-cache

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

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

76%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 highly actionable with executable curl examples and no fluff, but it presents destructive cache-clearing operations without any validation or confirmation step, capping workflow clarity. Progressive disclosure is good with a small signaling gap on the payload reference.

Suggestions

Add a validation/confirmation checkpoint before the DELETE endpoints, e.g. 'Verify impact via GET /api/cache/stats before clearing; clearing is irreversible.'

Turn the Payloads pointer into a clear one-level reference, e.g. 'See docs/openapi.yaml for full request/response schemas' as a dedicated, labeled reference rather than an inline aside.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean endpoint listings with copy-paste curl commands and no padding of concepts Claude already knows; only minor repetition (the Overview restates the description verbatim) keeps it from a 5.	4 / 5
Actionability	Every endpoint is paired with a complete, copy-paste-ready curl command including auth headers and the real base URL/port, covering all the common operations.	5 / 5
Workflow Clarity	Endpoints are listed as independent operations with no sequencing, and the destructive DELETE endpoints (clear all caches, clear entries, clear stats) have no validation or confirmation checkpoint — the missing-feedback-loop cap for destructive/batch operations holds this at 3.	3 / 5
Progressive Disclosure	Content is organized into clear Overview/Authentication/Endpoints/Payloads sections and offloads detailed schemas to the OpenAPI spec, but the Payloads pointer ('GET /api/openapi/spec or docs/openapi.yaml') is loosely signaled rather than a clean one-level reference, leaving a minor gap.	4 / 5
	Total	16 / 20 Passed

Description

58%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 specific and action-oriented about cache management but omits any explicit 'Use when...' trigger guidance, which is the primary gap. Trigger term naturalness could be broadened.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user asks to inspect, clear, or tune the LLM response cache or adjust cache TTL/similarity settings.'

Include natural user phrasings and synonyms such as 'flush cache', 'cache hit rate', and 'cache tuning' alongside the technical terms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'View cache statistics, clear entries, configure TTL policies, and control semantic-similarity caching thresholds' — giving good coverage, though it stops short of the fully comprehensive list a 5 would show.	4 / 5
Completeness	It clearly answers 'what' the skill does but provides no 'when' / 'Use when...' clause, so the trigger condition is only weakly implied — a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	It uses domain terms like 'cache statistics', 'TTL policies', and 'semantic-similarity caching' but lacks the natural user phrasings and synonyms (e.g. 'flush cache', 'cache hit rate') one would actually say, leaving common variations missing.	3 / 5
Distinctiveness Conflict Risk	The cache-management niche is fairly distinct and unlikely to collide with unrelated skills; only minor overlap risk exists with broader admin/observability skills.	4 / 5
	Total	14 / 20 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: c3945a7

Reviewed: 3 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.