Tessl • The management layer for AI agent skills

SkillPublic

redis-inspect

Inspect Redis cache keys, values, and TTLs for debugging. Supports both main cache and system cache. Use for debugging cache issues, checking cached values, and monitoring cache state. Read-only by default.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

82%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 highly actionable, well-organized single-file skill: complete commands, options, key-pattern tables, and a safety gate on the one write operation. Weaker spots are mild redundancy across sections and a missing pre-delete validation step; the ~140-line body is at the edge of what should stay inline.

Suggestions

Cut the redundant Cache Types subsection bullets (or the table's Purpose column) and fold Debugging Tips into Examples to remove repeated content — this is the cheapest conciseness win.

Add a pre-delete validation step in Write Operations (e.g. run `exists <key>` / `ttl <key>` and confirm the value with the user before `del ... --writable`) to create an explicit feedback loop around the destructive command.

Consider moving the Common Key Patterns reference (or the full command table) into a references/ file, leaving SKILL.md as a lean quick-start overview.

Dimension	Reasoning	Score
Conciseness	Mostly lean and table-driven with no background padding, but the opening sentence restates the description, the Cache Types table's Purpose column is repeated by the two subsections' bullet lists, and Debugging Tips largely re-runs Examples commands. Minor trimming would get it to anchor 5.	4 / 5
Actionability	Every example is a complete, copy-paste-ready invocation (e.g. `node .claude/skills/redis-inspect/query.mjs keys "user:*" --limit 20`), backed by a full command table, options table, and concrete key examples covering the common cases. Fully executable.	5 / 5
Workflow Clarity	The inspection path is clear (pick cache via --sys, locate keys via the pattern tables, then get/ttl/hgetall), and the single destructive op is gated by --writable plus an explicit permission instruction. Minor validation gaps remain: no suggested exists/ttl pre-check before del and no feedback-loop guidance, keeping it at anchor 4 rather than 5.	4 / 5
Progressive Disclosure	No bundle files exist, so the skill is a single well-sectioned SKILL.md; the only referenced path (query.mjs) is the tool itself and is consistently referenced throughout. Good structure and easy navigation, but at ~140 lines the command API, key-pattern reference, and examples could be split into a reference file, so it sits at anchor 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

87%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: concrete actions, an explicit 'Use for...' trigger clause, and a distinctive Redis-cache niche. The only weakness is that trigger-term coverage omits a few natural synonyms and the action list could cover more of the tool's commands.

Dimension	Reasoning	Score
Specificity	"Inspect Redis cache keys, values, and TTLs" plus "checking cached values" and "monitoring cache state" name several concrete actions, but coverage has minor gaps (no mention of hashes/sets/lists, server info, or deletion). Not comprehensive enough for 5, well beyond the 1-2 actions of anchor 3.	4 / 5
Completeness	Explicitly answers both: what ("Inspect Redis cache keys, values, and TTLs... Supports both main cache and system cache") and when ("Use for debugging cache issues, checking cached values, and monitoring cache state") with concrete trigger phrases. Matches the anchor-5 example pattern closely.	5 / 5
Trigger Term Quality	Natural terms users would say are present: "Redis", "cache", "TTLs", "debugging cache issues", "cached values", "monitoring cache state". A few common variations are missing (e.g. "check the cache", redis-cli-style phrasing), so it falls just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	"Redis" plus the cache-inspection framing carves out a clear niche with distinct triggers and minimal overlap risk with other skills; the read-only note further disambiguates intent.	5 / 5
	Total	18 / 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: civitai/civitai
Path: .claude/skills/redis-inspect/SKILL.md
Revision: a74d6fe

Reviewed: 1 month ago

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.

redis-inspect

Table of Contents

Is this your skill?