CtrlK
BlogDocsLog inGet started
Tessl Logo

iris-development

Iris is Redis's umbrella for AI-focused products. Use this skill when integrating with the Iris Redis Agent Memory (RAM) data plane on Redis Cloud — recording session events for an AI agent, creating or searching long-term memories, configuring a memory store, or tuning background memory promotion. Code examples use the official `redis-agent-memory` (Python) and `@redis-iris/agent-memory` (TypeScript) SDKs.

70

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

Well-structured overview-and-index skill with excellent progressive disclosure and concrete, actionable entry points. The body keeps executable detail in references, so conciseness, actionability, and workflow clarity sit just below perfect rather than at the top anchor.

Suggestions

Remove the forward-looking 'Additional Iris products will be added as separate sections when they ship' line — it is non-actionable padding.

Drop or trim the 'How to Use' code block that re-lists three reference paths already linked in Quick Reference to avoid redundancy.

Surface one inline validation checkpoint in the body (e.g. the health() smoke test) so workflow clarity does not rely entirely on the references.

DimensionReasoningScore

Conciseness

Mostly lean: tables for SDKs and rule priorities are token-efficient and the body delegates code to references. Minor trim opportunities — the forward-looking 'Additional Iris products will be added… when they ship' and the How-to-Use file list duplicating the Quick Reference.

4 / 5

Actionability

Gives concrete install commands ('pip install redis-agent-memory'), env vars, the production data-plane URL, and exact method names; the full executable code lives in references, which are clearly linked, leaving only minor gaps in the body itself.

4 / 5

Workflow Clarity

Priority table + Quick Reference sequence the user clearly through the four categories, and validation/smoke-test/polling checkpoints exist in the references (e.g. health() smoke test, promotion polling). The body delegates those checkpoints rather than restating them, a minor gap.

4 / 5

Progressive Disclosure

SKILL.md is a lean overview indexing nine real one-level-deep reference files, each clearly linked with a one-line description; cross-references between bundle files stay sibling-level (e.g. session-add-event → session-retrieval) with no 2+ level nesting.

5 / 5

Total

17

/

20

Passed

Description

92%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, specific description that names concrete capabilities, gives an explicit Use-when clause, and carves out a distinct niche. Slightly technical phrasing in spots keeps trigger-term quality just below perfect.

DimensionReasoningScore

Specificity

Lists four concrete actions — 'recording session events for an AI agent', 'creating or searching long-term memories', 'configuring a memory store', 'tuning background memory promotion' — giving comprehensive coverage rather than just 1–2 actions.

5 / 5

Completeness

Explicitly answers both what (integrating with the RAM data plane across four tasks) and when ('Use this skill when integrating with…') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Covers natural domain terms (Redis Agent Memory, RAM acronym, session events, long-term memories, memory store, promotion) but leans on jargon like 'data plane' and omits looser user phrasings, so a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche — Redis Agent Memory on Redis Cloud via specific SDKs — with distinct triggers and minimal overlap with other skills.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
redis/agent-skills
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.